Abstract

Background
General practitioners play a pivotal role in the diagnosis attention-deficit/hyperactivity disorder (ADHD) in adults. This systematic review aims to determine the effectivity and feasibility of screening tools for ADHD in adults in primary care.

Method
A literature search was performed in PubMed, Cochrane Library, Ovid, ERIC, PsycInfo, PSYNDEX and Embase in November 2022. Sensitivity and specificity were considered as primary outcomes. Further psychometric properties, feasibility in general practice as well as digital practicability were evaluated as secondary outcomes. Risk of bias was assessed via QUADAS-2/C. A narrative data synthesis and meta-analysis was performed (PROSPERO: CRD42022374597).

Results
A total of fifty-eight studies were included in data analysis. These studies referred to eighty-four various screening tools. ASRS-6 (DSM-V), WURS-25, CAARS-s:sV and TRAQ10 are suitable instruments for screening of ADHD in adults in primary care. The highest test accuracy was shown by ASRS 6 (DSM-V) (Sensitivity=0.83 [0.67–0.92], Specificity=0.87 [0.93–0.8], AUC=0.92, I2=8.6–12.3 %).

Limitations
Included studies used rating scales as reference standard. Some studies compared study groups to control groups with an unknown ADHD status and there is a large degree of heterogeneity between the populations. Some studies referred to the best-balanced results of sensitivity and specificity under a certain cut-off, that has not been determined before.

Conclusion
Feasibility studies are needed to provide more evidence for WURS-25 and CAARS-s:sV. The determination of sufficient cut-offs is important, to improve the identification of ADHD in adults by general physicians.

Introduction

Attention-deficit/hyperactive disorder (ADHD) according to the Diagnostic and Statistical Manual of Mental Disorders 5th edition (DSM-5) and hyperkinetic disorder (F90) or attention deficit without hyperactivity (F98.8) according to the International Classification of Diseases, editions 10 and 11 (ICD-10/11)) is commonly known as a childhood disorder which is characterized by altered hyperactivity, inattention and impulsivity (Drechsler et al., 2020). These symptoms persist until adulthood in about 50 % of all diagnosed patients (Sibley et al., 2017, 2022). Moreover, patients show characteristic features, which include executive dysfunction, disorganization and emotional distress, leading to an impairment of their daily lives (Barkley, 1997; Wender, 1998). Common comorbidities are depression, borderline personality disorder, social phobia, anxiety, or substance abuse (Fayyad et al., 2017; Kessler et al., 2006). Although a prevalence of approximately 2–3 % of ADHD in adults is estimated, only 0.2–0.4 % are actually diagnosed in Germany (Fayyad et al., 2017; Bachmann et al., 2017; de Zwaan et al., 2012). A possible reason seems to be a gap in medical care for young adults in a time of transition after leaving the pediatric setting (Eklund et al., 2016; Robb and Findling, 2013). Moreover, ADHD might be masked by other psychiatric symptoms and comorbidities (Retz et al., 2013). A missing or failed diagnosis prevents access to optimal medical care in the form of an evidence-based treatment of affected adults. General practitioners are considered to act as so-called „gatekeepers“, a role that is characterized by the initial identification of patients (Kwon et al., 2023; French et al., 2020). Consequently, there is a distinct need for appropriate diagnostic tools in primary care, as has already been identified in relevant guidelines (Eom and Kim, 2023; National Institute for Health and Care Excellence: Guidelines, 2018). There are many different screening tools, which differ in relevant aspects of the disorder. Some screening tools evaluate childhood symptoms, whereas others focus on current adult symptoms. Some screening tools are based on DSM-5 criteria, others on Utah criteria or no specified criteria. They differ in time or way of application, number of items, and scoring methods. For example, the choice of cutoff scores in ADHD screening tools directly influences clinical decision-making, including the initiation of treatment interventions. A higher cutoff score may exclude individuals who, despite exhibiting significant symptoms, do not meet the stringent criteria, potentially denying them access to necessary interventions. Conversely, a lower cutoff score could lead to the inclusion of individuals with mild symptoms, leading to over-treatment. The variability in cutoff points complicates the determination of treatment eligibility, potentially affecting the efficacy and efficiency of ADHD management strategies. Until, there is no comprehensive overview of validated studies including a quantitative meta-analysis (Taylor et al., 2011). Therefore, the aim of the study was to evaluate screening tools for ADHD in adults, considering sensitivity, specificity and feasibility for primary care.

Conclusion

Our findings show that screening tools as the ASRS-6 (DSM-V), the WURS-25, the CAARS-s:sV and the TRAQ10 are suitable instruments for screening of ADHD in adults in primary care due to their high validity and perceived feasibility in this setting. The best evidence exists for the ASRS-6, which was included in our meta-analysis. For more evidence concerning feasibility of the WURS-25 as well as the CAARS-s:sV, which also were part of the meta-analysis, feasibility studies are required. Regarding other tests like the TRAQ10 with equivalent promising results but insufficient options of comparison there is a need of further validation studies to create more evidence in that part. The determination of cut-offs is of great importance since it affects the ability of a screening tool distinguishing between real and false positives respectively negatives. Further research is required to identify the optimal cut-off of the different tests for a general population sample as we find it in primary care. Hence, the identification of ADHD in adults by general physicians would be improved without leading to increased misdiagnoses.

Abstract

Background
Evidence on the association between single nucleotide polymorphisms (SNPs) in the vitamin D receptor (VDR) and depressive symptoms is inconclusive.

Objectives
The primary aim of the study was to investigate the association between SNPs in the VDR gene and depressive symptoms.

Methods
In a sample of older adults from the Longitudinal Ageing Study Amsterdam (n = 922), depressive symptoms were assessed using the Centre for Epidemiological Studies Depression scale (CES-D scale) at baseline and after 3, 6, and 10 y of follow-up. Blood samples for SNP and serum 25-hydroxyvitamin D3 (25(OH)D3) determination were obtained at baseline. The association between 13 SNPs in the VDR gene and the course of depressive symptoms were evaluated using linear mixed models. The interaction between SNPs and serum 25(OH)D3 in relation to depressive symptoms was evaluated using multiple linear regression.

Results
No SNPs were associated with the course of depressive symptoms. Significant interactions between serum 25(OH)D3 and SNPs in the VDR gene were found. Stratified analysis revealed that within the GG genotype strata, 10 nmol/L higher serum 25(OH)D3 was associated with 0.27 (95% CI: −0.50, −0.04) and 0.23 (95% CI: −0.48, 0.02) lower scores on the CES-D scale for Cdx-2 and 1b-G-886A, respectively. This association was not found in persons having the GA or AA genotype.

Conclusions
No SNPs is associated with the course of depressive symptoms. Stratified analysis shows that the effect of serum 25(OH)D3 concentrations on depressive symptoms is different among genotypes of Cdx-2 and 1b-G-886A. Future research should elucidate on the function of Cdx-2 and 1b-G-886A to describe their effect.

Introduction

Depressive symptoms follow a U-shaped relationship with age, increasing again after the age of 60–65 y [1]. This is, however, not solely due to aging and varies widely between people [2]. A higher medical burden [3], aging-related anxiety [4], and nonhealth-related events [5] have been associated with depressive symptoms in older adults. The prevalence of depressive symptoms in older adults is estimated at 17% [6], but they are often overlooked [7] due to the overlap with symptoms, among others [6,8]. The burden will continue to rise due to the aging population and increasing life expectancy [9], thereby increasing years lived with disease [10] and societal costs [11].

Different factors (e.g., biological, social, and psychological) play a role in the onset and course of depressive symptoms [[12], [13], [14], [15]]. Vitamin D – a modifiable risk factor of which the status decreases with age [16] – has been associated with the course of depressive symptoms. In a previous study of the Longitudinal Ageing Study Amsterdam (LASA), an association between low vitamin D status and an increase in depressive symptoms among women was observed [17]. Two recent meta-analyses found a similar association in both men and women [18,19]. Genetic factors, such as single nucleotide polymorphisms (SNPs) in vitamin D-related genes may influence the response to, and therefore the requirement of, vitamin D [20]. The vitamin D receptor (VDR) gene encodes the VDR, the transporter of active vitamin D (1,25(OH)2D), and thereby influences the availability of 1,25(OH)2D [21].

Results

The study sample consisted of 922 participants who were on average 75.6 (SD 6.6) y old, were 51% women, and had a median CES-D score of 13.6 (IQR: 11.6–15.6). The prevalence of depressive symptoms [40] and antidepressant use at baseline was 24% and 2.5%, respectively. Mean serum 25(OH)D3 concentration was 46.6 nmol/L (SD 17.7), mean BMI was 26.6 kg/m2 (SD 5.2), and median physical activity in minutes per week was 128.6 (IQR: 67.7–189.7). The basic characteristics are summarized in Table 1 [35,36,40]. Compared with nonresponders, participants in the study sample were older and more often women, never smokers, moderate-to-excessive alcohol users, and more often had 2 or more comorbidities (all P < 0.05; Supplemental Table 2). The minor allele frequency was smallest for 282 W (n = 63/919; 3%), and no SNPs departed from Hardy–Weinberg equilibrium (Supplemental Table 1).

Abstract

Purpose
Given the increase in demand for optometry services by society and the importance of the Optometry profession in Portugal and Spain, the objective of this study was to determine job satisfaction and important factors related to this satisfaction in a sample of Portuguese and Spanish optometrists.

Methods
A prospective, cross-sectional, and observational study was carried out from June to December 2021. An adaptation of the 15-item job satisfaction in eye-care personnel (JSEP) questionnaire validated by Paudel et al. was administered to Portuguese and Spanish optometrists. The questionnaire was shared through different social media (Facebook, LinkedIn, WhatsApp, etc.) in a Google form during the months of June to December 2021 in Portugal and Spain.

Results
A total of 530 surveys were collected in Portugal (42.3%; n = 224) and Spain (57.7%; n = 306). The factors that most influence overall job satisfaction are salary, career development opportunities, recognition/prestige in society, good work-life balance (all p<0.001), workplace equipment and facilities, and encouragement reward positive feedback (both p = 0.002). When comparing the determinants of job satisfaction of optometrists, it was found that Portuguese professionals were generally more satisfied than Spanish ones (p<0.001). However, Spanish optometrists reported feeling more supported by their colleagues (p<0.001).

Conclusion
This study has shown that the level of job satisfaction was higher in Portugal than in Spain. The most important factors influencing job satisfaction were salary, job stability, and support from colleagues.

Introduction

Job satisfaction is defined as the feelings or emotions that connect workers to their jobs.1 Thus, it is known as “the positive emotional state resulting from the evaluation of one´s work or work experiences.”2 or “the extent to which people like or dislike their job.”3 That is, the attitude of workers towards their work in general, or more specifically, towards their colleagues, payroll, or working conditions. An employee may experience different job satisfaction through job stability, professional development, and growth, as well as a balanced work-life situation. Conversely, job stress can lead to burnout by decreasing people´s abilities to meet the demands of the job. In other words, an adequate workload can improve workers’ skills and enhance their success at work.4

Job satisfaction is considered a protective factor against burnout and the negative consequences of work-related stress.5 In healthcare professionals, job satisfaction is vital, as burnout can directly affect the health of patients and the quality of health care.6 Thus, job satisfaction is comprised of working conditions, communication, nature of work, organizational policies and procedures, salary and conditions, opportunities for promotion (also progression, recognition, or appreciation), safety, and supervision or relationships.7 Job satisfaction is also influenced by various factors, such as working conditions and organizational environment, stress levels, role conflict and ambiguity, role perceptions and content, and organizational and professional commitment.7, 8, 9, 10

Conclusion

This study has shown that the level of job satisfaction of the surveyed health professionals satisfied or very satisfied was higher in Portugal (74.1%) than in Spain (45.4%). The most valuable factors were support from colleagues, job stability, and workplace equipment and facilities; while the least valued factors were recognition/prestige in society, non-financial incentives, and career development opportunities.

Abstract

Employing the Internet of Things (IoT) in healthcare provides many advantages for patient monitoring and analysis of the patient’s health with the help of generated data. The basic role of IoT in healthcare is to ease the patient’s life by giving them a monitor over their medical condition. The use of IoT in medical devices requires a focus on the end-user. Medical devices such as glucose meters are designed to record the data of the patient and their vital signs. The generated information can be used to enhance decision-making for the physician. The collected information about the patient can be at risk due to certain security issues during the transferring of information can compromise the identity and social life of the patient. This review explores the IoT regarding its structural requirement and its role in various fields with special emphasis on healthcare. The security and privacy issues than can hinder the utilization of IoT at its potential and ways to overcome these issues are being addressed.

Role of IoT in medical devices

Medical Devices (MDs) are any instrument, reagent, apparatus, implement, machine or any other in-vitro reagent or calibrator, software which is intended to be used alone or in combination for the diagnosis, mitigation, prevention, treatment or alleviation of diseases in human beings.1 Generally, MDs are classified based on the risk associated with them. As per USFDA MDs are classified into three categories I, II, III where category I has lowest risk and category III has highest risk as shown in Table 12 (see Fig. 4)A report from Fortune Business Insights states that from 2018 to 2025 the Medical Device Industry will experience major investment in Research & Development of new technology from pharmaceutical players, approvals from regulatory authorities will also contribute to increase this number. The medical device global market was USD 42.5 Billion in 2018 and is estimated to reach USD 612.7 Billion by 2025. CAGR is expected at 5.4 % from 2018 to 2025.3

Further Medical Devices have been showing an increasing growth in the previous decade and with promising technology and innovations being made, it will keep growing more. Although there is conventional research and development being done by existing companies. With the entry of giants like Apple and Google, new technological advancements in the form of Artificial Intelligence, Data Analytics and Internet of Things (IoT) are being implemented in this sector.4

Conclusion

The amalgamation of a variety of technology is required to build an IoT. Due to this complexity, the system becomes more vulnerable to security and privacy threats. The generic engineering framework involved in patient monitoring remotely should meet the security requirements with the help of cryptographic algorithms. These algorithms should be device-specific to nurture the design & environment of patient-specific needs. The security and safety issues of a patient which arise from the application of IoT cannot be solved with the help of a single solution. To practice, the best security controls an informed user is also necessary. The management ability of the network and device automation can be of great help to deliver patient well-being and care. Delivering healthcare to patients efficiently and effectively, independent of time and location requires a new paradigm that is opened by IoT. The existing foundations of telemedicine have now been extended and better assessment of normal public health in a cohort sense has shifted the passive involvement of patient data gathering. Improving the outcomes for the patient and reducing the care cost are being balanced against the privacy and confidentiality of data and threats of cyber security. There is a vast source of data collection and potential to transfer clinical data, but there is a challenge to triage this data for clinical use. The cyber security and safety of patient data need to move faster than regulation and implementation of policy. The way forward for IoT needs superior standards every day to use the connected devices.

Abstract

Introduction
Child morbidity and mortality in resource-limited settings is a major public health problem. The previous studies were mainly concerned with determining the prevalence of child deaths and identifying associated factors. Extracting knowledge and discovering insights from hidden patterns in child data through supervised machine learning algorithms is limited. Therefore, this study aimed to predict the under-five death of children using a best performance-supervised machine learning algorithm.

Methods
A total of 1813 samples were used from the 2019 Ethiopian Demographic and Health Survey dataset. 70% and 30% of total instances were used for training the model and measuring the performance of each algorithm with 10-fold cross-validation techniques respectively. Five supervised machine learning algorithms were considered for model building and comparison. All the included algorithms were evaluated using confusion matrix elements. Information gain value was used to select important attributes to predict child deaths. The If/then logical association was used to generate rules based on relationships among attributes using Weka version 3.8.6 software.

Results
J48 is the second-best performance algorithm next to the random forest to predict child death, with 77.8% and 93.9% accuracy, respectively. Late initiation of breastfeeding, mothers with no formal education, short birth intervals, poor wealth status of the mother, and unexposed to media were the top five important attributes to predict child deaths. A total of six associated rules were generated that could determine the magnitude of child deaths. Of these, if children were rural residents, had a short birth interval, and if born as multiples (twins), then the probability of child death was 83.6%.

Conclusions
Five machine learning algorithms were included to predict child deaths and generate rules. Hence, the random forest algorithm was the best algorithm to predict child deaths. However, the study was limited since important attributes were not included in the data source, and irrelevant values were found. So, researchers are encouraged to use machine learning algorithms for future studies including important attributes that could predict child death. The current findings would be useful for stakeholders’ preparedness, and taking proactive childcare interventions. Encouraging women in education, media access, and economic development programs are essential interventions for child death reduction.

Introduction

Under-five mortality is the most important indicator to measure the health status of children, and it is a key marker for the development of countries [1]. The under-five mortality rate is the probability of children dying before their fifth birthday [2]. Globally, nearly 44% of all under-five deaths occurred before their first month of birth [3], and an estimated 4.1 million child deaths occurred in 2017 [4]. According to the Centers for Disease Control and Prevention, child mortality in the United States in 2020 was predicted to be 5.4 deaths per 1000 live births [5].

The risk of under-five mortality is highest in low-income countries. The under-five mortality rate in low-income countries was predicted to be 69 deaths per 1000 live births in 2017, which is almost 14 times the rate in high-income countries [6,7]. In Bangladesh, 522 under-five children died per 1000 live births [8]. In 2001, under-five mortality in Nepal was projected to be 91 deaths per 1000 live births [9]. Though under-five mortality shows a reduction from 166 to 67 per 1000 live births over a period of 16 years [10], Ethiopia appears to have the fifth-highest number of new-born deaths in the world [11]. Under-five mortality is projected to cause 472,000 children to die annually in Ethiopia before their fifth birthday, which places Ethiopia sixth in the world according to the number of under-five deaths [7,12]. According to WHO 2017, more than half of under-five deaths are due to infectious diseases that are easily preventable and treatable through simple and affordable interventions [13]. Under-five mortality is also caused by undernutrition, which further leads to stunting and wasting [14].

Conclusions and recommendations

This study aimed to identify the best-supervised machine learning algorithms to classify and select important attributes to predict the death of children before their fifth birthday. In line with the objectives, six supervised machine learning algorithms were considered that accurately predict the death of children before celebrating their fifth birthday. Different confusion matrix element was used to compare the candidate-supervised machine learning algorithms. Based on the result, the random forest algorithm was the best performance model to predict the death of children before celebrating their fifth birthday. Attributes such as late initiation of breastfeeding, mothers with no formal education, the short birth interval, poor wealth status of the mother, and being unexposed to media were the top important attributes to predict child deaths.

Generating associated rules for child death was another objective of the study. Accordingly, six rules were generated that were associated with the deaths of children before celebrating their fifth birthday. The findings of this study would have practical implications by supporting policymakers and stakeholders in developing childcare intervention mechanisms and preparing themselves to care for children as early as possible. Stakeholders are recommended to encourage mothers to initiate breastfeeding at the appropriate time. Improving mothers’ wealth status, closing the gap in media access, and creating awareness among mothers would be critical interventions to enhance the survival of children in Ethiopia. The generated rules would also have theoretical implications by extracting and representing knowledge. Moreover, researchers would use this study as a baseline and framework for further research studies, including important attributes that would predict child mortality in low-income countries.

Abstract

Lymphoma and leukemia are fatal syndromes of cancer that cause other diseases and affect all types of age groups including male and female, and disastrous and fatal blood cancer causes an increased savvier death ratio. Both lymphoma and leukemia are associated with the damage and rise of immature lymphocytes, monocytes, neutrophils, and eosinophil cells. So, in the health sector, the early prediction and treatment of blood cancer is a major issue for survival rates. Nowadays, there are various manual techniques to analyze and predict blood cancer using the microscopic medical reports of white blood cell images, which is very steady for prediction and causes a major ratio of deaths. Manual prediction and analysis of eosinophils, lymphocytes, monocytes, and neutrophils are very difficult and time-consuming. In previous studies, they used numerous deep learning and machine learning techniques to predict blood cancer, but there are still some limitations in these studies. So, in this article, we propose a model of deep learning empowered with transfer learning and indulge in image processing techniques to improve the prediction results. The proposed transfer learning model empowered with image processing incorporates different levels of prediction, analysis, and learning procedures and employs different learning criteria like learning rate and epochs. The proposed model used numerous transfer learning models with varying parameters for each model and cloud techniques to choose the best prediction model, and the proposed model used an extensive set of performance techniques and procedures to predict the white blood cells which cause cancer to incorporate image processing techniques. So, after extensive procedures of AlexNet, MobileNet, and ResNet with both image processing and without image processing techniques with numerous learning criteria, the stochastic gradient descent momentum incorporated with AlexNet is outperformed with the highest prediction accuracy of 97.3% and the misclassification rate is 2.7% with image processing technique. The proposed model gives good results and can be applied for smart diagnosing of blood cancer using eosinophils, lymphocytes, monocytes, and neutrophils.

Introduction

Leukemia and lymphoma are the most frequent kinds of blood cancer in people of all ages, particularly young people. This abnormal situation is induced by red blood cell proliferation and immature growth, which can harm red blood cells, bone marrow, and the immune system [1]. Leukemia accounts for more than 3.5% of new cancer cases in the United States, with over 50,000 new cases diagnosed in 2018 [2]. Cancerous lymphoblasts in the blood travel to other organs, including the heart, brain, lungs, and arteries, before spreading to important tissues throughout the body. Red blood cells are normally in charge of transporting oxygen from the heart to all organs. They make up half of the total blood volume. White blood cells, on the other hand, serve an important role in the human immune system, serving as the first line of protection against a variety of diseases and disorders [3]. As a result, accurately identifying these white blood cells is crucial in understanding the symptoms of the problem. Their categorization is determined by their cytoplasmic composition. Changes in lymphocytes, a kind of white blood cell, cause acute lymphoblastic leukemia [4]. Acute or chronic leukemia are the two types of leukemia. Without treatment, the typical recovery period for acute myeloid leukemia is roughly three months; however, the time of appearance of chronic leukemia is longer than that of acute leukemia. Chronic lymphoblastic leukemia is the most common kind of acute leukemia, accounting for around 25% of all juvenile malignancies [5, 6]. Early detection of leukemia and lymphoma has always been difficult for researchers, clinicians, and hematologists. Leukemia symptoms include enlarged lymph nodes, paleness, fever, and weight loss, although these symptoms can also be caused by other diseases [7]. Because of the moderate nature of the symptoms, diagnosing leukemia and lymphoma in its early stages is challenging. PBS microscopic assessment is the most often used leukemia and lymphoma diagnostic approach, while the gold standard for leukemia and lymphoma diagnosis only entails obtaining and analyzing white blood cell samples [8]. Several research have utilized machine learning and deep learning and machine diagnostics approaches to laboratory image processing during the last two decades in the hopes of pushing the boundaries of late diagnosis of leukemia and lymphoma and establishing their subtypes [9]. In this research, blood smear pictures were evaluated to diagnose, distinguish, and count cells in distinct kinds of leukemia and lymphoma [10].

Conclusion

The early detection of blood cancer using white blood cells can help meritoriously in its cure. The study’s proposed framework consists of three transfer learning models AlexNet, MobileNet, and ResNet empowered with SGDM, ADAM, and RMSPROP. The proposed framework applies all transfer learning models with varying learning rates effectively to white blood cancerous cells for early classification. To enhance the results, the proposed study used image processing techniques incorporating transfer learning and achieved the highest CA of 97.3% and 2.7% MCR. All experiments in the proposed study are comprehensively explained with respect to every model training and testing phase. This study helps health 5.0 to predict blood cancer in its early stages for early treatment. Furthermore, in the future, federated machine learning using the fed average technique will play a major role in better early prediction of blood cancer empowered with fuzzed machine learning and deep learning techniques will also apply more statistical techniques such as ANOVA and Chi-Square.

ABSTRACT

Electroencephalography (EEG) plays a vital role in detecting how brain responses to different stimulus. In this paper, we propose a novel Shallow-Deep Attention-based Network (SDANet) to classify the correct auditory stimulus evoking the EEG signal. It adopts the Attention-based Correlation Module (ACM) to discover the connection between auditory speech and EEG from global aspect, and the Shallow-Deep Similarity Classification Module (SDSCM) to decide the classification result via the embeddings learned from the shallow and deep layers. Moreover, various training strategies and data augmentation are used to boost the model robustness. Experiments are conducted on the dataset provided by Auditory EEG challenge (ICASSP Signal Processing Grand Challenge 2023). Results show that the proposed model has a significant gain over the baseline on the match-mismatch track.

INTRODUCTION

ICASSP 2023 Auditory EEG Challenge is designed to explore the relationship between auditory stimulus and evoked EEG signal. In this paper, we mainly focus on the first (match-mismatch) task. Traditional methods [1] adopt the linear model to fit the feature transform from the stimulus to the EEG signal. Recently, deep learning based methods have been proposed to improve the performance of relating speech with EEG signal[2, 3], where the feature transform modules are replaced by long context model, such as long short-term memory (LSTM), stacked dilated Convolutional blocks, etc.

CONCLUSION

The objective of the study is to learn the relationship between auditory stimulus and EEG. We propose a SDANet model with ACM and SDSCM to increase the crossing linkages rather than treating them separately. Results show that our model improves the classification accuracy effectively.

Abstract

Electroencephalography (EEG), which tracks the brain waves that contain the brain’s neural activity, plays an essential role in detecting human motion and treating neurological diseases. In the Artificial Intelligence (AI) era, deep learning algorithms are widely used in human action recognition and classification. Various convolutional neural networks that process this signal are also being born. This paper provides a detailed survey of the application of deep learning to EEG signals and outlines the research process when classifying EEG signals. At the same time, this paper reviews the relevant research on the classification of human action EEG signals in recent years. Human motion signals usually use different deep learning algorithms and convolutional neural network architectures in the EEG signal analysis task. This article will discuss the advantages and challenges of each method in other studies. Finally, the paper discusses future directions for deep learning-based EEG signal classification.

Abstract

Depression is a disorder that if not treated can hamper the quality of life. EEG has shown great promise in detecting depressed individuals from depression control individuals. It overcomes the limitations of traditional questionnaire-based methods. In this study, a machine learning-based method for detecting depression among young adults using EEG data recorded by the wireless headset is proposed. For this reason, EEG data has been recorded using an Emotiv Epoc+ headset. A total of 32 young adults participated and the PHQ9 screening tool was used to identify depressed participants. Features such as skewness, kurtosis, variance, Hjorth parameters, Shannon entropy, and Log energy entropy from 1 to 5 sec data filtered at different band frequencies were applied to KNN and SVM classifiers with different kernels. At AB band (8–30 Hz) frequency, 98.43 ± 0.15% accuracy was achieved by extracting Hjorth parameters, Shannon entropy, and Log energy entropy from 5 sec samples with a 5-fold CV using a KNN classifier. And with the same features and classifier overall accuracy = 98.10 ± 0.11, NPV = 0.977, precision = 0.984, sensitivity = 0.984, specificity = 0.976, and F1 score = 0.984 was achieved after splitting the data to 70/30 ratio for training and testing with 5-fold CV. From the findings, it can be concluded that EEG data from an Emotiv headset can be used to detect depression with the proposed method.

Introduction

Depressive disorder is a highly prevalent mental illness. Sadness, loss of interest or enjoyment, feelings of guilt or low self-worth, interrupted sleep or food, fatigue, and difficulty concentrating are some characteristics of depression. It may affect a person’s capacity to operate in daily life or at work or school. According to the World Health Organization (WHO) back in 2015, almost 4.4% of the world’s population was suffering from depression [1]. Because of the COVID-19 pandemic, many people suffered from depression due to job loss, study hampering, losing close relatives, staying indoors, etc. A study showed 19.3% increase in depression symptoms among people after COVID-19 in the United States [2]. A study has shown the changes in obsession, depression, and quality of life in schizophrenia patients before and after COVID-19 [3]. When depression is severe it can lead to suicide. Every year around 800 thousand people die because of suicide [1]. In 2017, 13.2% of young adults (aged 18–25) in the U.S. suffered from depression which was 5.1% less in the year 2009 [4]. Of the deaths of young people, around 9.1% are due to suicide [5]. In most suicide cases, people had psychiatric disorders where depression is the most common disorder among others [6]. According to a recent study, insecure attachment styles are linked to greater problems such as depression, social anxiety, and suicidal thoughts [7]. So, depression is a major issue that should be diagnosed and treated at an early age to prevent suicide and for the betterment of the quality of life.

Conclusion

In this work, we have recorded EEG data of young adults (19 depressed and 13 Control) evaluated by the PHQ9 screening tool and proposed a machine learning approach to learn about the EEG properties for depression detection.

We conducted multiple experiments with the reported machine learning (SVM and KNN) classifiers with our recorded data. The first experiment we conducted was on segmentation to find the better sample length suitable for ML. From our experiments, we have identified that 5-second segments are suitable for our work. Then, we have identified a suitable frequency range from various experiments that improve performance using features that are related to depression detection. We have found out that Hjorth parameters along with Shannon entropy and long energy entropy provide better results among other reported features and the beta band (12–30 Hz) gives the highest accuracy of 97.21 ± 0.21% with 25 iterations and 5-fold CV using weighted KNN compared to the other sub-bands. By combining the sub-bands, we have also investigated some other frequency ranges. We have found out that by taking the range from alpha to beta 8–30 Hz (AB), we can improve ML performance and achieve 98.43 ± 0.15% accuracy with 25 iterations and a 5-fold CV with fine KNN classifier. Using AB (8–30 Hz), we can see a significant improvement of 1.22% accuracy and slandered deviation. To further investigate the reliability, we divided the dataset 70/30 for training and testing with 5-fold CV and 10 iterations. In this experiment, we have found out that the ML performance is better by choosing the AB (8–30 Hz) band with fine KNN classifier with an accuracy of 98.10 ± 0.11%, precision of 0.984 ± 0.003, NPV of 0.977 ± 0.002, sensitivity of 0.984 ± 0.002, specificity of 0.976 ± 0.005, and F1 score of 0.984 ± 0.001. Then, we analyzed the ML performance in different regions of the brain and concluded that using the whole brain for depression detection will give the highest accuracy. The proposed method can detect depression among young adults with minimum requirements compared to other related works.

Abstract

     The increased accuracy and exhaustivity of modern Artificial Intelligence techniques in supporting the analysis of complex data, such as medical images, have exponentially increased real-world data collection for research purposes. This fact has led to the development of international repositories and high-performance computing solutions to deal with the computational demand for training models. However, other stages in the development of medical imaging biomarkers do not require such intensive computing resources, which has led to the convenience of integrating different computing backends tailored for the processing demands of the various stages of processing workflows. We present in this article a distributed and federated repository architecture for the development and application of medical image biomarkers that combines multiple cloud storages with cloud and HPC processing backends. The architecture has been deployed to serve the PRIMAGE (H2020 826494) project, aiming to collect and manage data from paediatric cancer. The repository seamlessly integrates distributed storage backends, an elastic Kubernetes cluster on a cloud on-premises and a supercomputer. Processing jobs are handled through a single control platform, synchronising data on demand. The article shows the specification of the different types of applications and a validation through a use case that make use of most of the features of the platform.

Introduction

     Increasingly, radiology is based on objective and quantifiable data extracted from Quantitative Imaging Biomarkers (QIBs). QIBs are quantitative indicators generated from structural, functional, physiological or biological characteristics of pathological lesions [1]. In the workflow development of QIBs, complex computational functions and models automatically extract attributes, namely radiomics features, from different types of radiological images to correlate them to the phenotype or genetic signatures of the lesions. These analyses aim to early detect and classify anomalies to predict prognostics, define follow-up results, or non-invasively assess the treatment response.

     In the last years, developers have analysed the images by learning from retrospective data, enriching radiomics features with demographic, clinical, liquid biopsies and genomic data because they improve the clinical value of the biomarkers [2]. Thus, gathering data processes are crucial to developing useful Clinical Decision support Systems (CDSS) based on QIBs in clinical practice, requiring a massive storage and high-performance computing capacity [3] for managing data on image biobanks. Furthermore, the huge amount of data makes traditional statistical analyses impractical, leading to a transition to novel textitArtificial Intelligence (AI) solutions such as Deep Learning [4]. Running AI algorithms efficiently requires high-computing performance resources [5] connected to the data storage backends.

Conclusions

     This work describes the design, implementation and validation of a software architecture to support the development and application of Quantitative Image Biomarkers. It implement a federated model to synchronise data among the different storage backends linked to different processing environments, including both Cloud and HPC resources. The architecture provides a federated Authentication and Authorisation Infrastructure based on Virtual Organisations that provide coherent and scalable authorisation management across the different providers. The processing backend is supported by a Kubernetes container management platform that runs the platform services and customised applications. The architecture is the outcome of a requirement elicitation process and uses mainstream, widely available components.

      The architecture uses the abstraction of the batch, High-Throughput-Compute, High-Performance computing and Interactive jobs to provide a simplified framework to develop applications with POSIX access to the distributed storage backends. HPC Jobs are managed through a mirror Kubernetes job that interacts with HPC batch queues to provide a seamless and coherent environment.

Abstract

This study aimed to investigate the application of machine learning techniques for disease prediction. Three popular machine learning algorithms, Random Forest, Support Vector Machines and Naive Bayes, were employed and their performance was evaluated. Results showed that the best performing model was based on Random Forest algorithm with the average accuracy of 87%. This model has been additionally tuned in order to achieve even better performance, which resulted with 90% accuracy. This study highlights the potential of AI in disease prediction and provides insights into the importance of algorithm selection and tuning for optimal performance.

Introduction

From a mathematical perspective, learning can bedefined as gaining awareness through study, experience, analysis, or instruction. Nevertheless, when given much thought, the process of learning cannot be described by merewords, since it is a subject to change and is unique for every individual [1]. In machine learning, pattern recognition serves as the basis for computational learning. Data which is fed into it as input is used to extract knowledge or information. [2]. This field represents a crossroads between mathematics, which provides all of the methods, concepts and theories that are relevant to the field, statistics, which specializes in making predictions based on the data available, and artificial intelligence, which is nowadays a shorthand for any task which a computer is capable of performing on par with or better than an individual. With the advent of machine learning, the indivisible component of ourlives has morphed into an integral part of our lives [3]. The algorithms of machine learning are strongly influencing us,whether they are used for selecting a movie or a TV series to watch or guiding you through the process of resetting your mixer (chatbots). There are a number of fields that are being impacted by this evolution, including transportation, gaming, environmental protection, security, media, healthcare, and the list is endless [4]. It is estimated that the world will have ashortage of 12.9 million health care workers by 2035,which if not addressed soon may have serious implications for the health of billions of people around the globe.

Conclusion

This research was focused on building the ML model that would be able to predict patient’s disease based on given symptoms. It consisted part of data preparation and augmentation, building three models based on three different classification algorithms and then evaluating their results.

In our case, the model which accomplished the best results was the Random Forest model, was further tuned and trained in order to achieve better accuracy. Final model accuracy was improved by 3% using Grid Search CV technique. However, further exploring of dataset and developing of the model that uses deep neural networks will be subject of our further research in order to determine whether or not it is possible to achieve even higher accuracy then what was presented in this paper.

Abstract

     Stuttering is a neurodevelopmental disorder affecting 5–8 % of preschool-age children, continuing into adulthood in 1 % of the population. The neural mechanisms underlying persistence and recovery from stuttering remain unclear and little information exists on neurodevelopmental anomalies in children who stutter (CWS) during preschool age, when stuttering symptoms typically first emerge. Here we present findings from the largest longitudinal study of childhood stuttering to date, comparing children with persistent stuttering (pCWS) and those who later recovered from stuttering (rCWS) with age-matched fluent peers, to examine the developmental trajectories of both gray matter volume (GMV) and white matter volume (WMV) using voxel-based morphometry. A total of 470 MRI scans were analyzed from 95 CWS (72 pCWS and 23 rCWS) and 95 fluent peers between 3 and 12 years of age. We examined overall group and group by age interactions in GMV and WMV in preschool age (3–5 years old) and school age (6–12 years old) CWS and controls, controlling for sex, IQ, intracranial volume, and socioeconomic status. The results provide broad support for a possible basal ganglia-thalamocortical (BGTC) network deficit starting in the earliest phases of the disorder and point to normalization or compensation of earlier occurring structural changes associated with stuttering recovery.

Introduction

     Developmental stuttering is a complex neurodevelopmental disorder (Smith and Weber, 2017) that disrupts the fluent flow of speech production. It is characterized by frequently occurring involuntary repetitions and prolongations in speech sounds, in addition to prolonged articulatory posture, and/or avoidance and struggle behaviors (Van Riper, 1971). Stuttering affects 5–8 % of preschool-age children (Yairi and Ambrose, 2013) and remains as a chronic speech disorder in 1 % of the general population. Typical onset of stuttering is reported to occur at 30–48 months (Bloodstein and Ratner, 2008, Reilly et al., 2013, Yairi and Ambrose, 2005) with approximately 80 % of children naturally recovering 24–36 months after the onset of stuttering (Yairi and Ambrose, 2013, Yairi and Ambrose, 2005, Yairi and Ambrose, 1999). Around this same developmental period, the neural systems supporting executive function, language, and speech-motor control undergo rapid and vigorous development (Smith and Weber, 2017, Almli et al., 2007, Chang et al., 2019, Friederici, 2006, Gilmore et al., 2018).

     In the past 20 years, an increasing number of neuroimaging studies have been conducted to understand the possible neural bases of stuttering. Convergent findings from systematic reviews and meta-analyses have highlighted several neuroanatomical differences in children and adults who stutter (AWS) compared to fluent speakers (Smith and Weber, 2017, Chang et al., 2019, Belyk et al., 2015, Budde, 2014, Ingham et al., 2005, Neef et al., 2015). Structural and functional anomalies in the left speech motor neural system, including the inferior frontal gyrus (IFG), posterior superior temporal gyrus (STG), basal ganglia-thalamo-cortical (BGTC) loop and the cerebellum have been associated with stuttering (see Chang et al., 2019 for review). In addition to gray matter anomalies, children who stutter (CWS) were found to have less white matter volume (WMV) bilaterally in the forceps minor of the corpus callosum (Beal et al., 2013) while another study found no significant differences (Choo et al., 2012).

Conclusion

     Regional gray and white matter volume differences across the whole brain were examined in preschool- and school-age CWS (both persistent and recovered) compared to age matched peers in the largest MRI dataset collected for this clinical population to date. Longitudinally collected scans that spanned up to 4 years per participant allowed tracking of developmental trajectories that differentiated among the groups. The results provide broad support for a possible BGTC network deficit starting at the early phase (preschool-age) of the disorder, involving the putamen, nucleus accumbens, left IFG/vPMC, and corticostriatal tracts. The deficits in input regions of the BGTC network appear to affect the output regions of the network including the thalamus in later phases of stuttering (school-age). The current data also provide insights into neural bases of natural recovery from stuttering during childhood. Children who recover from stuttering showed increased WMV in motor projection fibers, left AF, corpus callosum, and cerebellar peduncle around the dentate nuclei, suggesting that normalization or successful compensation of stuttering-linked neural deficits. Similar volume increases in corpus callosum, and cerebellar peduncle were also observed in pCWS, indicating an incomplete compensation. These results provide substantial new insights into possible neural bases of stuttering onset, persistence, and recovery during childhood.

Abstract

In conventional healthcare, real-time monitoring of patient records and information mining for timely diagnosis of chronic diseases under certain health conditions is a crucial process. Chronic diseases, if not diagnosed in time, may result in patients’ death. In modern medical and healthcare systems, Internet of Things (IoT) driven ecosystems use autonomous sensors to sense and track patients’ medical conditions and suggest appropriate actions. In this paper, a novel IoT and machine learning (ML)-based hybrid approach is proposed that considers multiple perspectives for early detection and monitoring of 6 different chronic diseases such as COVID-19, pneumonia, diabetes, heart disease, brain tumor, and Alzheimer’s. The results from multiple ML models are compared for accuracy, precision, recall, F1 score, and area under the curve (AUC) as a performance measure. The proposed approach is validated in the cloud-based environment using benchmark and real-world datasets. The statistical analyses on the datasets using ANOVA tests show that the accuracy results of different classifiers are significantly different. This will help the healthcare sector and doctors in the early diagnosis of chronic diseases.

Introduction

Healthcare has an undeniable impact on the well-being of individuals [1, 2]. Chronic diseases adversely affect the health of human beings. This requires an early and accurate diagnosis which is possible after a physical examination in the hospital. The delayed diagnosis requires patients’ admission to the hospital for treatment which results in increased healthcare cost and duration, and restricted healthcare facilities in rural and remote areas [3]. The traditional diagnosis approaches are human-centered and error-prone, e.g., missed or delayed diagnosis, failure to initiate the follow-up, inaccessible patients’ history, wrong medical prescription, and incomplete information about patient history which may lead to severe consequences to patients’ health [4]. These challenges require the healthcare domain to adopt the latest technological disruptions in the fields of IoT, artificial intelligence (AI), and ML to reduce human error.

The IoT has demonstrated its benefits in connecting medical devices, sensors, and healthcare professionals to provide quality medical services [5] which resulted in extended healthcare services and reduced costs. The medical history of patients collected through these IoT devices also helps in the effective monitoring of patients’ health and early diagnosis by healthcare service providers. These benefits have resulted in the transformation of present healthcare facilities from hospital-centric facilities to patient-centric facilities [6, 7]. The network of medical devices and healthcare professionals created through sensors is also referred to as the Internet of Medical Things (IoMT) which in a healthcare system is called healthcare Internet of Things (HIoT) [8].

Conclusion

Internet has a major impact on our lives, spanning from professional life to social relationships. The IoT has added a new dimension to this process by establishing communication among smart objects, leading to the vision of anytime, anywhere, any media, and anything communication. IoMT is a specialized version of IoT, which specifically deals with the healthcare domain and is playing a vital role in the healthcare sector to provide cost-effective solutions in terms of hospital billing and waiting time. In this paper, a new approach is presented to diagnose 6 different chronic diseases, namely, COVID-19, diabetes, pneumonia, Alzheimer, heart disease, and brain tumor, using machine learning classifiers based on 3 computing layers. The proposed approach is evaluated for each disease using different classifiers using both benchmark and real-world datasets. This also provides efficient and effective health services to the patients by disseminating the networked information to machine learning classifiers.

In the future, the proposed approach will be evaluated with more real-world datasets while considering more chronic diseases. Moreover, efforts will be made to develop cross-disciplinary chronic disease prediction models due to common feature sets.