Role of machine learning algorithms in suicide risk prediction: a systematic review-meta analysis of clinical studies.

OBJECTIVE: Suicide is a complex and multifactorial public health problem. Understanding and addressing the various factors associated with suicide is crucial for prevention and intervention efforts. Machine learning (ML) could enhance the prediction of suicide attempts. METHOD: A systematic review was performed using PubMed, Scopus, Web of Science and SID databases. We aim to evaluate the performance of ML algorithms and summarize their effects, gather relevant and reliable information to synthesize existing evidence, identify knowledge gaps, and provide a comprehensive list of the suicide risk factors using mixed method approach. RESULTS: Forty-one studies published between 2011 and 2022, which matched inclusion criteria, were chosen as suitable. We included studies aimed at predicting the suicide risk by machine learning algorithms except natural language processing (NLP) and image processing. The neural network (NN) algorithm exhibited the lowest accuracy at 0.70, whereas the random forest demonstrated the highest accuracy, reaching 0.94. The study assessed the COX and random forest models and observed a minimum area under the curve (AUC) value of 0.54. In contrast, the XGBoost classifier yielded the highest AUC value, reaching 0.97. These specific AUC values emphasize the algorithm-specific performance in capturing the trade-off between sensitivity and specificity for suicide risk prediction. Furthermore, our investigation identified several common suicide risk factors, including age, gender, substance abuse, depression, anxiety, alcohol consumption, marital status, income, education, and occupation. This comprehensive analysis contributes valuable insights into the multifaceted nature of suicide risk, providing a foundation for targeted preventive strategies and intervention efforts. CONCLUSIONS: The effectiveness of ML algorithms and their application in predicting suicide risk has been controversial. There is a need for more studies on these algorithms in clinical settings, and the related ethical concerns require further clarification.

Extracting cancer concepts from clinical notes using natural language processing: a systematic review.

BACKGROUND: Extracting information from free texts using natural language processing (NLP) can save time and reduce the hassle of manually extracting large quantities of data from incredibly complex clinical notes of cancer patients. This study aimed to systematically review studies that used NLP methods to identify cancer concepts from clinical notes automatically. METHODS: PubMed, Scopus, Web of Science, and Embase were searched for English language papers using a combination of the terms concerning "Cancer", "NLP", "Coding", and "Registries" until June 29, 2021. Two reviewers independently assessed the eligibility of papers for inclusion in the review. RESULTS: Most of the software programs used for concept extraction reported were developed by the researchers (n = 7). Rule-based algorithms were the most frequently used algorithms for developing these programs. In most articles, the criteria of accuracy (n = 14) and sensitivity (n = 12) were used to evaluate the algorithms. In addition, Systematized Nomenclature of Medicine-Clinical Terms (SNOMED-CT) and Unified Medical Language System (UMLS) were the most commonly used terminologies to identify concepts. Most studies focused on breast cancer (n = 4, 19%) and lung cancer (n = 4, 19%). CONCLUSION: The use of NLP for extracting the concepts and symptoms of cancer has increased in recent years. The rule-based algorithms are well-liked algorithms by developers. Due to these algorithms' high accuracy and sensitivity in identifying and extracting cancer concepts, we suggested that future studies use these algorithms to extract the concepts of other diseases as well.

A Mobile Application to Assist Alzheimer's Caregivers During COVID-19 Pandemic: Development and Evaluation.

Introduction: Access to healthcare services for patients with Alzheimer's disease (AD) was limited during the COVID-19 pandemic. A mobile application (app) can help overcome this limitation for patients and caregivers. Our study aims to develop and evaluate an app to help caregivers of patients with AD during COVID-19. Methods: The study was performed in three steps. First, a questionnaire of features required for the app design was prepared based on the interviews with caregivers of AD patients and neurologists. Then, questionnaire was provided to neurologists, medical informatics, and health information management specialists to identify the final features. Second, the app was designed using the information obtained from the previous phase. Third, the quality of the app and the level of user satisfaction were evaluated using the mobile app rating scale (MARS) and the questionnaire for user interface satisfaction (QUIS), respectively. Results: The number of 41 data elements in four groups (patient's profile, COVID-19 management and control, AD management and control, and program functions) were identified for designing the app. The quality evaluation of the app based on MARS and user satisfaction evaluation based on QUIS showed the app was good. Conclusion: This is the first study that focused on developing and evaluating a mobile app for assisting Alzheimer's caregivers during the COVID-19 pandemic. As the app was designed based on users' needs and covered both information about AD and COVID-19, it can help caregivers perform their tasks more efficiently.

Digital games for rehabilitation of speech disorders: A scoping review.

Background and Aims: Digital games are among the treatment methods for speech disorders that serve purposes other than mere entertainment. These games have been used for different speech disorders at any age. This study aims to review articles that have used digital games for rehabilitating speech disorders. Methods: This study was a scoping review. PubMed, Scopus, and Web of Science were searched on February 28, 2022, to access the articles on digital games used in rehabilitation of speech disorders without any date restrictions. The search strategy was as follows: ("video game [MeSH term]" OR "computer game" OR "mobile game" OR "serious game" OR gamification [MeSH term]) AND ("speech pathology" OR "speech therapy [MeSH term]" OR "speech disorder [MeSH term]" OR stuttering [MeSH term]). Original interventional and observational studies in English were included. The data were extracted from the relevant articles, including the first author's name, year of publication, country, target group, participants, mobile device/computer-based, type of game design, language level, number of sessions, and outcome. Descriptive statistics were used to analyze the data. Results: Of 693 retrieved articles, 10 articles were included in this study. Digital games were used for different speech disorders such as apraxia (20%), dysarthria (10%), articulatory hypokinesia in Parkinson's disease (10%), dysphonic disorder (10%), hearing disability (10%), phonological impairment (10%), and speech disorder in autism (10%). Most of the articles (60%) used a mobile device-based game. Phonemes (30%), words (30%), and sentences (20%) were the most frequently used language levels in designing digital games. All the reviewed articles reported the positive effect of digital games on speech and the patients' motivation in therapy. Conclusion: Digital games can improve patients' speech and motivation in therapy. Although studies showed the positive impact of digital games on speech disorders, personalized speech therapy should be considered in designing these games.

The usefulness of virtual, augmented, and mixed reality technologies in the diagnosis and treatment of attention deficit hyperactivity disorder in children: an overview of relevant studies.

BACKGROUND: Attention deficit hyperactivity disorder (ADHD) is a neurodevelopmental condition characterized by attention problems, excessive physical activity, and impulsivity. ADHD affects not only the patients but also their families. The development and use of technologies such as virtual reality (VR), augmented reality (AR), and mixed reality (MR) for ADHD has increased over recent years. However, little is known about their potential usefulness. This overview aimed to clarify the current knowledge about the use of these three innovative technologies for the diagnosis and treatment of children with ADHD. METHODS: This overview was conducted using the PubMed, Web of Science, and Scopus databases until January 24th, 2021. The following descriptive information was compiled from the identified studies: country, year of publication, sample size, study design, ADHD diagnosis methods, applied technology, hardware equipment, clinical target, and main findings. RESULTS: The initial database searches yielded 409 articles, but 103 were removed as duplicates. Eventually, 30 eligible studies remained for analysis, the majority of which were case-control (n = 22, 73%). Regarding the applied technology/hardware equipment, VR (n = 27; 90%), head-mounted displays (n = 19, 63%), VR-based continuous performance tests (VR-CPT) (n = 21, 70%) were most frequently used. Most studies (n = 21, 70%) used the DSM criteria for the diagnosis of childhood ADHD. They primarily evaluated the utility of these technologies in assessing ADHD symptoms (n = 10, 33%) and improving the ADHD diagnostic process (n = 7, 23%). CONCLUSION: This comprehensive overview evaluated the studies on the use of VR, AR, and MR technologies for children with ADHD. These technologies seem to be promising tools for improving the diagnosis and management of ADHD in this population.

The most used questionnaires for evaluating satisfaction, usability, acceptance, and quality outcomes of mobile health.

BACKGROUND: Various questionnaires are used for evaluating satisfaction, usability, acceptance, and quality outcomes of mobile health (mHealth) services. Using the best one to meet the needs of an mHealth study is a challenge for researchers. Therefore, this study aimed to review and determine the frequently used questionnaires for evaluating the mentioned outcomes of mHealth services. METHODS: The PubMed database was searched for conducting this review in April 2021. Papers that used a referenced questionnaire to evaluate the satisfaction, usability, acceptance, or quality outcomes of mHealth were included. The first author's name, year of publication, evaluation outcome, and evaluation questionnaire were extracted from relevant papers. Data were analyzed using descriptive statistics. RESULTS: In total, 247 papers were included in the study. Questionnaires were used for usability (40%), quality (34.5%), acceptance (8.5%), and satisfaction (4%) outcomes, respectively. System usability scale (36.5%), mobile application rating scale (35.5%), post study system usability questionnaire (6%), user mobile application rating scale (5%), technology acceptance model (4.5%), computer system usability questionnaire (2.5%), net promoter score (2%), health information technology usability evaluation scale (2%), the usefulness, satisfaction, and ease of use (1.5%), client satisfaction questionnaire (1.5%), unified theory of acceptance and use of technology (1.5%), questionnaire for user interaction satisfaction (1%), user experience questionnaire (1%), and after-scenario questionnaire (1%) were the most used questionnaires, respectively. CONCLUSION: Despite the existence of special questionnaires for evaluating several outcomes of mHealth, general questionnaires with fewer items and higher reliability have been used more frequently. Researchers should pay more attention to questionnaires with a goal-based design.

A study on women's health information needs in menopausal age.

Menopause is a natural event experienced by women in middle age. To help women manage this event, it is important to identify their health information needs. A study specific questionnaire was used to identify menopausal women's health information needs and the resources and challenges related to finding information about menopause. A total of 301 women aged 48-55 years completed the questionnaire. Data were analysed using negative binomial regression and chi-square tests. The most frequently sought information was that related to breast cancer (n = 209, 69.5%), hot flushes (n = 200, 66.5%), cervical cancer (n = 194, 64.5%), non-hormonal therapies for menopausal symptoms (n = 192, 64%), laboratory tests (n = 189, 63%) and joint and muscle pain (n = 188, 62.5%). The main sources of information were audiovisual media (n = 171, 57%), obstetricians (n = 165, 55%), friends (n = 157, 52%), family (n = 157, 52%) and the internet (n = 153, 51%). The two main challenges were not knowing how to correctly access information (n = 115, 38%) and not being aware of reliable sources of information (n = 108, 36%). Therefore, it is essential for policymakers and decision-makers to provide reliable and accurate information to increase awareness and reduce anxiety of women experiencing menopause.

Effect of Computerized Physician Order Entry and Clinical Decision Support System on Adverse Drug Events Prevention in the Emergency Department: A Systematic Review.

Objective: An adverse drug event (ADE) is an injury resulting from a medical intervention related to a drug. The emergency department (ED) is a ward vulnerable to more ADEs because of overcrowding. Information technologies such as computerized physician order entry (CPOE) and clinical decision support system (CDSS) may decrease the occurrence of ADEs. This study aims to review research that reported the evaluation of the effectiveness of CPOE and CDSS on lowering the occurrence of ADEs in the ED. Data Sources: PubMed, EMBASE, and Web of Science databases were used to find studies published from 2003 to 2018. The search was conducted in November 2018. Study Selection and Data Extraction: The search resulted in 1700 retrieved articles. After applying inclusion and exclusion criteria, 11 articles were included. Data on the date, country, type of system, medication process stages, study design, participants, sample size, and outcomes were extracted. Data Synthesis: Results showed that CPOE and CDSS may prevent ADEs in the ED through significantly decreasing the rate of errors, ADEs, excessive dose, and inappropriate prescribing (in 54.5% of articles); furthermore, CPOE and CDSS may significantly increase the rate of appropriate prescribing and dosing in compliance with established guidelines (45.5% of articles). Conclusion: This study revealed that the use of CPOE and CDSS can lower the occurrence of ADEs in the ED; however, further randomized controlled trials are needed to address the effect of a CDSS, with basic or advanced features, on the occurrence of ADEs in the ED.

Virtual reality applications to assist pregnant women: a scoping review.

BACKGROUND: Virtual reality (VR) is a computer technology that simulates the real world to allow users to communicate with a similar but artificial environment. VR technologies can be used in pregnancy to help mothers gain a better understanding of this significant yet stressful event. The aim of this study was to find and summarize VR applications to help pregnant women during their pregnancy and delivery. METHODS: PubMed, Embase, and Web of Science databases were searched on November 11th, 2020 to access relevant studies. The following data were extracted from the collected studies: first author's name, year of publication, country, type of study, sample size, study objective, VR components (hardware and software), data gathering method, and study outcomes. Through a descriptive summary and analysis, the results eventually presented. RESULTS: Nine studies were included in this study. Four studies (44.5%) had used VR technology to reduce the anxiety of pregnant women, four studies (44.5%) had applied VR for decreasing delivery pain, and one study (11%) used VR for exercise trainings. Five studies (56%) used VR headsets and three studies (33.5%) used VR glasses. Most studies showed that VR was a useful method to be used for different purposes in both pregnancy and delivery (n = 8, 89%). CONCLUSION: The use of VR technology for pregnancy has been increasing in recent years. This technology has different applications in pregnancy, from reducing anxiety and pain to exercise training. However, more studies are required to reach a general common understanding about the efficacy of VR during pregnancy and delivery.

The most used questionnaires for evaluating telemedicine services.

BACKGROUND: Questionnaires are commonly used tools in telemedicine services that can help to evaluate different aspects. Selecting the ideal questionnaire for this purpose may be challenging for researchers. This study aims to review which questionnaires are used to evaluate telemedicine services in the studies, which are most common, and what aspects of telemedicine evaluation do they capture. METHODS: The PubMed database was searched in August 2020 to retrieve articles. Data extracted from the final list of articles included author/year of publication, journal of publication, type of evaluation, and evaluation questionnaire. Data were analyzed using descriptive statistics. RESULTS: Fifty-three articles were included in this study. The questionnaire was used for evaluating the satisfaction (49%), usability (34%), acceptance (11.5%), and implementation (2%) of telemedicine services. Among telemedicine specific questionnaires, Telehealth Usability Questionnaire (TUQ) (19%), Telemedicine Satisfaction Questionnaire (TSQ) (13%), and Service User Technology Acceptability Questionnaire (SUTAQ) (5.5%), were respectively most frequently used in the collected articles. Other most used questionnaires generally used for evaluating the users' satisfaction, usability, and acceptance of technology were Client Satisfaction Questionnaire (CSQ) (5.5%), Questionnaire for User Interaction Satisfaction (QUIS) (5.5%), System Usability Scale (SUS) (5.5%), Patient Satisfaction Questionnaire (PSQ) (5.5%), and Technology Acceptance Model (TAM) (3.5%) respectively. CONCLUSION: Employing specifically designed questionnaires or designing a new questionnaire with fewer questions and more comprehensiveness in terms of the issues studied provides a better evaluation. Attention to user needs, end-user acceptance, and implementation processes, along with users' satisfaction and usability evaluation, may optimize telemedicine efforts in the future.

Digital Health Solutions to Control the COVID-19 Pandemic in Countries With High Disease Prevalence: Literature Review.

BACKGROUND: COVID-19, the disease caused by the novel coronavirus SARS-CoV-2, has become a global pandemic, affecting most countries worldwide. Digital health information technologies can be applied in three aspects, namely digital patients, digital devices, and digital clinics, and could be useful in fighting the COVID-19 pandemic. OBJECTIVE: Recent reviews have examined the role of digital health in controlling COVID-19 to identify the potential of digital health interventions to fight the disease. However, this study aims to review and analyze the digital technology that is being applied to control the COVID-19 pandemic in the 10 countries with the highest prevalence of the disease. METHODS: For this review, the Google Scholar, PubMed, Web of Science, and Scopus databases were searched in August 2020 to retrieve publications from December 2019 to March 15, 2020. Furthermore, the Google search engine was used to identify additional applications of digital health for COVID-19 pandemic control. RESULTS: We included 32 papers in this review that reported 37 digital health applications for COVID-19 control. The most common digital health projects to address COVID-19 were telemedicine visits (11/37, 30%). Digital learning packages for informing people about the disease, geographic information systems and quick response code applications for real-time case tracking, and cloud- or mobile-based systems for self-care and patient tracking were in the second rank of digital tool applications (all 7/37, 19%). The projects were deployed in various European countries and in the United States, Australia, and China. CONCLUSIONS: Considering the potential of available information technologies worldwide in the 21st century, particularly in developed countries, it appears that more digital health products with a higher level of intelligence capability remain to be applied for the management of pandemics and health-related crises.

Review of Systematic Reviews in the Field of Telemedicine.

Background: Although the systematic reviews regarding telemedicine have increased in recent decades, no comprehensive studies have been conducted to review these systematic reviews. The present study aimed to review the published systematic reviews regarding telemedicine applications for the report and appraisal of several aspects. Methods: The literature search was performed in the PubMed database for the systematic reviews published during January 2010-June 2020 in the field of telemedicine using "telemedicine" Mesh terms. The extracted data from the selected articles were the year of publication, telemedicine specialty, clinical outcomes, cost evaluation, and satisfaction assessment. Data analysis was performed using descriptive statistics. Results: Among 746 retrieved articles, 191 cases were selected and reviewed. Most of the studies were focused on telemedicine (n=35; 18.3%), followed by telerehabilitation (n=22; 11.5%), tele-diabetes (n=18; 9.4%), telecardiology (n=16; 8.3%), home telecare (n=13; 6.8%), telepsychiatry (n=12; 6.3%), teledermatology (n=11; 5.7%), and teleneurology (n=9; 4.7%). The selected studies were primarily focused on clinical outcomes (72.7%), followed by cost-effectiveness (32.4%) and user satisfaction (29.3%). In addition, they mostly indicated that telemedicine services yielded acceptable clinical outcomes (72.5%), cost-effectiveness (67.7%), and healthcare provider/patient satisfaction (83.9%). Conclusion: Although telerehabilitation, tele-diabetes, telecardiology, home telecare, and telepsychiatry were studied further, there are still some specific specialties such as teleradiology, telepathology, and telepediatric that should be considered more. Moreover, investigation of various outcomes could result in a more comprehensive view of this field. Therefore, further investigations in this regard would improve telemedicine applications and encourage potential telemedicine providers to initiate these applications.

A review and content analysis of national apps for COVID-19 management using Mobile Application Rating Scale (MARS).

The expansion of mobile health apps for the management of COVID-19 grew exponentially in recent months. However, no study has evaluated these apps. The objective of this study was to develop a reliable measure and rate the quality of COVID-19 mobile health apps, to eventually provide a roadmap for future mHealth app development. In this study, we used COVID-related keywords to identify apps for iOS and Android devices. 13 apps (13.5% of the total number of apps identified) were selected for evaluation. App quality was assessed independently using MARS by two reviewers. Search queries yielded a total of 97 potentially relevant apps, of which 13 met our final inclusion criteria. Kendall's coefficient of concordance value for the inter-rater agreement was 0.93 (p = .03). COVID-19 GOV PK app had the highest average MARS score (4.7/5), and all of the apps had acceptable MARS scores (> 3.0). This study suggests that most COVID-related apps meet acceptable criteria for quality, content, or functionality, and they must highlight esthetic and interesting features for overall quality improvement to be welcomed by users.

Virtual reality applications for chronic conditions management: A review.

Background: Virtual Reality (VR) as a computer technology that simulating real environments and situations exploited in numerous healthcare areas such as chronic diseases. The significance of timely treatment and rehabilitation of patients with chronic conditions is high due to the long lasting nature of these conditions. This paper sought to perform a review of published works in the field of VR application in chronic conditions for treatment and rehabilitation purposes. Methods: We searched the MEDLINE database through PubMed in April 2016 for retrieving published papers from January 2001 to December 2015. From 117 retrieved papers, 52had the inclusion criteria, and their full texts were accessible. Data were extracted from papers based on following items: the name of the first author, year of the study, applied VR methods, type of condition and disease, number of subjects that participated in the study, and finally the status of success and failure of VR application. Data were analyzed using descriptive analysis. Results: Results of the reviewed investigations have been considered in two main categories including treatment oriented papers (n=38, 73%) while twenty of these papers have been conducted on phobias (53%); also, there are rehabilitation-oriented experiments (n=14, 27%) while thirteen of these papers have been performed on stroke. In 40 papers (77%), the VR technology application reported proper and in 11 papers (21%) the application of VR resulted in relatively proper outcomes and only there is a work (2%) with poor results for VR intervention. Conclusion: VR technology has been increasingly used in recent years for treatment and rehabilitation purposes among patients affected by chronic conditions in order to motivate them for more successful management.

Minimum data set development for a drug poisoning registry system.

OBJECTIVE: Drug poisoning is the most prevalent type of poisoning throughout the world that can occur intentional or unintentional. Standard way for data gathering with uniform definitions is a requirement for preventing, controlling and managing of drug poisoning management. The purpose of this study was to develop a minimum data set, as an initial step, for a drug poisoning registry system in Iran. METHODS: This was descriptive and cross-sectional study that was performed in 2019. As the first step a comprehensive literature review was performed to retrieve related resources in Persian and English languages. For the second step the medical records of drug poisoning patients at Afzalipour hospital affiliated to Kerman University of Medical Sciences were assessed. Related data from these two steps were gathered by a checklist. Finally, a questionnaire that was created based on the checklist data elements and had three columns of 'essential,' 'useful, but not essential', and 'not essential' was used to reach a consensus on the data elements. Then the content validity ratio and the mean of experts' judgments were calculated for each data element. The Cronbach's alpha value for the entire questionnaire was obtained 0.9. RESULTS: The minimum data set of a drug poisoning registry system was categorised into the administrative part with three sections including 32 data elements, and clinical parts with six sections including 81 data elements. CONCLUSION: This study provides a minimum data set for development of a drug poisoning registry system. Collecting this minimum data set is critical for helping policy makers and healthcare providers to prevent, control and manage drug poisoning.

A Trial Study of Static Telepathology in Iran.

Static telepathology is one of the telepathology methods, in which the captured images of the slides are transmitted for consultation at a later time. This study aimed to compare the diagnostic accuracy of the conventional pathology and static telepathology systems. Eighty-two cases that had been selected randomly from 4 pathology centers in the city of Kerman were diagnosed by a pathologist, first based on light microscopy and then after 2 months based on static images (2 images per case) captured by a Nikon 50i microscopic camera. The images were sent to the pathologist via e-mail. The diagnostic accuracy of the telepathology system was calculated. The light microscopic diagnoses were concordant with the telepathologic diagnoses in 71 of 82 reviewed cases. Different diagnoses of 7 cases were due to the images captured from the inappropriate location of the slides. The diagnostic accuracy of the telepathology system was 86.5%. The results of this study showed that static telepathology is very accurate and can be widely used in Iran. However, efficient implementation and use of telepathology require paying attention to different issues such as educational, legal, ethical, financial, and security and observance of the standards related to this field.

Comparison of two heuristic evaluation methods for evaluating the usability of health information systems.

OBJECTIVES: In addition to following the usual Heuristic Evaluation (HE) method, the usability of health information systems can also be evaluated using a checklist. The objective of this study is to compare the performance of these two methods in identifying usability problems of health information systems. METHODS: Eight evaluators independently evaluated different parts of a Medical Records Information System using two methods of HE (usual and with a checklist). The two methods were compared in terms of the number of problems identified, problem type, and the severity of identified problems. RESULTS: In all, 192 usability problems were identified by two methods in the Medical Records Information System. This was significantly higher than the number of usability problems identified by the checklist and usual method (148 and 92, respectively) (p < 0.0001). After removing the duplicates, the difference between the number of unique usability problems identified by the checklist method (n = 100) and usual method (n = 44) was significant (p < 0.0001). Differences between the mean severity of the real usability problems (1.83) and those identified by only one of the methods (usual = 2.05, checklist = 1.74) were significant (p = 0.001). CONCLUSIONS: This study revealed the potential of the two HE methods for identifying usability problems of health information systems. The results demonstrated that the checklist method had significantly better performance in terms of the number of identified usability problems; however, the performance of the usual method for identifying problems of higher severity was significantly better. Although the checklist method can be more efficient for less experienced evaluators, wherever usability is critical, the checklist should be used with caution in usability evaluations.