Federated Learning for Healthcare Domain - Pipeline, Applications and Challenges

Federated learning is the process of developing machine learning models over datasets distributed across data centers such as hospitals, clinical research labs, and mobile devices while preventing data leakage. This survey examines previous research and studies on federated learning in the healthcare sector across a range of use cases and applications. Our survey shows what challenges, methods, and applications a practitioner should be aware of in the topic of federated learning. This paper aims to lay out existing research and list the possibilities of federated learning for healthcare industries.© 2022 Copyright held by the owner/author(s).

Predicting COVID-19 Severity Integrating RNA-Seq Data Using Machine Learning Techniques

A fundamental challenge in the fight against COVID-19 is the development of reliable and accurate tools to predict disease progression in a patient. This information can be extremely useful in distinguishing hospitalized patients at higher risk for needing UCI from patients with low severity. How SARS-CoV-2 infection will evolve is still unclear. Method(s): A novel pipeline was developed that can integrate RNA-Seq data from different databases to obtain a genetic biomarker COVID-19 severity index using an artificial intelligence algorithm. Our pipeline ensures robustness through multiple cross-validation processes in different steps. Result(s): CD93, RPS24, PSCA, and CD300E were identified as COVID-19 severity gene signatures. Furthermore, using the obtained gene signature, an effective multi-class classifier capable of discrimi-nating between control, outpatient, inpatient, and ICU COVID-19 patients was optimized, achieving an accuracy of 97.5%. Conclusion(s): In summary, during this research, a new intelligent pipeline was implemented to develop a specific gene signature that can detect the severity of patients suffering COVID-19. Our approach to clinical decision support systems achieved excellent results, even when processing unseen samples. Our system can be of great clinical utility for the strategy of planning, organizing and managing human and material resources, as well as for automatically classifying the severity of patients affected by COVID-19.Copyright © 2023 Bentham Science Publishers.

Decision support systems in healthcare: systematic review, meta- analysis and prediction, with example of COVID-19

Objective: The objective of this study was to provide an overview of Decision Support Systems (DSS) applied in healthcare used for diagnosis, monitoring, prediction and recommendation in medicine. Methods: We conducted a systematic review using PRISMA (Preferred Reporting Items for Systematic Reviews and Meta-Analysis) guidelines of articles published until September 2022 from PubMed, Cochrane, Scopus and web of science databases. We used KH coder to analyze included research. Then we categorized decision support systems based on their types and medical applications. Results: The search strategy provided a total of 1605 articles in the studied period. Of these, 231 articles were included in this qualitative review. This research was classified into 4 categories based on the DSS type used in healthcare: Alert Systems, Monitoring Systems, Recommendation Systems and Prediction Systems. Under each category, domain applications were specified according to the disease the system was applied to. Conclusion: In this systematic review, we collected CDSS studies that use ML techniques to provide insights into different CDSS types. We highlighted the importance of ML to support physicians in clinical decision-making and improving healthcare according to their purposes.

A decision support system for selecting the most suitable machine learning in healthcare using user parameters and requirements

The application of machine learning in the medical field is still limited. The main reason behind the lack of use is the unavailability of an easy-to-use machine learning system that targets non-technical users. The objective of this paper is to propose an automated machine learning system to aid non-technical users. The proposed system provides the user with simple choices to provide suggestions to the system. The system uses the combination of the user's choices and performance evaluation to select the most suited model from available options. In this study, we employed the system on a Parkinson's disease dataset. The templates for support vector machine and random forest algorithms are provided to the system. Support vector machines and random forests were able to produce 80% and 75% accuracy, respectively. The system used performance parameters of the system and user choices to select the most suited models for each test case. The support vector machine was selected as the most suited model in three test cases, while random forest was selected as the most suited for one test case. The test cases also showed that the weighted time parameter impacted the results heavily.Copyright © 2022 The Author(s)

Implementing patient decision aids into general practice clinical decision support systems: Feasibility study in cardiovascular disease prevention.

Objective: Patient decision aids (DA) facilitate shared decision making, but implementation remains a challenge. This study tested the feasibility of integrating a cardiovascular disease (CVD) prevention DA into general practice software. Methods: We developed a desktop computer application (app) to auto-populate a CVD prevention DA from general practice medical records. 4 practices received monthly practice reports from July-Nov 2021, and 2 practices use the app with limited engagement. CVD risk assessment data and app use were monitored. Results: The proportion of eligible patients with complete CVD risk assessment data ranged from 59 to 94%. Monthly app use ranged from 0 to 285 sessions by 13 individual practice staff including GPs and nurses, with staff using the app an average of 67 sessions during the study period. High users in the 5-month study period continued to use the app for 10 months. Low use was attributed to reduced staff capacity during COVID-19 and technical issues. Conclusion: High users sustained interest in the app, but additional strategies are required for low users. The study will inform implementation plans for new guidelines. Innovation: This study showed it is feasible to integrate patient decision aids with Australian general practice software, despite the challenges of COVID-19 at the time of the study.

Deep learning-based hybrid clinical decision support system algorithm for COVID-19 diagnosis via PCR graphics and Thorax CT images, preliminary data

Introduction: The limited sensitivity of microbiological testing, challenges in radiological differential diagnosis, and expectations of quick and accurate diagnosis required developing clinical decision support systems (CDSS). We propose a new deep learning-based hybrid CDSS that combines the advantageous aspects of thorax computed tomography(CT) and reverse transcriptase-polymerase chain reaction(PCR) to overcome the weakness of each one. Method(s): We retrospectively constructed a database that contains CT images of healthy subjects and patients with COVID-19 pneumonia(CP), bacterial/viral pneumonia(BVP), interstitial lung diseases(ILD), and PCR data of patients who were tested positive and negative for SARS-CoV-2. A new 3D-convolutional neural network (3D-CNN) and long short-term memory network(LSTM) based CDSS is developed to perform accurate and robust detection of COVID19 using CT images and PCR data. Result(s): Performance results of the proposed models (Fig1) provide highly reliable diagnosis of COVID-19 with 93.2% and 99.7% AUC for CT and PCR data, respectively. Conclusion(s): Proposed CDSS with state-of-the-art deep learning methods provides similar performance compared to both radiologists in CT evaluation and microbiologists in PCR evaluation and can be safely used. We plan to develop a hybrid CDSS algorithm further, combining laboratory data with CT and PCR models.

Situation Awareness-Oriented Dashboard in ICUs in Support of Resource Management in Time of Pandemics.

In a pediatric intensive care unit (PICU) of 32 beds, clinicians manage resources 24 hours a day, 7 days a week, from a large-screen dashboard implemented in 2017. This resource management dashboard efficiently replaces the handwriting information displayed on a whiteboard, offering a synthetic view of the bed's layout and specific information on staff and equipment at bedside. However, in 2020 when COVID-19 hit, the resource management dashboard showed several limitations. Mainly, its visualization offered to the clinicians limited situation awareness (SA) to perceive, understand and predict the impacts on resource management and decision-making of an unusual flow of patients affected by the most severe form of coronavirus. To identify the SA requirements during a pandemic, we conducted goal-oriented interviews with 11 clinicians working in ICUs. The result is the design of an SA-oriented dashboard with 22 key indicators (KIs): 1 on the admission capacity, 15 at bedside and 6 displayed as statistics in the central area. We conducted a usability evaluation of the SA-oriented dashboard compared to the resource management dashboard with 6 clinicians. The results showed five usability improvements of the SA-oriented dashboard and five limitations. Our work contributes to new knowledge on the clinicians' SA requirements to support resource management and decision-making in ICUs in times of pandemics.

Evaluation of a clinical decision support system and an automated electronic health record alert on outpatient prescribing of cefdinir

Purpose of Study: Acute bacterial upper respiratory infections, such as acute otitis media, pharyngitis, and sinusitis, are common indications for antibiotics in pediatrics, and it is estimated one-third of these prescriptions may be inappropriate. Cefdinir is an oral cephalosporin commonly used in pediatrics due to taste and ease of once-a-day dosing. However, there are no evidencebased guidelines recommending it as a first-line agent. Outpatient clinician education has demonstrated some improvement in antibiotic prescribing habits but is often not sustainable long term. Clinical decision support systems in the form of pathways and order sets are more feasible in the outpatient setting and have demonstrated sustained improvements in provider prescribing habits. Best practice advisory alerts are commonly used in the inpatient setting and have shown promising results, but there are little data on their use in the outpatient setting. Methods Used: We developed an intervention in our electronic health record consisting of an order-set based on our local acute upper respiratory infection guidelines and a best practice advisory alert targeting Cefdinir use in non-penicillin allergic patients. The pre-intervention period was defined as April 2018 to December 2021. The post-intervention periodwas defined as January 2022 to December 2022. Data shown here are through September 2022. Oral antibiotic prescriptions from all general pediatric clinics within our institution with diagnosis codes pertaining to acute otitis media, pharyngitis, and sinusitis were included. Thesewere then grouped into first-line and non-first-line categories. Patient data were collected for each prescription, including diagnosis, date, sex, and race/ethnicity. The primary endpoint was the percentage of first-line prescribing. Summary of Results: A total of 45 038 prescriptions were included in our analyses with 36 578 in the pre-intervention period and 8460 in the post-intervention period. There was no difference noted between the pre- and postgroups in patient sex, however, there were notable differences in patient race/ethnicity and diagnosis. Firstline prescribing accounted for 73.5% of the pre-intervention group, and 81.9% of the post-intervention group (P = <0.001). Conclusion(s): Implementation of an outpatient order-set coupled with a best practice advisory alertwas associated with an 8.4% increase in first-line antibiotic prescribing for acute upper respiratory infections in outpatient pediatric clinics affiliated with our institution. Differences in diagnoses noted between pre- and post-intervention periods may be attributable to the COVID-19 pandemic. Copyright © 2023 Southern Society for Clinical Investigation.

Patient views on asthma diagnosis and how a clinical decision support system could help: A qualitative study.

INTRODUCTION: Making a diagnosis of asthma can be challenging for clinicians and patients. A clinical decision support system (CDSS) for use in primary care including a patient-facing mode, could change how information is shared between patients and healthcare professionals and improve the diagnostic process. METHODS: Participants diagnosed with asthma within the last 5 years were recruited from general practices across four UK regions. In-depth interviews were used to explore patient experiences relating to their asthma diagnosis and to understand how a CDSS could be used to improve the diagnostic process for patients. Interviews were audio recorded, transcribed verbatim and analysed using a thematic approach. RESULTS: Seventeen participants (12 female) undertook interviews, including 14 individuals and 3 parents of children with asthma. Being diagnosed with asthma was generally considered an uncertain process. Participants felt a lack of consultation time and poor communication affected their understanding of asthma and what to expect. Had the nature of asthma and the steps required to make a diagnosis been explained more clearly, patients felt their understanding and engagement in asthma self-management could have been improved. Participants considered that a CDSS could provide resources to support the diagnostic process, prompt dialogue, aid understanding and support shared decision-making. CONCLUSION: Undergoing an asthma diagnosis was uncertain for patients if their ideas and concerns were not addressed by clinicians and were influenced by a lack of consultation time and limitations in communication. An asthma diagnosis CDSS could provide structure and an interface to prompt dialogue, provide visuals about asthma to aid understanding and encourage patient involvement. PATIENT AND PUBLIC CONTRIBUTION: Prespecified semistructured interview topic guides (young person and adult versions) were developed by the research team and piloted with members of the Asthma UK Centre for Applied Research Patient and Public Involvement (PPI) group. Findings were regularly discussed within the research group and with PPI colleagues to aid the interpretation of data.

Artificial intelligence assisted acute patient journey.

Artificial intelligence is taking the world by storm and soon will be aiding patients in their journey at the hospital. The trials and tribulations of the healthcare system during the COVID-19 pandemic have set the stage for shifting healthcare from a physical to a cyber-physical space. A physician can now remotely monitor a patient, admitting them only if they meet certain thresholds, thereby reducing the total number of admissions at the hospital. Coordination, communication, and resource management have been core issues for any industry. However, it is most accurate in healthcare. Both systems and providers are exhausted under the burden of increasing data and complexity of care delivery, increasing costs, and financial burden. Simultaneously, there is a digital transformation of healthcare in the making. This transformation provides an opportunity to create systems of care that are artificial intelligence-enabled. Healthcare resources can be utilized more justly. The wastage of financial and intellectual resources in an overcrowded healthcare system can be avoided by implementing IoT, telehealth, and AI/ML-based algorithms. It is imperative to consider the design principles of the patient's journey while simultaneously prioritizing a better user experience to alleviate physician concerns. This paper discusses the entire blueprint of the AI/ML-assisted patient journey and its impact on healthcare provision.

Automated evaluation of ECG parameters during the COVID-19 pandemic

Algorithms for prompt automated evaluation of electrocardiogram parameters in the absence of specialized equipment and specialized specialists are considered. The patient's electrocardiogram is recorded on a paper tape, then it is photographed on the primary care doctor's mobile phone and processed by a specialized application. The application digitizes the photographed image of the electrocardiogram, evaluates its main parameters as well as calculates criteria for the differential diagnosis of certain diseases using approximate formulas. In addition, the digitized electrocardiogram image is transmitted to the server and processed using a machine learning system. Algorithms for digitizing and analyzing an electrocardiogram have been developed that make it possible to evaluate its elements that are important for diagnosis, and the average error in determining the position of the most complex (smoothed) peaks — P and T waves — was no more than 0.1 mm. An algorithm for the criteria analysis of an electrocardiogram is proposed to support the differential diagnosis of acute myocardial infarction with ST segment elevation and early ventricular repolarization syndrome which provides accuracy values of 0.85 and F-scores of 0.74. An alternative algorithm based on a deep neural network is proposed which provides the best values — 0.96 and 0.88, respectively, but requires large computing resources and is executed on the server. The algorithms are implemented as a set of library functions. They can be used both independently and as part of a full-scale clinical decision support system for automated evaluation of electrocardiogram parameters based on a client-server architecture. In addition, all calculation results, together with a photograph of the original electrocardiogram, can be promptly transferred to a qualified cardiologist in order to receive an advisory opinion remotely. © 2022, ITMO University. All rights reserved.

PiMS: A Pre-ML Labelling Tool

Machine Learning (ML) techniques in clinical decision support systems are scarce due to the limited availability of clinically validated and labelled training data sets. We present a framework to (1) enable quality controls at data submission toward ML appropriate data, (2) provide in-situ algorithm assessments, and (3) prepare dataframes for ML training and robust stochastic analysis. We developed and evaluated PiMS (Pandemic Intervention and Monitoring Systems): a remote monitoring solution for patients that are Covid-positive. The system was trialled at two hospitals in Melbourne, Australia (Alfred Health and Monash Health) involving 109 patients and 15 clinicians. © 2022 IEEE.

HIV retention in care: results and lessons learned from the Positive Pathways Implementation Trial.

BACKGROUND: Sustained, routine care is vital to the health of people with HIV (PWH) and decreasing transmission of HIV. We evaluated whether the identification of PWH at-risk of falling out of care and prompts for outreach were effective in retaining PWH in care in the United States. METHODS: In this cluster randomized controlled trial, 20 AIDS Healthcare Foundation Healthcare Centers (HCCs) were randomized to the intervention (n = 10) or control (n = 10) arm; all maintained existing retention efforts. The intervention included daily automated flags in CHORUS™, a mobile app and web-based reporting solution utilizing electronic health record data, that identified PWH at-risk of falling out of care to clinic staff. Among flagged PWH, the association between the intervention and visits after a flag was assessed using logistic regression models fit with generalized estimating equations (independent correlation structure) to account for clustering. To adjust for differences between HCCs, models included geographic region, number of PWH at HCC, and proportions of PWH who self-identified as Hispanic or had the Ryan White Program as a payer. RESULTS: Of 15,875 PWH in care, 56% were flagged; 76% (intervention) and 75% (control) resulted in a visit, of which 76% were within 2 months of the flag. In adjusted analyses, flags had higher odds of being followed by a visit (odds ratio [OR]: 1.08, 95% confidence interval [CI]: 0.97, 1.21) or a visit within 2 months (OR: 1.07, 95% CI: 0.97, 1.17) at intervention than control HCCs. Among at-risk PWH with viral loads at baseline and study end, the proportion with < 50 copies/mL increased in both study arms, but more so at intervention (65% to 74%) than control (62% to 67%) HCCs. CONCLUSION: Despite challenges of the COVID-19 pandemic, adding an intervention to existing retention efforts, and the reality that behavior change takes time, PWH flagged as at-risk of falling out of care were marginally more likely to return for care at intervention than control HCCs and a greater proportion achieved undetectability. Sustained use of the retention module in CHORUS™ has the potential to streamline retention efforts, retain more PWH in care, and ultimately decrease transmission of HIV. TRIAL REGISTRATION: The study was first registered at Clinical Trials.gov (NCT04147832, https://clinicaltrials.gov/show/NCT04147832 ) on 01/11/2019.

A machine learning algorithm to analyse the effects of vaccination on COVID-19 mortality.

The coronavirus disease 2019 (COVID-19), with new variants, continues to be a constant pandemic threat that is generating socio-economic and health issues in manifold countries. The principal goal of this study is to develop a machine learning experiment to assess the effects of vaccination on the fatality rate of the COVID-19 pandemic. Data from 192 countries are analysed to explain the phenomena under study. This new algorithm selected two targets: the number of deaths and the fatality rate. Results suggest that, based on the respective vaccination plan, the turnout in the participation in the vaccination campaign, and the doses administered, countries under study suddenly have a reduction in the fatality rate of COVID-19 precisely at the point where the cut effect is generated in the neural network. This result is significant for the international scientific community. It would demonstrate the effective impact of the vaccination campaign on the fatality rate of COVID-19, whatever the country considered. In fact, once the vaccination has started (for vaccines that require a booster, we refer to at least the first dose), the antibody response of people seems to prevent the probability of death related to COVID-19. In short, at a certain point, the fatality rate collapses with increasing doses administered. All these results here can help decisions of policymakers to prepare optimal strategies, based on effective vaccination plans, to lessen the negative effects of the COVID-19 pandemic crisis in socioeconomic and health systems.

The Impact of a Clinical Decision Support System for Addressing Physical Activity and Healthy Eating During Smoking Cessation Treatment: Hybrid Type I Randomized Controlled Trial.

BACKGROUND: People who smoke have other risk factors for chronic diseases, such as low levels of physical activity and poor diet. Clinical decision support systems (CDSSs) might help health care practitioners integrate interventions for diet and physical activity into their smoking cessation programming but could worsen quit rates. OBJECTIVE: The aims of this study are to assess the effects of the addition of a CDSS for physical activity and diet on smoking cessation outcomes and to assess the implementation of the study. METHODS: We conducted a pragmatic hybrid type I effectiveness-implementation trial with 232 team-based primary care practices in Ontario, Canada, from November 2019 to May 2021. We used a 2-arm randomized controlled trial comparing a CDSS addressing physical activity and diet to treatment as usual and used the Reach, Effectiveness, Adoption, Implementation, and Maintenance framework to measure implementation outcomes. The primary outcome was self-reported 7-day tobacco abstinence at 6 months. RESULTS: We enrolled 5331 participants in the study. Of these, 2732 (51.2%) were randomized to the intervention group and 2599 (48.8%) to the control group. At the 6-month follow-up, 29.7% (634/2137) of respondents in the intervention arm and 27.3% (552/2020) in the control arm reported abstinence from tobacco. After multiple imputation, the absolute group difference was 2.1% (95% CI -0.5 to 4.6; F1,1000.42=2.43; P=.12). Mean exercise minutes changed from 32 (SD 44.7) to 110 (SD 196.1) in the intervention arm and from 32 (SD 45.1) to 113 (SD 195.1) in the control arm (group effect: B=-3.7 minutes; 95% CI -17.8 to 10.4; P=.61). Servings of fruit and vegetables changed from 2.64 servings to 2.42 servings in the intervention group and from 2.52 servings to 2.45 servings in the control group (incidence rate ratio for intervention group=0.98; 95% CI 0.93-1.02; P=.35). CONCLUSIONS: A CDSS for physical activity and diet may be added to a smoking cessation program without affecting the outcomes. Further research is needed to improve the impact of integrated health promotion interventions in primary care smoking cessation programs. TRIAL REGISTRATION: ClinicalTrials.gov NCT04223336 https://www.clinicaltrials.gov/ct2/show/NCT04223336. INTERNATIONAL REGISTERED REPORT IDENTIFIER (IRRID): RR2-10.2196/19157.

Implementing a E-Health Tool for COVID-19 Care in West and Central Africa

Introduction/ Background: Limited access to Covid-19 guidelines may have led to patient mismanagement and antibiotic overuse. E-health tools can improve access to Covid-19 guidelines. This qualitative study supported by ANRS, Expertise France aims to identify the implementation challenges of a CDSS and aims to improve the management of Covid-19 and common infections. Methods: By videoconference, 21 qualitative, semi structured interviews were conducted with health care practitioners (57%), health care actors trained in engineering (9%), project managers (14%), biologists (5%), microbiologists/antimicrobial resistance experts (10%), and anthropologists (5%). Once transcribed by an external firm, the data were analyzed by the same researchers following a thematic analysis. Identified site visits were conducted in Abidjan and an acceptability questionnaire completed by the practitioners and the responses have been analyzed. Results: This analysis revealed limited access to Covid-19 clinical guidelines and infections in general, which were identified as structural challenges for nonspecialist practitioners depending on the country. The clinical decision support system (CDSS) <<Antibioclic Afrique>> was deployed on a pilot basis in Abidjan (Côte d'Ivoire). Out of 1380 practitioners who visited the website in 2390 sessions from February to October 2021, 62.5% had never had access to such a tool and 53.8% found it very relevant. These results formed the basis for a pilot CDSS for antimicrobial prescribing in Africa. (https://www.antibioclic-afrique.com) available as an IOS and Android mobile application. Impact: According to WHO, the diffusion of digital health tools is still very limited in Africa . This CDSS aims at improving the management of Covid-19 by strengthening prescribers' capacities and their adherence to clinical guidelines. Considering the weight of socio-economic factors in the misuse of antibiotics, qualitative multi-dimensional studies are needed. Conclusion: These results confirm the relevance of the CDSS for better access to Covid-19 clinical guidelines and demonstrate that digital tools can help practitioners in their diagnostic and therapeutic decisions. The survey continues and the feedback from users will allow us to improve it.

eHealthResp: educational intervention to improve antibiotic use in primary care - a protocol for a pilot study

Introduction: Antibiotic resistances are among themost threatening public health issues worldwide, being highly associated with inadequate antibiotic use. To tackle this challenge, it is crucial to educate health professionals to appropriately prescribe and dispense antibiotics. Thus, out team developed eHealthResp, an educational intervention composed by two online courses and a clinical decision support system in the form of a mobile app directed to primary care physicians and community pharmacists, aiming to improve antibiotic prescribing and dispensing in respiratory tract infections. Objectives: The main goal of this pilot study is to validate the eHealthResp online courses and the clinical decision support system (mobile app), involving a small group of health professionals. Methods: Aproximately 15 physicians and 15 pharmacists will be recruited to participate in the study. Participants will have complete autonomy to explore and evaluate the eHealthResp mobile app and online courses, composed by six modules on respiratory tract infections for physicians (i) acute otitis media, ii) acute rhinosinusitis, iii) acute pharyngotonsilitis, iv) acute tracheobronchitis, v) community-acquired pneumonia, and vi) COVID-19), and three modules for pharmacists (i) common cold and flu, ii) acute rhinosinusitis, acute pharyngotonsilitis, and acute tracheobronchitis, and iii) acting protocol). Each online course is also composed by four clinical cases and the most recommended pharmacological therapy. Additionally, for the the global validation of the online course and the mobile app, participants will be invited to complete a questionnaire including three sections of questions. The first part, consisting of five brief questions, will allow the collection of sociodemographic data. The second part contains four groups of closed questions, and the third part consists of four open-answer questions, both aiming to evaluate the online course and mobile app elements. Results: After the assessment made by the physicians and pharmacists who agreed to participate in the pilot study, the data obtained will be duly analyzed and integrated by the research team. The appropriate changes will be incorporated into the e-Health platforms to improve the quality of both the online courses and the eHealthResp mobile app. Conclusions: The findings of this pilot study will provide important information for the next stage of the project, ensuring the feasibility of the educational interventions in a group of primary care physicians and community pharmacists from the Centre region of Portugal, using a randomized controlled trial designed by clusters.