Towards Outcome-Driven Patient Subgroups: A Machine Learning Analysis Across Six Depression Treatment Studies.

BACKGROUND: Major depressive disorder (MDD) is a heterogeneous condition; multiple underlying neurobiological and behavioral substrates are associated with treatment response variability. Understanding the sources of this variability and predicting outcomes has been elusive. Machine learning (ML) shows promise in predicting treatment response in MDD, but its application is limited by challenges to the clinical interpretability of ML models, and clinicians often lack confidence in model results. In order to improve the interpretability of ML models in clinical practice, our goal was to demonstrate the derivation of treatment-relevant patient profiles comprised of clinical and demographic information using a novel ML approach. METHODS: We analyzed data from six clinical trials of pharmacological treatment for depression (total n = 5438) using the Differential Prototypes Neural Network (DPNN), a ML model that derives patient prototypes which can be used to derive treatment-relevant patient clusters while learning to generate probabilities for differential treatment response. A model classifying remission and outputting individual remission probabilities for five first-line monotherapies and three combination treatments was trained using clinical and demographic data. Prototypes were evaluated for interpretability by assessing differences in feature distributions (e.g. age, sex, symptom severity) and treatment-specific outcomes. RESULTS: A 3-prototype model achieved an area under the receiver operating curve of 0.66 and an expected absolute improvement in remission rate for those receiving the best predicted treatment of 6.5% (relative improvement of 15.6%) compared to the population remission rate. We identified three treatment-relevant patient clusters. Cluster A patients tended to be younger, to have increased levels of fatigue, and more severe symptoms. Cluster B patients tended to be older, female, have less severe symptoms, and the highest remission rates. Cluster C patients had more severe symptoms, lower remission rates, more psychomotor agitation, more intense suicidal ideation, and more somatic genital symptoms. CONCLUSION: It is possible to produce novel treatment-relevant patient profiles using ML models; doing so may improve interpretability of ML models and the quality of precision medicine treatments for MDD.

Modulatory immune responses in fungal infection associated with organ transplant - advancements, management, and challenges.

Organ transplantation stands as a pivotal achievement in modern medicine, offering hope to individuals with end-stage organ diseases. Advancements in immunology led to improved organ transplant survival through the development of immunosuppressants, but this heightened susceptibility to fungal infections with nonspecific symptoms in recipients. This review aims to establish an intricate balance between immune responses and fungal infections in organ transplant recipients. It explores the fundamental immune mechanisms, recent advances in immune response dynamics, and strategies for immune modulation, encompassing responses to fungal infections, immunomodulatory approaches, diagnostics, treatment challenges, and management. Early diagnosis of fungal infections in transplant patients is emphasized with the understanding that innate immune responses could potentially reduce immunosuppression and promise efficient and safe immuno-modulating treatments. Advances in fungal research and genetic influences on immune-fungal interactions are underscored, as well as the potential of single-cell technologies integrated with machine learning for biomarker discovery. This review provides a snapshot of the complex interplay between immune responses and fungal infections in organ transplantation and underscores key research directions.

Computational design and evaluation of mRNA- and protein-based conjugate vaccines for influenza A and SARS-CoV-2 viruses.

BACKGROUND: Israel confirmed the first case of "flurona"-a co-infection of seasonal flu (IAV) and SARS-CoV-2 in an unvaccinated pregnant woman. This twindemic has been confirmed in multiple countries and underscores the importance of managing respiratory viral illnesses. RESULTS: The novel conjugate vaccine was designed by joining four hemagglutinin, three neuraminidase, and four S protein of B-cell epitopes, two hemagglutinin, three neuraminidase, and four S proteins of MHC-I epitopes, and three hemagglutinin, nine neuraminidase, and five S proteins of MHC-II epitopes with linkers and adjuvants. The constructed conjugate vaccine was found stable, non-toxic, non-allergic, and antigenic with 0.6466 scores. The vaccine contained 14.87% alpha helix, 29.85% extended strand, 9.64% beta-turn, and 45.64% random coil, which was modeled to a 3D structure with 94.7% residues in the most favored region of the Ramachandran plot and Z-score of -3.33. The molecular docking of the vaccine with TLR3 represented -1513.9 kcal/mol of binding energy with 39 hydrogen bonds and 514 non-bonded contacts, and 1.582925e-07 of eigenvalue complex. Immune stimulation prediction showed the conjugate vaccine could activate T and B lymphocytes to produce high levels of Th1 cytokines and antibodies. CONCLUSION: The in silico-designed vaccine against IAV and SARS-CoV-2 showed good population coverage and immune response with predicted T- and B-cell epitopes, favorable molecular docking, Ramachandran plot results, and good protein expression. It fulfilled safety criteria, indicating potential for preclinical studies and experimental clinical trials.

Mathematical modeling of BCG-based bladder cancer treatment using socio-demographics.

Cancer is one of the most widespread diseases around the world with millions of new patients each year. Bladder cancer is one of the most prevalent types of cancer affecting all individuals alike with no obvious "prototypical patient". The current standard treatment for BC follows a routine weekly Bacillus Calmette-Guérin (BCG) immunotherapy-based therapy protocol which is applied to all patients alike. The clinical outcomes associated with BCG treatment vary significantly among patients due to the biological and clinical complexity of the interaction between the immune system, treatments, and cancer cells. In this study, we take advantage of the patient's socio-demographics to offer a personalized mathematical model that describes the clinical dynamics associated with BCG-based treatment. To this end, we adopt a well-established BCG treatment model and integrate a machine learning component to temporally adjust and reconfigure key parameters within the model thus promoting its personalization. Using real clinical data, we show that our personalized model favorably compares with the original one in predicting the number of cancer cells at the end of the treatment, with [Formula: see text] improvement, on average.

Multi-species prey-predator dynamics during a multi-strain pandemic.

Small and large scale pandemics are a natural phenomenon repeatably appearing throughout history, causing ecological and biological shifts in ecosystems and a wide range of their habitats. These pandemics usually start with a single strain but shortly become multi-strain due to a mutation process of the pathogen causing the epidemic. In this study, we propose a novel eco-epidemiological model that captures multi-species prey-predator dynamics with a multi-strain pandemic. The proposed model extends and combines the Lotka-Volterra prey-predator model and the Susceptible-Infectious-Recovered epidemiological model. We investigate the ecosystem's sensitivity and stability during such a multi-strain pandemic through extensive simulation relying on both synthetic cases as well as two real-world configurations. Our results are aligned with known ecological and epidemiological findings, thus supporting the adequacy of the proposed model in realistically capturing the complex eco-epidemiological properties of the multi-species multi-strain pandemic dynamics.

Hospitalisation outcomes for patients with severe mental illness treated by female vs. male psychiatry residents.

OBJECTIVE: Recent literature suggests that female physicians provide higher quality of care compared to their male counterparts across a variety of physical medical conditions. We examine whether a similar phenomenon is observed for psychiatry residents treating hospitalised psychiatric patients. METHODS: We analysed 300 hospitalised patient records from Shalvata Mental Healthcare Centre (Hod Hasharon, Israel). Resident-patient sex matchings were compared. RESULTS: No significant differences were observed in terms of residents' age and patients' age, medical condition and hospitalisation history. Male and female patients treated by female residents presented shorter hospitalisations (58 and 54 days compared to 67 and 66 days, respectively, p < .05), longer time to next hospitalisation (269 and 179 days compared to 179 and 123 days, respectively, p < .01), lower 30-day readmission rate (37% and 35% compared to 10% and 19%, respectively, p < .05), higher levels of family involvement during hospitalisation (2.6 and 2.7 points compared to 2.1 and 1.9 points, respectively, p < .01) and higher chances of obtaining rehabilitation services (39% and 34% vs. 23% and 17%, respectively, p < .05). CONCLUSIONS: Hospitalised patients treated by female psychiatry residents are associated with better hospitalisation outcomes compared to those cared for by male residents. KEY POINTSBoth male and female patients treated by female residents presented better hospitalisation outcomes.These hospitalisation outcomes include shorter hospitalisation periods, longer time to next hospitalisation, lower 30-day remission rate, significantly higher levels of family involvement and higher chances of obtaining rehabilitation services.Further work is needed in order to investigate the sources and reasons for the identified differences.

Factors contributing to preventing operating room "never events": a machine learning analysis.

BACKGROUND: A surgical "Never Event" is a preventable error occurring immediately before, during or immediately following surgery. Various factors contribute to the occurrence of major Never Events, but little is known about their quantified risk in relation to a surgery's characteristics. Our study uses machine learning to reveal and quantify risk factors with the goal of improving patient safety and quality of care. METHODS: We used data from 9,234 observations on safety standards and 101 root-cause analyses from actual, major "Never Events" including wrong site surgery and retained foreign item, and three random forest supervised machine learning models to identify risk factors. Using a standard 10-cross validation technique, we evaluated the models' metrics, measuring their impact on the occurrence of the two types of Never Events through Gini impurity. RESULTS: We identified 24 contributing factors in six surgical departments: two had an impact of > 900% in Urology, Orthopedics, and General Surgery; six had an impact of 0-900% in Gynecology, Urology, and Cardiology; and 17 had an impact of < 0%. Combining factors revealed 15-20 pairs with an increased probability in five departments: Gynecology, 875-1900%; Urology, 1900-2600%; Cardiology, 833-1500%; Orthopedics,1825-4225%; and General Surgery, 2720-13,600%. Five factors affected wrong site surgery's occurrence (-60.96 to 503.92%) and five affected retained foreign body (-74.65 to 151.43%): two nurses (66.26-87.92%), surgery length < 1 h (85.56-122.91%), and surgery length 1-2 h (-60.96 to 85.56%). CONCLUSIONS: Using machine learning, we could quantify the risk factors' potential impact on wrong site surgeries and retained foreign items in relation to a surgery's characteristics, suggesting that safety standards should be adjusted to surgery's characteristics based on risk assessment in each operating room. . TRIAL REGISTRATION NUMBER: MOH 032-2019.

COVID-19 restrictions and visitations to an Israeli psychiatric emergency department: A four-lockdowns retrospective study.

We examine the volume and characteristics of psychiatric ED visitations through a perspective of four COVID-19 lockdowns. All adult visitations to the ED of Shalvata Mental Healthcare center (Israel) during 2020-2021 were retrieved and statistically analysed and data from 2017 to 2019 was considered as control. Voluntary and involuntary ED visitations were considered, separately and combined. We find that the significant decrease in the volume of voluntary ED visitations during the 1st lockdown was quickly overturned, roughly returning to the pre-pandemic state following its conclusion. In parallel, the volume of involuntary ED visitations has dramatically increased, with the most striking levels observed during the second and third lockdowns. Elapsed time since the first occurrence of COVID-19 in Israel and the level of governmental restrictions is significantly associated with the increase in the volume of ED visits and admissions, the admission rate and the rate of involuntary visits. The prolonged consequences associated with the pandemic and the measures taken to control it suggest that it is unreasonable to expect a return to normal ED utilization in the near future. As such, alternatives to strict lockdowns should be favored when possible and urgent strengthening of psychiatric care is warranted.

The Trade-Off between Airborne Pandemic Control and Energy Consumption Using Air Ventilation Solutions.

Airborne diseases cause high mortality and adverse socioeconomic consequences. Due to urbanization, more people spend more time indoors. According to recent research, air ventilation reduces long-range airborne transmission in indoor settings. However, air ventilation solutions often incur significant energy costs and ecological footprints. The trade-offs between energy consumption and pandemic control indoors have not yet been thoroughly analyzed. In this work, we use advanced sensors to monitor the energy consumption and pandemic control capabilities of an air-conditioning system, a pedestal fan, and an open window in hospital rooms, classrooms, and conference rooms. A simulation of an indoor airborne pandemic spread of Coronavirus (COVID-19) is used to analyze the Pareto front. For the three examined room types, the Pareto front consists of all three air ventilation solutions, with some ventilation configurations demonstrating significant inefficiencies. Specifically, air-conditioning is found to be efficient only at a very high energy cost and fans seem to pose a reasonable alternative. To conclude, a more informed ventilation policy can bring about a more desirable compromise between energy consumption and pandemic spread control.

Machine-learning based routing of callers in an Israeli mental health hotline.

BACKGROUND: Mental health contact centers (also known as Hotlines) offer crisis intervention and counselling by phone calls and online chats. These mental health helplines have shown great success in improving the mental state of the callers, and are increasingly becoming popular in Israel and worldwide. Unfortunately, our knowledge about how to conduct successful routing of callers to counselling agents has been limited due to lack of large-scale data with labeled outcomes of the interactions. To date, many of these contact centers are overwhelmed by chat requests and operate in a simple first-come-first-serve (FCFS) scheduling policy which, combined, may lead to many callers receiving suboptimal counselling or abandoning the service before being treated. In this work our goal is to improve the efficiency of mental health contact centers by using a novel machine-learning based routing policy. METHODS: We present a large-scale machine learning-based analysis of real-world data from the online contact center of ERAN, the Israeli Association for Emotional First Aid. The data includes over 35,000 conversations over a 2-years period. Based on this analysis, we present a novel call routing method, that integrates advanced AI-techniques including the Monte Carlo tree search algorithm. We conducted an experiment that included various realistic simulations of incoming calls to contact centers, based on data from ERAN. We divided the simulations into two common settings: standard call flow and heavy call flow. In order to establish a baseline, we compared our proposed solution to two baseline methods: (1) The FCFS method; and (2) a greedy solution based on machine learning predictions. Our comparison focuses on two metrics - the number of calls served and the average feedback of the callers (i.e., quality of the chats). RESULTS: In the preliminary analysis, we identify indicative features that significantly contribute to the effectiveness of a conversation and demonstrate high accuracy in predicting the expected duration and the callers' feedback. In the routing methods evaluation, we find that in heavy call flow settings, our proposed method significantly outperforms the other methods in both the quantity of served calls and average feedback. Most notably, we find that in the heavy call flow settings, our method improves the average feedback by 24% compared to FCFS and by 4% compared to the greedy solution. Regarding the standard-flow setting, we find that our proposed method significantly outperforms the FCFS method in the callers' average feedback with a 12% improvement. However, in this setting, we did not find a significant difference between all methods in the quantity of served-calls and no significant difference was found between our proposed method and the greedy solution. CONCLUSION: The proposed routing policy has the potential to significantly improve the performance of mental health contact centers, especially in peak hours. Leveraging artificial intelligence techniques, such as machine learning algorithms, combined with real-world data can bring about a significant and necessary leap forward in the way mental health hotlines operate and consequently reduce the burden of mental illnesses on health systems. However, implementation and evaluation in an operational contact center is necessary in order to verify that the results replicate in practice.

Treatment selection using prototyping in latent-space with application to depression treatment.

Machine-assisted treatment selection commonly follows one of two paradigms: a fully personalized paradigm which ignores any possible clustering of patients; or a sub-grouping paradigm which ignores personal differences within the identified groups. While both paradigms have shown promising results, each of them suffers from important limitations. In this article, we propose a novel deep learning-based treatment selection approach that is shown to strike a balance between the two paradigms using latent-space prototyping. Our approach is specifically tailored for domains in which effective prototypes and sub-groups of patients are assumed to exist, but groupings relevant to the training objective are not observable in the non-latent space. In an extensive evaluation, using both synthetic and Major Depressive Disorder (MDD) real-world clinical data describing 4754 MDD patients from clinical trials for depression treatment, we show that our approach favorably compares with state-of-the-art approaches. Specifically, the model produced an 8% absolute and 23% relative improvement over random treatment allocation. This is potentially clinically significant, given the large number of patients with MDD. Therefore, the model can bring about a much desired leap forward in the way depression is treated today.

Publication patterns' changes due to the COVID-19 pandemic: a longitudinal and short-term scientometric analysis.

In recent months the COVID-19 (also known as SARS-CoV-2 and Coronavirus) pandemic has spread throughout the world. In parallel, extensive scholarly research regarding various aspects of the pandemic has been published. In this work, we analyse the changes in biomedical publishing patterns due to the pandemic. We study the changes in the volume of publications in both peer reviewed journals and preprint servers, average time to acceptance of papers submitted to biomedical journals, international (co-)authorship of these papers (expressed by diversity and volume), and the possible association between journal metrics and said changes. We study these possible changes using two approaches: a short-term analysis through which changes during the first six months of the outbreak are examined for both COVID-19 related papers and non-COVID-19 related papers; and a longitudinal approach through which changes are examined in comparison to the previous four years. Our results show that the pandemic has so far had a tremendous effect on all examined accounts of scholarly publications: A sharp increase in publication volume has been witnessed and it can be almost entirely attributed to the pandemic; a significantly faster mean time to acceptance for COVID-19 papers is apparent, and it has (partially) come at the expense of non-COVID-19 papers; and a significant reduction in international collaboration for COVID-19 papers has also been identified. As the pandemic continues to spread, these changes may cause a slow down in research in non-COVID-19 biomedical fields and bring about a lower rate of international collaboration.

LBA: Online Learning-Based Assignment of Patients to Medical Professionals.

Central to any medical domain is the challenging patient to medical professional assignment task, aimed at getting the right patient to the right medical professional at the right time. This task is highly complex and involves partially conflicting objectives such as minimizing patient wait-time while providing maximal level of care. To tackle this challenge, medical institutions apply common scheduling heuristics to guide their decisions. These generic heuristics often do not align with the expectations of each specific medical institution. In this article, we propose a novel learning-based online optimization approach we term Learning-Based Assignment (LBA), which provides decision makers with a tailored, data-centered decision support algorithm that facilitates dynamic, institution-specific multi-variate decisions, without altering existing medical workflows. We adapt our generic approach to two medical settings: (1) the assignment of patients to caregivers in an emergency department; and (2) the assignment of medical scans to radiologists. In an extensive empirical evaluation, using real-world data and medical experts' input from two distinctive medical domains, we show that our proposed approach provides a dynamic, robust and configurable data-driven solution which can significantly improve upon existing medical practices.

Are drivers ready for traffic enforcement drones?

Traffic enforcement drones reduce high-risk driving behavior which often leads to traffic crashes. However, the introduction of drones may face a public acceptance challenge which may severely hinder their potential impact. In this paper, we report and discuss the results of a drivers' survey, administered both in the US and Israel, regarding the benefits, concerns and policy considerations for the deployment of traffic enforcement drones. The results show that drivers perceive traffic enforcement drones as significantly more efficient and deterring compared to current aerial traffic enforcement resources (i.e., police helicopters) and comparable in quality to speed cameras. Privacy and safety are the main concerns expressed with regards to such technology, yet these concerns have been shown to be significantly relieved if traffic enforcement drones are restricted to interurban spaces. Interestingly, only a few Israeli participants object to the introduction of traffic enforcement drones to the traffic police's arsenal compared to about half of American participants. These results combine to suggest several practical guidelines for decision-makers which can facilitate the deployment of this potentially life-saving technology in the field.