Clinical Decision Support

This study is stage 2, round 3 of a larger study which refines and optimizes the EMBED clinical decision support (CDS) to increase number of ED physicians following standard of care for the administration of buprenorphine to appropriate patients with opioid use disorder. See NCT03658642

Pulmonary nodules are frequently found during low-dose computed tomography (LDCT) health screening. The main challenge is not only detecting nodules, but also recommending the appropriate next step, such as routine follow-up, short-interval imaging follow-up, or specialist evaluation. This multicenter cluster-randomized trial will evaluate whether an artificial intelligence (AI)-assisted reporting workflow improves the appropriateness of pulmonary nodule management decisions in health examination settings without increasing under-management or missed referrals. Participating health examination branches, rather than individual participants, will be randomly assigned in a 1:1 ratio to a conventional reporting workflow or an AI-assisted reporting workflow. All final reports will be reviewed and signed by qualified physicians. An independent expert endpoint committee, blinded to study assignment and AI output, will determine the acceptable management range for each case. Approximately 2,000 adults with pulmonary nodules detected on LDCT will be included across at branches.

This study develops a multi-agent collaborative prediction model to forecast adverse drug reactions using real-world clinical medical records. It validates model performance via evidence-based data and compares decision outputs between the AI model and clinical physicians, aiming to improve early identification of drug adverse events. Only de-identified historical medical data will be analyzed; no new clinical interventions will be conducted, with no additional risks to participants.

This trial evaluates CITE, a retrieve-and-verify layer that audits an AI-generated care plan against a full-text evidence corpus and flags patient-specific codifiable safety hazards to the clinician. The co-primary outcomes are how accurately CITE flags these hazards (sensitivity and specificity versus blinded clinician adjudication) and its clinician alert burden and acceptance, compared with AI care plans using safety guardrails alone and with unassisted clinician care, in Medicaid primary care.

Drug-related iatrogenesis is a major public health issue, accounting for a significant proportion of adverse events and hospitalizations in emergency departments. Optimizing prescription management in this context is critical to improve both patient safety and physician efficiency This study aims to evaluate the impact of the POSOS AI-driven device on the medical time required for prescription management in polymedicated patients admitted to emergency departments. The main objective is to establish whether the use of POSOS can reduce transcription time compared to standard electronic management.

The goal of this study is to investigate the effect of AI integration into clinical physical therapy clinical decision in improving cost effectiveness and clinical outcomes purposes of the study are: 1. Compare the effectiveness of AI driven and human driven clinical decision in physical therapy clinical practice on management of pain in myofascial pain syndrome. 2. Compare the effectiveness of AI driven and human driven clinical decision in physical therapy clinical practice on improving joint range of motion limitations in myofascial pain syndrome. 3. Compare the effectiveness of AI driven and human driven clinical decision in physical therapy clinical practice on improving muscle strength in myofascial pain syndrome. 4. Compare the effectiveness of AI driven and human driven clinical decision in physical therapy clinical practice on management of functional limitation in myofascial pain syndrome. 5. Compare the effectiveness of AI driven and human driven clinical decision in physical therapy clinical practice on cost-effectiveness in physical therapy management of myofascial pain syndrome.

A cluster randomized study in the primary care setting to evaluate a computer-based clinical decision support system to aid in the identification and management of patients with FH. The primary outcome of the study is the number of patients diagnosed with FH thirty-six months after study initiation.

Mortality and Rehospitalization Risk Assessment by Skilled Caregivers Compared to Existing Tools in Acute Geriatric Departments Background The elderly population in Israel and worldwide is steadily increasing, leading to greater demand for medical services, including palliative care. In 2019, individuals aged 65+ accounted for 64% of hospital admissions and 70% of hospital days in Israel. Approximately 19% of these were readmissions, a rate that increases with age. Effective tools for identifying patients at high risk of rehospitalization and mortality are lacking, which, if improved, could benefit patients through targeted palliative and end-of-life care. Enhanced tools could reduce unnecessary interventions, improve patient well-being, and alleviate economic burdens on healthcare. Research Objectives 1. Evaluate mortality and rehospitalization rates in acute geriatric departments. 2. Identify risk factors for rehospitalization and mortality in acutely hospitalized elderly patients. 3. Compare the effectiveness of skilled caregiver assessments versus validated prediction tools for mortality and rehospitalization within one year. Hypotheses 1. Mortality and rehospitalization rates in acute geriatric departments are comparable to those in internal medicine. 2. Multiple factors-such as age, family support, comorbidities, functional and cognitive status-correlate with mortality risk. 3. Skilled caregiver assessments predict mortality and rehospitalization more accurately than existing validated tools. Study Design Type: Prospective cohort observational study. Location: Shmuel Harofe Hospital. Study Population Participants are elderly patients admitted to acute geriatric departments at Shmuel Harofe Hospital for acute conditions. Approximately 600 participants will be recruited, with an additional 200-300 if statistical analysis reveals trends. Recruitment Period: Two years. Follow-up Period: Up to one year post-admission. Methods and Materials Data will be collected on demographic, functional, cognitive, and emotional factors, as well as clinical history, hospital admissions, comorbidities, and lab results. Predictive assessments will include: 1. Mortality Prediction using the WALTER Index for the elderly. 2. Rehospitalization Risk using the LACE Index, validated for 30-day readmission risk. 3. Subjective Caregiver Assessments from geriatric specialists and nursing supervisors, estimating life expectancy and 30-day, 3-month, and 1-year rehospitalization risk. Data Analysis Data will be coded and statistically analyzed without interventions outside of standard care. The WALTER and LACE indices will utilize existing clinical data. Ethical Considerations As this is an observational study without intervention, a waiver for informed consent was granted. Importance of Research Early identification of high-risk patients will enable preventive interventions, support transitions to palliative care where appropriate, and promote advance directives, ultimately improving patient care and reducing healthcare costs by preventing costly, unnecessary readmissions and interventions.