The Latest in Predictive Analytics
Identification of elders at higher risk for fall with statewide electronic health records and a machine learning algorithm
Falls in our elder population are a major cause of injury, hospitalization and mortality worldwide, and a major source of medical costs. Current risk screening and assessment methods are often manual, include a limited number of intrinsic factors, exclude environmental factors and/or lack discriminatory capabilities that a robust machine-learned model can provide. See how machine learning can provide better discrimination for intervention and prevention.
Development of an early-warning system for high-risk patients for suicide attempt using deep learning and electronic health records
Suicide is a leading cause of death in the US, particularly for young people, veterans and Native Americans. An early warning system can be an effective way to identify those in need before a crisis is upon them. See how AI and machine learning on longitudinal health records can be used to identify those at risk – up to 60+ times as likely to attempt a suicide in a future 1 year period.
Prediction of the 1-Year Risk of Incident Lung Cancer: Prospective Study Using Electronic Health Records from the State of Maine
Lung cancer is the leading cause of cancer death worldwide. Early detection of individuals at risk of lung cancer is critical to reduce the mortality rate.
Using data from individual patient electronic health records (EHR’s), we retrospectively developed and prospectively validated an accurate risk prediction model of new incident lung cancer occurring in the next 1 year. Through statistical learning from the statewide EHR data in the preceding 6 months, our model was able to identify high-risk patients, which can be used in population health to inform early detection, preventive interventions and/or enable more focused diagnostics and surveillance.
A Real-Time Early Warning System for Monitoring Inpatient Mortality Risk: Prospective Study Using Electronic Medical Record Data
The rapid deterioration observed in the condition of some hospitalized patients can be attributed to either disease progression or imperfect triage and level of care assignment after their admission. In this study, data collected from a system-wide electronic medical record (EMR) were exposed to multiple machine learning methods. The prospectively validated algorithm scored patients’ daily and long-term risk of inpatient mortality probability after admission and stratified them into distinct risk groups.
We demonstrated the capability of the newly-designed EWS to monitor and alert clinicians about patients at high risk of in-hospital death in real time, thereby providing opportunities for timely interventions
Assessing Statewide All-Cause Future One-Year Mortality: Prospective Study with Implications for Quality of Life, Resource Utilization, and Medical Futility
Using data from a statewide elderly population (aged 65 years and older), we sought to prospectively validate an algorithm to identify patients at risk for dying in the next year for the purpose of minimizing decision uncertainty, improving quality of life, and reducing futile treatment.
As a high-prevalence health condition, hypertension is clinically costly, difficult to manage, and often leads to severe and life-threatening diseases such as cardiovascular disease (CVD) and stroke. The aim of this study was to develop and validate prospectively a risk prediction model of incident essential hypertension within the following year.
Estimating One-Year Risk of Incident Chronic Kidney Disease: Retrospective Development and Validation Study Using Electronic Medical Record Data From the State of Maine
The model identified 72.90% of high-risk patients at least 3 months before the confirmatory diagnosis was made by physicians. Of those patients, 41.02% had diabetes or an abnormal glucose test result at the time they were identified at high risk for CKD.
Summary: Analysis of a patient’s pre-disease clinical history can provide early warning of an impending Type 2 Diabetes diagnosis. This allows providers to take proactive steps to prevent or delay onset of the disease. In this study, HBI used longitudinal EHR data from the Maine State Health Information Exchange to identify a dynamic driver network (DDN) and associated critical transition state six months prior to diagnosis.
Web-based Real-Time Case Finding for the Population Health Management of Patients With Diabetes Mellitus: A Prospective Validation of the Natural Language Processing–Based Algorithm With Statewide Electronic Medical Records
Summary: Diabetes case finding based on structured medical records does not fully identify diabetic patients whose medical histories related to diabetes are available in the form of free text. Manual chart reviews have been used but involve high labor costs and long latency.