ABSTRACT
OBJECTIVES: Evaluate if augmenting a transitions of care delivery model with insights from artificial intelligence (AI) that applied clinical and exogenous social determinants of health data would reduce rehospitalization in older adults. DESIGN: Retrospective case-control study. SETTING AND PARTICIPANTS: Adult patients discharged from integrated health system between November 1, 2019, and February 31, 2020, and enrolled in a rehospitalization reduction transitional care management program. INTERVENTION: An AI algorithm utilizing multiple data sources including clinical, socioeconomic, and behavioral data was developed to predict patients at highest risk for readmitting within 30 days and provide care navigators five care recommendations to prevent rehospitalization. METHODS: Adjusted incidence of rehospitalization was estimated with Poisson regression and compared between transitional care management enrollees that used AI insights and matched enrollees for whom AI insights were not used. RESULTS: Analyses included 6371 hospital encounters between November 2019 and February 2020 across 12 hospitals. Of the encounters 29.3% were identified by AI as being medium-high risk for re-hospitalizing within 30 days, for which AI provided transitional care recommendations to the transitional care management team. The navigation team completed 40.2% of AI recommendations for these high-risk older adults. These patients had overall 21.0% less adjusted incidence of 30-day rehospitalization compared with matched control encounters, or 69 fewer rehospitalizations per 1000 encounters (95% CI 0.65â0.95). CONCLUSIONS AND IMPLICATIONS: Coordinating a patient's care continuum is critical for safe and effective transition of care. This study found that augmenting an existing transition of care navigation program with patient insights from AI reduced rehospitalization more than without AI insights. Augmenting transitional care with insights from AI could be a cost-effective intervention to improve transitional care outcomes and reduce unnecessary rehospitalization. Future studies should examine cost-effectiveness of augmenting transitional care models of care with AI when hospitals and post-acute providers partner with AI companies.
Subject(s)
Patient Readmission , Transitional Care , Humans , Aged , Retrospective Studies , Case-Control Studies , Artificial Intelligence , Patient DischargeABSTRACT
PURPOSE: For patients with advanced cancer, timely referral to palliative care (PC) services can ensure that end-of-life care aligns with their preferences and goals. Overestimation of life expectancy may result in underutilization of PC services, counterproductive treatment measures, and reduced quality of life for patients. We assessed the impact of a commercially available augmented intelligence (AI) tool to predict 30-day mortality risk on PC service utilization in a real-world setting. METHODS: Patients within a large hematology-oncology practice were scored weekly between June 2018 and October 2019 with an AI tool to generate insights into short-term mortality risk. Patients identified by the tool as being at high or medium risk were assessed for a supportive care visit and further referred as appropriate. Average monthly rates of PC and hospice referrals were calculated 5 months predeployment and 17 months postdeployment of the tool in the practice. RESULTS: The mean rate of PC consults increased from 17.3 to 29.1 per 1,000 patients per month (PPM) pre- and postdeployment, whereas the mean rate of hospice referrals increased from 0.2 to 1.6 per 1,000 PPM. Eliminating the first 6 months following deployment to account for user learning curve, the mean rate of PC consults nearly doubled over baseline to 33.0 and hospice referrals increased 12-fold to 2.4 PPM. CONCLUSION: Deployment of an AI tool at a hematology-oncology practice was found to be feasible for identifying patients at high or medium risk for short-term mortality. Insights generated by the tool drove clinical practice changes, resulting in significant increases in PC and hospice referrals.
Subject(s)
Hospice Care , Hospices , Humans , Intelligence , Palliative Care , Quality of LifeABSTRACT
Aim: An augmented intelligence tool to predict short-term mortality risk among patients with cancer could help identify those in need of actionable interventions or palliative care services. Patients & methods: An algorithm to predict 30-day mortality risk was developed using socioeconomic and clinical data from patients in a large community hematology/oncology practice. Patients were scored weekly; algorithm performance was assessed using dates of death in patients' electronic health records. Results: For patients scored as highest risk for 30-day mortality, the event rate was 4.9% (vs 0.7% in patients scored as low risk; a 7.4-times greater risk). Conclusion: The development and validation of a decision tool to accurately identify patients with cancer who are at risk for short-term mortality is feasible.
Subject(s)
Artificial Intelligence , Neoplasms/mortality , Adolescent , Adult , Aged , Aged, 80 and over , Algorithms , Decision Support Systems, Clinical , Electronic Health Records , Female , Humans , Machine Learning , Male , Middle Aged , Neoplasms/therapy , Reproducibility of Results , Risk Assessment , Socioeconomic Factors , Young AdultABSTRACT
OBJECTIVES: To determine if it is possible to risk-stratify avoidable utilization without clinical data and with limited patient-level data. STUDY DESIGN: The aim of this study was to demonstrate the influences of socioeconomic determinants of health (SDH) with regard to avoidable patient-level healthcare utilization. The study investigated the ability of machine learning models to predict risk using only publicly available and purchasable SDH data. A total of 138,115 patients were analyzed from a deidentified database representing 3 health systems in the United States. METHODS: A hold-out methodology was used to ensure that the model's performance could be tested on a completely independent set of subjects. A proprietary decision tree methodology was used to make the predictions. Only the socioeconomic features-age group, gender, and race-were used in the prediction of a patient's risk of admission. RESULTS: The decision tree-based machine learning approach analyzed in this study was able to predict inpatient and emergency department utilization with a high degree of discrimination using only purchasable and publicly available data on SDH. CONCLUSIONS: This study indicates that it is possible to risk-stratify patients' risk of utilization without interacting with the patient or collecting information beyond the patient's age, gender, race, and address. The implications of this application are wide and have the potential to positively affect health systems by facilitating targeted patient outreach with specific, individualized interventions to tackle detrimental SDH at not only the individual level but also the neighborhood level.