A randomized trial examining the effect of predictive analytics and tailored interventions on the cost of care.

This two-arm randomized controlled trial evaluated the impact of a Stepped-Care intervention (predictive analytics combined with tailored interventions) on the healthcare costs of older adults using a Personal Emergency Response System (PERS). A total of 370 patients aged 65 and over with healthcare costs in the middle segment of the cost pyramid for the fiscal year prior to their enrollment were enrolled for the study. During a 180-day intervention period, control group (CG) received standard care, while intervention group (IG) received the Stepped-Care intervention. The IG had 31% lower annualized inpatient cost per patient compared with the CG (3.7 K, $8.1 K vs. $11.8 K, p = 0.02). Both groups had similar annualized outpatient costs per patient ($6.1 K vs. $5.8 K, p = 0.10). The annualized total cost reduction per patient in the IG vs. CG was 20% (3.5 K, $17.7 K vs. $14.2 K, p = 0.04). Predictive analytics coupled with tailored interventions has great potential to reduce healthcare costs in older adults, thereby supporting population health management in home or community settings.

Predictive analytics and tailored interventions improve clinical outcomes in older adults: a randomized controlled trial.

This study explored the potential to improve clinical outcomes in patients at risk of moving to the top segment of the cost acuity pyramid. This randomized controlled trial evaluated the impact of a Stepped-Care approach (predictive analytics + tailored nurse-driven interventions) on healthcare utilization among 370 older adult patients enrolled in a homecare management program and using a Personal Emergency Response System. The Control group (CG) received care as usual, while the Intervention group (IG) received Stepped-Care during a 180-day intervention period. The primary outcome, decrease in emergency encounters, was not statistically significant (15%, p = 0.291). However, compared to the CG, the IG had significant reductions in total 90-day readmissions (68%, p = 0.007), patients with 90-day readmissions (76%, p = 0.011), total 180-day readmissions (53%, p = 0.020), and EMS encounters (49%, p = 0.006). Predictive analytics combined with tailored interventions could potentially improve clinical outcomes in older adults, supporting population health management in home or community settings.

Factors Influencing Exercise Engagement When Using Activity Trackers: Nonrandomized Pilot Study.

BACKGROUND: It is well reported that tracking physical activity can lead to sustained exercise routines, which can decrease disease risk. However, most stop using trackers within a couple months of initial use. The reasons people stop using activity trackers can be varied and personal. Understanding the reasons for discontinued use could lead to greater acceptance of tracking and more regular exercise engagement. OBJECTIVE: The aim of this study was to determine the individualistic reasons for nonengagement with activity trackers. METHODS: Overweight and obese participants (n=30) were enrolled and allowed to choose an activity tracker of their choice to use for 9 weeks. Questionnaires were administered at the beginning and end of the study to collect data on their technology use, as well as social, physiological, and psychological attributes that may influence tracker use. Closeout interviews were also conducted to further identify individual influencers and attributes. In addition, daily steps were collected from the activity tracker. RESULTS: The results of the study indicate that participants typically valued the knowledge of their activity level the activity tracker provided, but it was not a sufficient motivator to overcome personal barriers to maintain or increase exercise engagement. Participants identified as extrinsically motivated were more influenced by wearing an activity tracker than those who were intrinsically motivated. During the study, participants who reported either owning multiple technology devices or knowing someone who used multiple devices were more likely to remain engaged with their activity tracker. CONCLUSIONS: This study lays the foundation for developing a smart app that could promote individual engagement with activity trackers.

A machine learning model to predict the risk of 30-day readmissions in patients with heart failure: a retrospective analysis of electronic medical records data.

BACKGROUND: Heart failure is one of the leading causes of hospitalization in the United States. Advances in big data solutions allow for storage, management, and mining of large volumes of structured and semi-structured data, such as complex healthcare data. Applying these advances to complex healthcare data has led to the development of risk prediction models to help identify patients who would benefit most from disease management programs in an effort to reduce readmissions and healthcare cost, but the results of these efforts have been varied. The primary aim of this study was to develop a 30-day readmission risk prediction model for heart failure patients discharged from a hospital admission. METHODS: We used longitudinal electronic medical record data of heart failure patients admitted within a large healthcare system. Feature vectors included structured demographic, utilization, and clinical data, as well as selected extracts of un-structured data from clinician-authored notes. The risk prediction model was developed using deep unified networks (DUNs), a new mesh-like network structure of deep learning designed to avoid over-fitting. The model was validated with 10-fold cross-validation and results compared to models based on logistic regression, gradient boosting, and maxout networks. Overall model performance was assessed using concordance statistic. We also selected a discrimination threshold based on maximum projected cost saving to the Partners Healthcare system. RESULTS: Data from 11,510 patients with 27,334 admissions and 6369 30-day readmissions were used to train the model. After data processing, the final model included 3512 variables. The DUNs model had the best performance after 10-fold cross-validation. AUCs for prediction models were 0.664 ± 0.015, 0.650 ± 0.011, 0.695 ± 0.016 and 0.705 ± 0.015 for logistic regression, gradient boosting, maxout networks, and DUNs respectively. The DUNs model had an accuracy of 76.4% at the classification threshold that corresponded with maximum cost saving to the hospital. CONCLUSIONS: Deep learning techniques performed better than other traditional techniques in developing this EMR-based prediction model for 30-day readmissions in heart failure patients. Such models can be used to identify heart failure patients with impending hospitalization, enabling care teams to target interventions at their most high-risk patients and improving overall clinical outcomes.

Evaluating the Impact of a Web-Based Risk Assessment System (CareSage) and Tailored Interventions on Health Care Utilization: Protocol for a Randomized Controlled Trial.

BACKGROUND: Soaring health care costs and a rapidly aging population, with multiple comorbidities, necessitates the development of innovative strategies to deliver high-quality, value-based care. OBJECTIVE: The goal of this study is to evaluate the impact of a risk assessment system (CareSage) and targeted interventions on health care utilization. METHODS: This is a two-arm randomized controlled trial recruiting 370 participants from a pool of high-risk patients receiving care at a home health agency. CareSage is a risk assessment system that utilizes both real-time data collected via a Personal Emergency Response Service and historical patient data collected from the electronic medical records. All patients will first be observed for 3 months (observation period) to allow the CareSage algorithm to calibrate based on patient data. During the next 6 months (intervention period), CareSage will use a predictive algorithm to classify patients in the intervention group as "high" or "low" risk for emergency transport every 30 days. All patients flagged as "high risk" by CareSage will receive nurse triage calls to assess their needs and personalized interventions including patient education, home visits, and tele-monitoring. The primary outcome is the number of 180-day emergency department visits. Secondary outcomes include the number of 90-day emergency department visits, total medical expenses, 180-day mortality rates, time to first readmission, total number of readmissions and avoidable readmissions, 30-, 90-, and 180-day readmission rates, as well as cost of intervention per patient. The two study groups will be compared using the Student t test (two-tailed) for normally distributed and Mann Whitney U test for skewed continuous variables, respectively. The chi-square test will be used for categorical variables. Time to event (readmission) and 180-day mortality between the two study groups will be compared by using the Kaplan-Meier survival plots and the log-rank test. Cox proportional hazard regression will be used to compute hazard ratio and compare outcomes between the two groups. RESULTS: We are actively enrolling participants and the study is expected to be completed by end of 2018; results are expected to be published in early 2019. CONCLUSIONS: Innovative solutions for identifying high-risk patients and personalizing interventions based on individual risk and needs may help facilitate the delivery of value-based care, improve long-term patient health outcomes and decrease health care costs. TRIAL REGISTRATION: ClinicalTrials.gov NCT03126565; https://clinicaltrials.gov/ct2/show/NCT03126565 (Archived by WebCite at http://www.webcitation.org/6ymDuAwQA).