Prevention of Unplanned Hospital Admissions in Multimorbid Patients Using Computational Modeling: Observational Retrospective Cohort Study

Abstract

Background Enhanced management of multimorbidity constitutes a major clinical challenge. Multimorbidity shows well-established causal relationships with the high use of health care resources and, specifically, with unplanned hospital admissions. Enhanced patient stratification is vital for achieving effectiveness through personalized postdischarge service selection. Objective The study has a 2-fold aim: (1) generation and assessment of predictive models of mortality and readmission at 90 days after discharge; and (2) characterization of patients’ profiles for personalized service selection purposes. Methods Gradient boosting techniques were used to generate predictive models based on multisource data (registries, clinical/functional and social support) from 761 nonsurgical patients admitted in a tertiary hospital over 12 months (October 2017 to November 2018). K-means clustering was used to characterize patient profiles. Results Performance (area under the receiver operating characteristic curve, sensitivity, and specificity) of the predictive models was 0.82, 0.78, and 0.70 and 0.72, 0.70, and 0.63 for mortality and readmissions, respectively. A total of 4 patients’ profiles were identified. In brief, the reference patients (cluster 1; 281/761, 36.9%), 53.7% (151/281) men and mean age of 71 (SD 16) years, showed 3.6% (10/281) mortality and 15.7% (44/281) readmissions at 90 days following discharge. The unhealthy lifestyle habit profile (cluster 2; 179/761, 23.5%) predominantly comprised males (137/179, 76.5%) with similar age, mean 70 (SD 13) years, but showed slightly higher mortality (10/179, 5.6%) and markedly higher readmission rate (49/179, 27.4%). Patients in the frailty profile (cluster 3; 152/761, 19.9%) were older (mean 81 years, SD 13 years) and predominantly female (63/152, 41.4%, males). They showed medical complexity with a high level of social vulnerability and the highest mortality rate (23/152, 15.1%), but with a similar hospitalization rate (39/152, 25.7%) compared with cluster 2. Finally, the medical complexity profile (cluster 4; 149/761, 19.6%), mean age 83 (SD 9) years, 55.7% (83/149) males, showed the highest clinical complexity resulting in 12.8% (19/149) mortality and the highest readmission rate (56/149, 37.6%). Conclusions The results indicated the potential to predict mortality and morbidity-related adverse events leading to unplanned hospital readmissions. The resulting patient profiles fostered recommendations for personalized service selection with the capacity for value generation.

The value of admission avoidance: cost-consequence analysis of one-year activity in a consolidated service

“…The accompanying studies on HaH-HA carried out at HCB [ 21 , 27 , 28 ] and at regional level [ 11 , 29 ] during the period have provided a comprehensive picture of the modality of care and contributed to identify future directions toward quality assurance of the service delivery. While the current report provides analytical costs for the entire population of HaH patients attended at HCB during the study period, the Triple Aim assessment done in a subset of these patients [ 27 ] confirmed health value generation of HaH-HA reporting a positive impact on patient reported outcomes and patient reported experience.…”

“…The OECD report [ 29 ], based on modelling of regional data, produced relevant outcomes: (i) Confirming health value generation of HaH-HA, as well as its scalability, (ii) Quantifying the potential for cost savings of HaH-HA at health system level, and (iii) Identifying high level requirements for the service deployment with emphasis on potential inequities associated to limited HaH-HA accessibility for socially vulnerable patients. Last, but not least, the two studies assessing the role of predictive modelling for selection of candidates for HaH-HA [ 21 ] and enhanced transitional care after discharge [ 28 ] pave the way toward implementation of digital tools for clinical support of service delivery.…”

“…The current study is one of the core components of a broader research endeavor conducted in Catalonia (Spain) to analyze different key dimensions of the HaH services. That is, (i) assessment of healthcare value generation using a Triple Aim approach [ 27 ], (ii) evaluation of HaH over a five-year period, 2015–2019, in the 27 service providers at the regional level [ 11 ], (iii) predictive modelling for service selection and personalized transitional care after discharge [ 21 , 28 ], and (iv) analysis of the potential for generalization of the service across the OECD countries [ 29 ].…”

Multicentric validation of a Multimorbidity Adjusted Disability Score to stratify depression-related risks using temporal disease maps

“…Finally, MADS, or derived scores, can be integrated as part of holistic strategies for subject-specific risk assessment that combines information on various patient’s determinants of health, also known as Multisource Clinical Predictive Modelling (MCPM). The integration of MADS with other pertinent risk factors and clinical information within MCPM approaches offers a comprehensive framework for conducting risk assessments and implementing personalized interventions in the clinical arena 36,37 . This statement was grounded on the hypothesis that the implementation of comprehensive strategies for subject-specific risk prediction and stratification, incorporating multiple sources of covariates influencing patients’ health, could enhance the accuracy of predictions and facilitate informed clinical decision-making by providing reliable estimates of individual prognosis 38 .…”

Toward Adoption of Health Risk Assessment in Population-Based and Clinical Scenarios: Lessons From JADECARE

“…It has become essential for informing health policy decisions, allocating resources, benchmarking, implementing preventive strategies and selecting appropriate healthcare services [1][2][3]. Likewise, in the clinical arena, HRA is a building block for generating predictive models to support clinical decision-making [4,5]. Indeed, population-based, and clinically-oriented HRA approaches are complementary elements needed to efficiently adopt integrated patientcentred care strategies.…”