Purpose: To develop and internally validate prediction models with machine learning for future potentially preventable healthcare utilization in patients with multiple long term conditions (MLTC). This study is the first step in investigating whether prediction models can help identify patients with MLTC that are most in need of integrated care. Methods: A retrospective cohort study was performed with electronic health record data from adults with MLTC from an academic medical center in the Netherlands. Based on demographic and healthcare utilization characteristics in 2017, we predicted ≥ 12 outpatient visits, ≥ 1 emergency department (ED) visits, and ≥ 1 acute hospitalizations in 2018. Four machine learning models (elastic net regression, extreme gradient boosting (XGB), logistic regression, and random forest) were developed, optimized, and evaluated in a hold-out dataset for each outcome. Results: A total of 14,486 patients with MLTC were included. Based on the area under the curve (AUC) and calibration curves, the XGB model was selected as final model for all three outcomes. The AUC was 0.82 for ≥ 12 outpatient visits, 0.76 for ≥ 1 ED visits and 0.73 for ≥ 1 acute hospitalizations. Despite adequate AUC and calibration, precision-recall curves showed suboptimal performance. Conclusions: The final selected models per outcome can identify patients with future potentially preventable high healthcare utilization. However, identifying high-risk patients with MLTC and substantiating if they are most in need of integrated care remains challenging. Further research is warranted investigating whether patients with high healthcare utilization are indeed the most in need of integrated care and whether quantitively identified patients match the identification based on clinicians’ experience and judgment.
Purpose: Patient-centered healthcare, with aligning treatment to a patients’ goal, is recognized by experts as essential to improve healthcare for older patients with multimorbidity. Little literature exists on goals of these specific patients. Therefore, we aimed to explore goals of older hospitalized patients with multimorbidity and compare their goals to those of older hospitalized patients without multimorbidity. Methods: Older hospitalized patients (aged ≥ 70 years) were included in a prospective mixed-methods cohort study at the University Medical Centre Groningen, the Netherlands. Goals were assessed by a standardized interview, whereafter they were categorized and analyzed descriptively. Results: Four hundred and ninety-three older hospitalized patients (median age 75 (IQR 72–80), 64% male) were included, of which 223 patients presented with multimorbidity (45%). Goals mentioned most often were ‘controlling disease’ and ‘alleviating complaints’. No differences were found in goals mentioned by patients with and without multimorbidity. Forty-one percent of both patients with and without multimorbidity mentioned goals that were disease-unrelated. Conclusion: No major differences were found in goals of older hospitalized patients with and without multimorbidity. However, the large proportion of patients mentioning disease-unrelated goals emphasizes the importance of goal elicitation by healthcare professionals within hospital care to provide optimally integrated care.
Objective: To develop and internally validate prediction models for future hospital care utilization in patients with multiple chronic conditions. Design: Retrospective cohort study. Setting: A teaching hospital in the Netherlands (542 beds) Participants: All adult patients (n = 18.180) who received care at the outpatient clinic in 2017 for two chronic diagnoses or more (including oncological diagnoses) and who returned for hospital care or outpatient clinical care in 2018. Development and validation using a stratified random split-sample (n = 12.120 for development, n = 6.060 for internal validation). Outcomes: ≥2 emergency department visits in 2018, ≥1 hospitalization in 2018 and ≥12 outpatient visits in 2018. Statistical analysis: Multivariable logistic regression with forward selection. Results: Evaluation of the models’ performance showed c-statistics of 0.70 (95% CI 0.69–0.72) for the hospitalization model, 0.72 (95% CI 0.70–0.74) for the ED visits model and 0.76 (95% 0.74–0.77) for the outpatient visits model. With regard to calibration, there was agreement between lower predicted and observed probability for all models, but the models overestimated the probability for patients with higher predicted probabilities. Conclusions: These models showed promising results for further development of prediction models for future healthcare utilization using data from local electronic health records. This could be the first step in developing automated alert systems in electronic health records for identifying patients with multimorbidity with higher risk for high healthcare utilization, who might benefit from a more integrated care approach.
Objectives: This study aims to develop and pilot a hospital care coordination team intervention for patients with multimorbidity and identify key uncertainties Methods: Practice-based, participatory pilot study with mixed methods in a middle-large teaching hospital. We included adult patients who had visited seven or more outpatient specialist clinics in 2018. The intervention consisted of an intake, a comprehensive review by a dedicated care coordination team, a consultation to discuss results and two follow-up appointments. We collected both quantitative and qualitative data. Results: Out of 131 invited patients, 28 participants received the intake and comprehensive review. The intervention resulted in mixed outputs and short-term outcomes. Among the 28 participants, 21 received recommendations for at least two out of three categories (medication, involved medical specialists, other). Patients’ experienced effects ranged from no to very large effects. Key uncertainties were how to identify patients with a need for care coordination and the minimum of required data that can be collected during regular clinical care with feasible effort. Discussion: Recruitment and selection for hospital care coordination should be refined to include patients with multimorbidity who might benefit most. Outcomes of research and clinical care should align and first focus on evaluating the results of care coordination before evaluating health-related outcomes.