Identifying persistent high-cost patients in the hospital for care management: development and validation of prediction models
Abstract Background Healthcare use by High-Need High-Cost (HNHC) patients is believed to be modifiable through better coordination of care. To identify patients for care management, a hybrid approach is recommended that combines clinical assessment of need with model-based prediction of cost. Models...
Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
BMC
2024-11-01
|
| Series: | BMC Health Services Research |
| Subjects: | |
| Online Access: | https://doi.org/10.1186/s12913-024-11936-7 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1846147990157262848 |
|---|---|
| author | Ursula W. de Ruijter Z. L. Rana Kaplan Frank Eijkenaar Carolien C. H. M. Maas Agnes van der Heide Willem A. Bax Hester F. Lingsma |
| author_facet | Ursula W. de Ruijter Z. L. Rana Kaplan Frank Eijkenaar Carolien C. H. M. Maas Agnes van der Heide Willem A. Bax Hester F. Lingsma |
| author_sort | Ursula W. de Ruijter |
| collection | DOAJ |
| description | Abstract Background Healthcare use by High-Need High-Cost (HNHC) patients is believed to be modifiable through better coordination of care. To identify patients for care management, a hybrid approach is recommended that combines clinical assessment of need with model-based prediction of cost. Models that predict high healthcare costs persisting over time are relevant but scarce. We aimed to develop and validate two models predicting Persistent High-Cost (PHC) status upon hospital outpatient visit and hospital admission, respectively. Methods We performed a retrospective cohort study using claims data from a national health insurer in the Netherlands—a regulated competitive health care system with universal coverage. We created two populations of adults based on their index event in 2016: a first hospital outpatient visit (i.e., outpatient population) or hospital admission (i.e., hospital admission population). Both were divided in a development (January-June) and validation (July-December) cohort. Our outcome of interest, PHC status, was defined as belonging to the top 10% of total annual healthcare costs for three consecutive years after the index event. Predictors were predefined based on an earlier systematic review and collected in the year prior to the index event. Predictor effects were quantified through logistic multivariable regression analysis. To increase usability, we also developed smaller models containing the lowest number of predictors while maintaining comparable performance. This was based on relative predictor importance (Wald χ2). Model performance was evaluated by means of discrimination (C-statistic) and calibration (plots). Results In the outpatient development cohort (n = 135,558), 2.2% of patients (n = 3,016) was PHC. In the hospital admission development cohort (n = 24,805), this was 5.8% (n = 1,451). Both full models included 27 predictors, while their smaller counterparts had 10 (outpatient model) and 11 predictors (hospital admission model). In the outpatient validation cohort (n = 84,009) and hospital admission validation cohort (n = 20,768), discrimination was good for full models (C-statistics 0.75; 0.74) and smaller models (C-statistics 0.70; 0.73), while calibration plots indicated that models were well-calibrated. Conclusions We developed and validated two models predicting PHC status that demonstrate good discrimination and calibration. Both models are suitable for integration into electronic health records to aid a hybrid case-finding strategy for HNHC care management. |
| format | Article |
| id | doaj-art-c645f63eb9d84d60ad1ead900e8a6a75 |
| institution | Kabale University |
| issn | 1472-6963 |
| language | English |
| publishDate | 2024-11-01 |
| publisher | BMC |
| record_format | Article |
| series | BMC Health Services Research |
| spelling | doaj-art-c645f63eb9d84d60ad1ead900e8a6a752024-12-01T12:15:36ZengBMCBMC Health Services Research1472-69632024-11-0124111110.1186/s12913-024-11936-7Identifying persistent high-cost patients in the hospital for care management: development and validation of prediction modelsUrsula W. de Ruijter0Z. L. Rana Kaplan1Frank Eijkenaar2Carolien C. H. M. Maas3Agnes van der Heide4Willem A. Bax5Hester F. Lingsma6Department of Public Health, Erasmus MC University Medical CenterDepartment of Public Health, Erasmus MC University Medical CenterErasmus School of Health Policy & Management, Erasmus UniversityDepartment of Public Health, Erasmus MC University Medical CenterDepartment of Public Health, Erasmus MC University Medical CenterDepartment of Internal Medicine, Northwest ClinicsDepartment of Public Health, Erasmus MC University Medical CenterAbstract Background Healthcare use by High-Need High-Cost (HNHC) patients is believed to be modifiable through better coordination of care. To identify patients for care management, a hybrid approach is recommended that combines clinical assessment of need with model-based prediction of cost. Models that predict high healthcare costs persisting over time are relevant but scarce. We aimed to develop and validate two models predicting Persistent High-Cost (PHC) status upon hospital outpatient visit and hospital admission, respectively. Methods We performed a retrospective cohort study using claims data from a national health insurer in the Netherlands—a regulated competitive health care system with universal coverage. We created two populations of adults based on their index event in 2016: a first hospital outpatient visit (i.e., outpatient population) or hospital admission (i.e., hospital admission population). Both were divided in a development (January-June) and validation (July-December) cohort. Our outcome of interest, PHC status, was defined as belonging to the top 10% of total annual healthcare costs for three consecutive years after the index event. Predictors were predefined based on an earlier systematic review and collected in the year prior to the index event. Predictor effects were quantified through logistic multivariable regression analysis. To increase usability, we also developed smaller models containing the lowest number of predictors while maintaining comparable performance. This was based on relative predictor importance (Wald χ2). Model performance was evaluated by means of discrimination (C-statistic) and calibration (plots). Results In the outpatient development cohort (n = 135,558), 2.2% of patients (n = 3,016) was PHC. In the hospital admission development cohort (n = 24,805), this was 5.8% (n = 1,451). Both full models included 27 predictors, while their smaller counterparts had 10 (outpatient model) and 11 predictors (hospital admission model). In the outpatient validation cohort (n = 84,009) and hospital admission validation cohort (n = 20,768), discrimination was good for full models (C-statistics 0.75; 0.74) and smaller models (C-statistics 0.70; 0.73), while calibration plots indicated that models were well-calibrated. Conclusions We developed and validated two models predicting PHC status that demonstrate good discrimination and calibration. Both models are suitable for integration into electronic health records to aid a hybrid case-finding strategy for HNHC care management.https://doi.org/10.1186/s12913-024-11936-7PrognosisMeaningful useHealth expendituresManaged care programsValue-based health care |
| spellingShingle | Ursula W. de Ruijter Z. L. Rana Kaplan Frank Eijkenaar Carolien C. H. M. Maas Agnes van der Heide Willem A. Bax Hester F. Lingsma Identifying persistent high-cost patients in the hospital for care management: development and validation of prediction models BMC Health Services Research Prognosis Meaningful use Health expenditures Managed care programs Value-based health care |
| title | Identifying persistent high-cost patients in the hospital for care management: development and validation of prediction models |
| title_full | Identifying persistent high-cost patients in the hospital for care management: development and validation of prediction models |
| title_fullStr | Identifying persistent high-cost patients in the hospital for care management: development and validation of prediction models |
| title_full_unstemmed | Identifying persistent high-cost patients in the hospital for care management: development and validation of prediction models |
| title_short | Identifying persistent high-cost patients in the hospital for care management: development and validation of prediction models |
| title_sort | identifying persistent high cost patients in the hospital for care management development and validation of prediction models |
| topic | Prognosis Meaningful use Health expenditures Managed care programs Value-based health care |
| url | https://doi.org/10.1186/s12913-024-11936-7 |
| work_keys_str_mv | AT ursulawderuijter identifyingpersistenthighcostpatientsinthehospitalforcaremanagementdevelopmentandvalidationofpredictionmodels AT zlranakaplan identifyingpersistenthighcostpatientsinthehospitalforcaremanagementdevelopmentandvalidationofpredictionmodels AT frankeijkenaar identifyingpersistenthighcostpatientsinthehospitalforcaremanagementdevelopmentandvalidationofpredictionmodels AT carolienchmmaas identifyingpersistenthighcostpatientsinthehospitalforcaremanagementdevelopmentandvalidationofpredictionmodels AT agnesvanderheide identifyingpersistenthighcostpatientsinthehospitalforcaremanagementdevelopmentandvalidationofpredictionmodels AT willemabax identifyingpersistenthighcostpatientsinthehospitalforcaremanagementdevelopmentandvalidationofpredictionmodels AT hesterflingsma identifyingpersistenthighcostpatientsinthehospitalforcaremanagementdevelopmentandvalidationofpredictionmodels |