Care-needs level prediction for elderly long-term care using insurance claims data

Fukunishi, Hiroaki; Kobayashi, Yasuki

doi:10.1016/j.imu.2023.101321

Cited by 1 publication

(2 citation statements)

References 40 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Simultaneously, the study conducted by H. Fukunishi also utilized the same dataset but concentrated on predicting the needs of individuals aged 75 and older. The study achieved a precision score of 0.694 and a recall score of 0.505 [ 10 ]. Our own model also yielded promising results, achieving an AUROC of 0.728 using Logistic Regression techniques.…”

Section: Discussionmentioning

confidence: 99%

“…Prior studies have employed machine learning (ML) techniques for predicting LTC needs; however, they often limit their scope to very specific service usage scenarios. For instance, two Japanese studies used healthcare insurance claims and multiclass classification to predict eligibility for government allowances instead of assessing demand for LTC services directly, with one study focusing on people over 75 [ 9 , 10 ]. In contrast, a study from Taiwan forecasts the scores for difficulties in Activities of Daily Living (ADL) and Instrumental Activities of Daily Living (IADL), achieving mean absolute errors of 17.67 and 1.31, respectively [ 11 ].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Predicting Long-Term Care Service Demands for Cancer Patients: A Machine Learning Approach

Chien,

Chang,

Yen

et al. 2023

Cancers

View full text Add to dashboard Cite

Background: Long-term care (LTC) service demands among cancer patients are significantly understudied, leading to gaps in healthcare resource allocation and policymaking. Objective: This study aimed to predict LTC service demands for cancer patients and identify the crucial factors. Methods: 3333 cases of cancers were included. We further developed two specialized prediction models: a Unified Prediction Model (UPM) and a Category-Specific Prediction Model (CSPM). The UPM offered generalized forecasts by treating all services as identical, while the CSPM built individual predictive models for each specific service type. Sensitivity analysis was also conducted to find optimal usage cutoff points for determining the usage and non-usage cases. Results: Service usage differences in lung, liver, brain, and pancreatic cancers were significant. For the UPM, the top 20 performance model cutoff points were adopted, such as through Logistic Regression (LR), Quadratic Discriminant Analysis (QDA), and XGBoost (XGB), achieving an AUROC range of 0.707 to 0.728. The CSPM demonstrated performance with an AUROC ranging from 0.777 to 0.837 for the top five most frequently used services. The most critical predictive factors were the types of cancer, patients’ age and female caregivers, and specific health needs. Conclusion: The results of our study provide valuable information for healthcare decisions, resource allocation optimization, and personalized long-term care usage for cancer patients.

show abstract

Section: Discussionmentioning

confidence: 99%