Dataset Information

Modeling Patient Journeys for Demand Segments in Chronic Care, With an Illustration to Type 2 Diabetes

ABSTRACT: Chronic care is an important area for cost-effective and efficient health service delivery. Matching demand and services for chronic care is not easy as patients may have different needs in different stages of the disease. More insight is needed into the complete patient journey to do justice to the services required in each stage of the disease, to the different experiences of patients in each part of the journey, and to outcomes in each stage. With patient journey we refer to the “journey” of the patient along the services received within a demand segment of chronic care. We developed a generic framework for describing patient journeys and provider networks, based on an extension of the well-known model of Donabedian, to relate demand, services, resources, behavior, and outcomes. We also developed a generic operational model for the detailed modeling of services and resources, allowing for insight into costs. The generic operational model can be tailored to the specific characteristics of patient groups. We applied this modeling approach to type 2 diabetes (T2D) patients. Diabetes care is a form of chronic care for patients suffering diabetes mellitus. We studied the performance of T2D networks, using a descriptive model template. To identify and describe demand we made use of the following demand segments within the diabetes type 2 population: patients targeted for prevention; patients with stage 1 diabetes treated by their GP with lifestyle advice; patients with diabetes stage 2 treated by their GP with lifestyle advice and oral medication; patients with stage 3 diabetes treated by their GP with lifestyle advice, oral medication, and insulin injections; patients with stage 4 diabetes with complications (treated by internal medicine specialists). We used a Markov model to describe the transitions between the different health states. The model enables the patient journey through the health care system for cohorts of newly diagnosed T2D patients to be described, and to make a projection of the resource requirements of the different demand segments over the years. We illustrate our approach with a case study on a T2D care network in The Netherlands and reflect on the role of demand segmentation to analyse the case study results, with the objective of improving the T2D service delivery.

SUBMITTER: Elkhuizen S

PROVIDER: S-EPMC7493672 | biostudies-literature | 2020 Jan

REPOSITORIES: biostudies-literature

ACCESS DATA

Similar Datasets

Project description:Background. This study aimed to estimate the health care expenditure for managing type 2 diabetes (T2D) in the community setting of Nepal. Methods. This is a baseline cross-sectional study of a heath behavior intervention that was conducted between September 2021 and February 2022 among patients with T2D (N = 481) in the Kavrepalanchok and Nuwakot districts of Nepal. Bottom-up and micro-costing approaches were used to estimate the health care costs and were stratified according to residential status and the presence of comorbid conditions. A generalized linear model with a log-link and gamma distribution was applied for modeling the continuous right-skewed costs, and 95% confidence intervals were obtained from 10,000 bootstrapping resampling techniques. Results. Over 6 months the mean health care resource cost to manage T2D was US $22.87 per patient: 61% included the direct medical cost (US $14.01), 15% included the direct nonmedical cost (US $3.43), and 24% was associated with productivity losses (US $5.44). The mean health care resource cost per patient living in an urban community (US $24.65) was about US $4.95 higher than patients living in the rural community (US $19.69). The health care costs per patient with comorbid conditions was US $22.93 and was US $22.81 for those without comorbidities. Patients living in rural areas had 16% lower health care expenses compared with their urban counterparts. Conclusion. T2D imposes a substantial financial burden on both the health care system and individuals. There is a need to establish high-value care treatment strategies for the management of T2D to reduce the high health care expenses.HighlightsMore than 60% of health care expenses comprise the direct medical cost, 15% direct nonmedical cost, and 24% patient productivity losses. The costs of diagnosis, hospitalization, and recommended foods were the main drivers of health care costs for managing type 2 diabetes.Health care expenses among patients living in urban communities and patients with comorbid conditions was higher compared with those in rural communities and those with without comorbidities.The results of this study are expected to help integrate diabetes care within the existing primary health care systems, thereby reducing health care expenses and improving the quality of diabetes care in Nepal.

Project description:IntroductionAn increasing shortage of donor blood is expected, considering the demographic change in Germany. Due to the short shelf life and varying daily fluctuations in consumption, the storage of platelet concentrates (PCs) becomes challenging. This emphasizes the need for reliable prediction of needed PCs for the blood bank inventories. Therefore, the objective of this study was to evaluate multimodal data from multiple source systems within a hospital to predict the number of platelet transfusions in 3 days on a per-patient level.MethodsData were collected from 25,190 (42% female and 58% male) patients between 2017 and 2021. For each patient, the number of received PCs, platelet count blood tests, drugs causing thrombocytopenia, acute platelet diseases, procedures, age, gender, and the period of a patient's hospital stay were collected. Two models were trained on samples using a sliding window of 7 days as input and a day 3 target. The model predicts whether a patient will be transfused 3 days in the future. The model was trained with an excessive hyperparameter search using patient-level repeated 5-fold cross-validation to optimize the average macro F2-score.ResultsThe trained models were tested on 5,022 unique patients. The best-performing model has a specificity of 0.99, a sensitivity of 0.37, an area under the precision-recall curve score of 0.45, an MCC score of 0.43, and an F1-score of 0.43. However, the model does not generalize well for cases when the need for a platelet transfusion is recognized.ConclusionA patient AI-based platelet forecast could improve logistics management and reduce blood product waste. In this study, we build the first model to predict patient individual platelet demand. To the best of our knowledge, we are the first to introduce this approach. Our model predicts the need for platelet units for 3 days in the future. While sensitivity underperforms, specificity performs reliably. The model may be of clinical use as a pretest for potential patients needing a platelet transfusion within the next 3 days. As sensitivity needs to be improved, further studies should introduce deep learning and wider patient characterization to the methodological multimodal, multisource data approach. Furthermore, a hospital-wide consumption of PCs could be derived from individual predictions.

Dataset Information

Modeling Patient Journeys for Demand Segments in Chronic Care, With an Illustration to Type 2 Diabetes

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets