Estimate Health Care Costs Research Articles

Trends in the prevalence of obesity and estimation of the direct health costs attributable to child and adolescent obesity in Brazil from 2013 to 2022.

Childhood obesity is a major global public health issue globally and in Brazil. The impacts of childhood obesity include higher risk of disease during childhood and of obesity and non-communicable diseases in adulthood and represent an important epidemiological and economic burden to countries. This study aims to analyze the trends and to estimate the direct healthcare costs of childhood and adolescent obesity to the National Health System from 2013 to 2022. We used Prais-Winsten regressions for determining the trends in the prevalence of obesity and modeled the attributable to childhood and adolescent obesity in the Brazilian National Health System using previous meta-analysis of studies. The hospitalizations of children and adolescents with obesity as a primary cause totaled Int$2.6 million to the Brazilian National Health System from 2013 to 2022, demonstrating that obesity is rarely considered as a cause of hospitalization especially among children and adolescents. The additional costs of hospitalizations attributable to childhood obesity totaled Int$101.5 million during the same period. The additional non-hospital, outpatient and medication cost attributable to childhood obesity in Brazil were estimated at Int$6.0 million, so the total estimated healthcare costs were of approximately Int$107.5 million in the last decade. This study highlights that childhood and adolescent obesity are increasing for most age-groups and that its costs are not limited to the economic impacts on adult health and represent a relevant economic burden to the Brazilian National Health System and to families because of additional costs during childhood and adolescence. Therefore, the prevention and control of childhood and adolescent obesity must be public health priorities.

MSR232 A Validation of New Methods for Estimating Healthcare Costs Adjusted for End-of-Life Cost and Censoring

MSR232 A Validation of New Methods for Estimating Healthcare Costs Adjusted for End-of-Life Cost and Censoring

Temporal incremental healthcare costs associated with complications in Hong Kong Chinese patients with type 2 diabetes: A prospective study in Joint Asia diabetes evaluation (JADE) Register (2007-2019).

We examined incremental healthcare costs (inpatient and outpatient) related to complications in Chinese patients with type 2 diabetes (T2D) during the year of occurrence and post-event years, utilizing the Joint Asia Diabetes Evaluation (JADE) Register cohort of Hong Kong Chinese patients with T2D between 2007 and 2019. 19,440 patients with T2D underwent structured evaluation utilizing the JADE platform with clinical outcomes data retrieved from territory-wide electronic medical records including inpatient, outpatient and emergency care. Two-part model was adopted to account for skewed healthcare costs distribution. Incremental healthcare costs associated with nine non-fatal diabetes complications and all-cause death were estimated, adjusted for demographic, clinical, lifestyle factors and comorbidities. In this prospective cohort [mean±SD age:59.9±11.9years, 56.6% men, duration of diabetes:7.3±7.5years, HbA1C:7.5±1.6%] observed for 7 (interquartile range:4-9) years (142,132 patient-years), the mean annual healthcare costs, mainly due to inpatient cost, were USD$2,990±9,960. Lower extremity amputation (LEA) (USD$31,302; 95%CI: 25,706-37,004), hemorrhagic stroke (USD$21,164; 17,680-24,626), ischemic stroke (USD$17,976; $15,937-20,352) and end-stage disease (ESRD) (USD$14,774; 13,405-16,250) in the year of event incurred the highest cost. Residual healthcare costs in the post-event years were highest for ESRD, LEA, haemorrhagic stroke and incident cancer. These comprehensive temporal healthcare cost estimates for diabetes-related complications allows the performance of long-term, patient-level, cost-effectiveness analyses on T2D prevention and treatment strategies relevant to an Asian and possibly global contexts. These may inform decision-makers on resource allocation aimed at reducing the burden of T2D and chronic diseases.

Associations Between Hearing Loss and Health-Related Costs: A Retrospective Population-Based Cohort Study.

Hearing loss (HL) is a leading cause of disability worldwide, but its health-related costs have been incompletely studied. Our objective was to examine the association between HL and direct health care costs and identify subgroups in which costs associated with HL are especially high. This was a retrospective population-based cohort study of adults treated in a universal health care system between April 2008 and March 2019. HL was identified using administrative health data. We estimate health care costs in 2023 Canadian dollars, including costs for hospitalization, provider claims, ambulatory care visits, prescription medications, and long-term care (LTC). Of 4,424,632 participants, 146,644 (3.3%) had HL. Participants with HL were older (Mdn = 55 years [interquartile range: 43-68] vs. 35 years [24-50]) and had more comorbidities (1 [0-2] vs. 0 [0-1]) at baseline than participants without, whereas the likelihood of female sex, rural residence, and material deprivation were similar between groups with and without HL. Over median follow-up of 11.0 years, total age-sex adjusted annual health costs and each of its component costs were significantly higher in participants with HL compared to those without (annual total costs: $6,871, 95% confidence interval [CI] [$6,778, $6,962] vs. $4,716, 95% CI [$4,729, $4,763]). After full adjustment (a maximum of 29 comorbidities), annual costs remained significantly higher in participants with HL overall and for certain subcomponents (provider claims, ambulatory visits, and medications), whereas adjusted costs of hospitalization and LTC were lower among people with HL. The magnitude of the incremental costs among participants with HL was most pronounced for younger participants, men, or those with less comorbidity. Total projected annual direct health costs for Alberta residents with HL were $1.01 billion in 2023, of which $125 million (95% CI [$116, $135 million]) was attributable to HL specifically. Compared to those without HL, health costs were markedly higher among participants with HL, partially due to a higher burden of comorbidity. The relatively high population attributable costs of HL suggest that better prevention, recognition, and management of this condition could yield substantial economic benefits. https://doi.org/10.23641/asha.27353439.

Costs of Transfer From Nontrauma to Trauma Centers Among Patients With Minor Injuries

ImportanceNearly half the patients transferred from nontrauma centers to trauma centers have minor injuries, yet trauma center care is not associated with a difference in morality among patients with minor injuries. Consequently, reducing the frequency of such transfers has been postulated as a method to improve resource allocation. Currently, the economic implications of these transfers are not well understood.ObjectiveTo estimate health care costs associated with the transfer of patients with minor injuries from nontrauma to trauma centers.Design, Setting, and ParticipantsThis retrospective, population-based cohort study was conducted from April 1, 2009, to March 31, 2020, in Ontario, Canada. Participants included individuals aged 16 years or older who were transferred to a trauma center after presenting to a nontrauma center with a minor injury (survival >24 hours, Injury Severity Score [ISS] <16, and absence of an American College of Surgeons–defined critical injury). Statistical analysis was conducted from March 2022 to June 2024.Main Outcomes and MeasuresThe main outcome was total health care costs within 30 days of injury, standardized to 2015 Canadian dollars (CAD$). Propensity scoring was used to match transferred patients with controls admitted to nontrauma centers. Negative binomial models were used to estimate differences in costs between transferred patients and matched controls.ResultsOf the 14 557 patients with minor injuries transferred to a trauma center (mean [SD] age, 48.1 [20.9] years; 5367 female patients [36.9%]; median ISS, 4 [IQR, 2-5]), 12 652 (86.9%) were matched with a control. Thirty days after injury, mean health care costs among transferred patients were CAD$13 540 (95% CI, CAD$13 319-CAD$13 765), a 6.5% (95% CI, 4.4%-8.5%) increase relative to controls (CAD$12 719 [95% CI, CAD$12 582-CAD$12 857]). Half the transferred patients (54.9% [7994 of 14 557]) were admitted, while the remainder were discharged after evaluation in the trauma center emergency department. Among patients admitted to a trauma center, mean 30-day costs were CAD$19 602 (95% CI, CAD$19 294-CAD$19 915), a 54.6% (95% CI, 51.5%-57.8%) increase relative to controls.Conclusions and RelevanceThis cohort study of patients with minor injuries transferred from nontrauma centers to trauma centers found that the transfer of these patients was associated with increased costs to the health care system. Given the high prevalence of such transfers, these findings suggest that the development of systems to support the care of patients with minor injuries at their local hospitals is essential to the sustainability of trauma systems.

Opioid-related clinical outcomes and associated healthcare costs following abuse/misuse of oxycodone formulations: A HEOR analysis from real-world data.

The United States (US) opioid epidemic is a continued burden on the healthcare system and on the lives of individuals affected by the consequences of opioid abuse/misuse. The objective of this study was to use real-world data from intentional abuse/misuse exposures managed by US poison centers to compare clinical outcomes and quantify healthcare costs among three study cohorts: -exposures that involved Xtampza ER®, other oxycodone extended-release (ER), and oxycodone immediate-release (IR). A real-world, observational study. Descriptive statistics were used to describe patient and exposure characteristics. Drug utilization-adjusted rates of intentional abuse/misuse and clinical outcomes were used to determine relative risk. Healthcare cost estimates were calculated by extrapolating average charge per opioid-related disorder emergency department (ED) visit and per inpatient stay based upon case disposition rates, adjusted for population and drug utilization. Compared to Xtampza ER, exposures that involved other oxycodone ER were 7.4 times more likely to be intentional abuse/misuse, 25.9 times more likely to result in major effect or death, 9.7 times more likely to require a visit to the ED, and 14.3 times more likely to result in hospital admission. Similar results were found for oxycodone IR when compared to Xtampza ER. This study is the first of its kind to synthesize clinical outcomes with opioid-related healthcare costs, suggesting that even when Xtampza ER is abused/misused, the rates of major effect/death, ED visits, and hospital admissions were significantly lower than those for other oxycodone-containing medications, resulting in relatively low downstream opioid-related healthcare costs.

Predicting hospital length of stay using machine learning on a large open health dataset

BackgroundGovernments worldwide are facing growing pressure to increase transparency, as citizens demand greater insight into decision-making processes and public spending. An example is the release of open healthcare data to researchers, as healthcare is one of the top economic sectors. Significant information systems development and computational experimentation are required to extract meaning and value from these datasets. We use a large open health dataset provided by the New York State Statewide Planning and Research Cooperative System (SPARCS) containing 2.3 million de-identified patient records. One of the fields in these records is a patient’s length of stay (LoS) in a hospital, which is crucial in estimating healthcare costs and planning hospital capacity for future needs. Hence it would be very beneficial for hospitals to be able to predict the LoS early. The area of machine learning offers a potential solution, which is the focus of the current paper.MethodsWe investigated multiple machine learning techniques including feature engineering, regression, and classification trees to predict the length of stay (LoS) of all the hospital procedures currently available in the dataset. Whereas many researchers focus on LoS prediction for a specific disease, a unique feature of our model is its ability to simultaneously handle 285 diagnosis codes from the Clinical Classification System (CCS). We focused on the interpretability and explainability of input features and the resulting models. We developed separate models for newborns and non-newborns.ResultsThe study yields promising results, demonstrating the effectiveness of machine learning in predicting LoS. The best R2 scores achieved are noteworthy: 0.82 for newborns using linear regression and 0.43 for non-newborns using catboost regression. Focusing on cardiovascular disease refines the predictive capability, achieving an improved R2 score of 0.62. The models not only demonstrate high performance but also provide understandable insights. For instance, birth-weight is employed for predicting LoS in newborns, while diagnostic-related group classification proves valuable for non-newborns.ConclusionOur study showcases the practical utility of machine learning models in predicting LoS during patient admittance. The emphasis on interpretability ensures that the models can be easily comprehended and replicated by other researchers. Healthcare stakeholders, including providers, administrators, and patients, stand to benefit significantly. The findings offer valuable insights for cost estimation and capacity planning, contributing to the overall enhancement of healthcare management and delivery.

MEDICAL INSURANCE PREMIUM PREDICTION WITH MACHINE LEARNING

A machine learning method for predicting health insurance rates is presented in this article. With healthcare expenditures becoming more complex, it is critical for insurance companies and policyholders to accurately estimate insurance prices. Utilizing a dataset that included medical history, demographic data, and other pertinent variables, a variety of machine learning techniques, such as ensemble methods and regression, were used to create prediction models. R-Squared and mean absolute error were two measures used to assess these models' performance. According to the developed models' results, insurance premiums can be predicted with accuracy, offering useful information for insurance counteragents. This approach has the potential to optimize pricing strategies, enhance risk assessment, and improve decision-making in the healthcare insurance sector. Machine Learning-Based Prediction of Medical Insurance Premiums Make predictions about health insurance companies based on personal traits. A dataset of policyholder attributes (such as age, gender, BMI, number of children, smoking behaviors, and geography) was gathered and preprocessed .Divide the data into sets for testing and training. Create and train a model for an artificial neural network with TensorFlow and Karas. R-squared metrics and mean R-squared error were used to assess the performance of the model. created a high R-Squared predictive model that was accurate. determined the main determinants of insurance rates. Machine learning has shown promise in estimating healthcare costs. This experiment demonstrates how well machine learning predicts medical insurance rates. Insurance companies may offer more individualized insurance plans, expedite the underwriting process, and help customers make well-informed decisions about their healthcare coverage by creating these predictive models. The created model can help policyholders make educated judgments and insurance companies establish proper prices. In the long run, our research helps the insurance industry enhance data-driven techniques, which benefits insurers as well as insured individuals in general.

ESTIMATING THE COSTS, HEALTH-RELATED QUALITY OF LIFE, AND REVISION RISK IN THE YEAR AFTER ELECTIVE PRIMARY AND REVISION HIP ARTHROPLASTY PROCEDURES BY IMPLANT BEARING MATERIALS: AN ANALYSIS OF LINKED DATA FROM THE NATIONAL JOINT REGISTRY (NJR), HOSPITAL EPISODE STATISTICS (HES), AND PATIENT-REPORTED OUTCOME MEASURES (PROMS) FOR ENGLISH PATIENTS

Implants in total hip replacement (THR) are associated with different clinical and cost-effectiveness profiles,. We estimate the costs and outcomes for NHS patients in the year after THR associated with implant bearing materials using linked routinely collected data.We linked NJR primary elective THR patients for osteoarthritis to HES and National PROMs. We estimated health care costs, health-related quality of life indices, and revision risks, in the year after primary and revision THRs overall. We used generalised linear models adjusting for patient and hospital characteristics and estimated 10-year cumulative probability of revision. We imputed utilities using chained equations for half the sample with missing PROMS.We linked 577,973 elective primary THRs and 11,812 subsequent revisions. One year after primary THR, patients with the cemented THRs using cobalt chrome or stainless steel head with HCLPE liner/cup cost the NHS, on average, £13,101 (95%CI £13,080,£13,122), had an average quality-of-life score of 0.788 (95%CI 0.787,0.788), and a 10-year revision probability of 1.9% (95%CI 1.6,2.3). Compared to the reference, patients receiving a cemented THR with delta ceramic head and HCLPE liner/cup, hybrid THR with delta ceramic head and HCLPE liner/cup, and hybrid THR with alumina head and HCLPE liner/cup had lower 1-year costs (-£572 \[95% CI -£775,-£385\], -£346 \[-£501,-£192\], -£371 \[-£574,-£168\] respectively), better quality of life (0.007 \[95% CI 0.003,0.011\], 0.013 \[0.010,0.016\], 0.009 \[0.005,0.013\] respectively), and lower 10-year revision probabilities (1.4% \[1.03,2.0\], 1.5 \[1.3,1.7\], 1.6%\[1.2,2.1\] respectively).Implant bearing materials are associated with varying mean costs and health outcomes after primary THR. Ours is the first study to derive costs and health outcomes from large, linked databases using multiple imputation methods to deal with bias. Our findings are useful for commissioning and procurement decisions and to inform a subsequent cost-effectiveness model with more granular detail on THR implant types.

Real-World Healthcare Cost Savings and Reduced Relapse Rate with Off-Label Rituximab versus Disease-Modifying Treatments Approved for Relapsing-Remitting Multiple Sclerosis: A Nationwide Cost-Effectiveness Study.

Although off-label use of rituximab is a common alternative to disease-modifying therapies (DMTs) approved for multiple sclerosis (MS) in several countries, the impact of this on treatment cost-effectiveness is not well known. We evaluated the relative cost-effectiveness of rituximab and MS-approved DMTs in a register-based cohort study of Swedish residents with relapsing-remitting MS, aged 18-65 years, starting treatment with rituximab, natalizumab, fingolimod, or dimethyl fumarate between January 2010 and July 2016, and followed through July 2021 (n = 5,924). By linking the population-based Swedish MS register to several Swedish health care and demographic registers, we estimated health care costs in relation to number of relapses, over 5 years from treatment start. Differences between treatments were estimated in inverse probability of treatment-weighted regression models, adjusting for a broad range of potential confounders covering demographics, medical history, and MS-related clinical characteristics. Off-label rituximab was associated with both lower total health care costs (mean cost savings ranged $35,000-$66,000 vs. each approved DMT), and fewer relapses (mean number of prevented relapses ranged 0.12-0.22), per started therapy over 5 years. Results were robust to variations in discounting and pricing of health care visits, with the main driver of cost-savings being the price of the index drug itself. The cost-effectiveness of rituximab dominated the MS-approved alternatives. Off-label, low-dose rituximab should be considered for persons with MS and could reduce barriers to treatment, especially in resource-limited settings. ANN NEUROL 2024;95:1099-1111.

Health care resource utilization and costs associated with diagnosed medication overuse headache and potential acute medication overuse in individuals with migraine.

Estimate health care resource utilization and costs associated with medication overuse headache and potential acute medication overuse. A retrospective analysis was conducted with Clinformatics Data Mart data (1 January 2019-31 December 2019) that included continuously enrolled commercially insured adults with migraine (International Classification of Diseases, Tenth Revision, Clinical Modification [ICD-10-CM] code G43.xxx). Medication overuse headache was defined as ≥1 inpatient or ≥2 outpatient claims with an ICD-10-CM code G44.41/40 (drug-induced headache). Potential acute medication overuse was defined as possessing sufficient medication for >10 mean treatment days/month for ergots, triptans, opioids, or combination analgesics or >15 mean cumulative days/month for simple prescription analgesics (e.g., acetaminophen, aspirin, other non-opioid analgesics) for >6 consecutive months. All-cause and migraine-related health care resource utilization and costs were compared after adjusting for demographic and clinical characteristics. Among 90,017 individuals with migraine, the frequency of medication overuse headache/potential acute medication overuse was 12.6% (diagnosed medication overuse headache: 0.6%; potential acute medication overuse: 12.1%). Adjusted all-cause total costs ($31,235 vs $21,486; difference: $9,749 [P < 0.001]) and adjusted migraine-related total costs ($9,770 vs $6,207; difference: $3,563 [P < 0.001]) were higher in the medication overuse headache/potential acute medication overuse group versus those without medication overuse headache/potential acute medication overuse. Individuals with diagnosed medication overuse headache/potential acute medication overuse had higher all-cause and migraine-related health care resource utilization and costs versus individuals without medication overuse headache/potential acute medication overuse, suggesting that improved migraine management is needed to reduce associated costs.

The Economic Costs of Tobacco Related Illnesses in Kenya.

To estimate the economic costs of selected tobacco-related illnesses (TRI) in Kenya in 2022. This study was conducted in 2 phases. Phase 1, conducted between 2021 and 2022, entailed conducting a cross-sectional study conducted in 4 national public referral hospitals in Kenya. Patients with cardiovascular disease, cancer, chronic obstructive pulmonary disease, or tuberculosis were interviewed to compute the indirect and direct medical costs related to the illness. Activity-Based Costing approach was used to capture costs for services along the continuum of care pathway. In the second phase, the Tobacco Attributable Factor was used to estimate the direct, indirect, and ultimately economic cost due to tobacco smoking. The estimated health care cost attributed to tobacco use in Kenya is US$396,107,364. Among TRIs included in the study, myocardial infarction had the highest health care cost at US$158,687,627, followed by peripheral arterial disease and stroke with health care cost of US$64,723,181 and US$44,746,700 respectively. The main cost driver across all the illnesses is the cost for medication accounting for over 90% of the total health care cost. The productivity losses from the diseases ranged between US$148 to US$360 and accounted for 27% to 48% of the economic costs. The total cost attributable to tobacco use to Kenya's economy for the selected TRIs was between US$544.74 million and US$756.22 million. Tobacco related illnesses impose a significant economic burden as reported for direct and indirect costs. These findings underscore the need for strengthened implementation of the provision of the Framework Convention on Tobacco Control and the Tobacco Control Act (2007) to facilitate a reduction in tobacco consumption in the population.

Risk adjustment for regional healthcare funding allocations with ensemble methods: an empirical study and interpretation

We experiment with recent ensemble machine learning methods in estimating healthcare costs, utilizing Finnish data containing rich individual-level information on healthcare costs, socioeconomic status and diagnostic data from multiple registries. Our data are a random 10% sample (553,675 observations) from the Finnish population in 2017. Using annual healthcare cost in 2017 as a response variable, we compare the performance of Random forest, Gradient Boosting Machine (GBM) and eXtreme Gradient Boosting (XGBoost) to linear regression. As machine learning methods are often seen as unsuitable in risk adjustment applications because of their relative opaqueness, we also introduce visualizations from the machine learning literature to help interpret the contribution of individual variables to the prediction. Our results show that ensemble machine learning methods can improve predictive performance, with all of them significantly outperforming linear regression, and that a certain level of interpretation can be provided for them. We also find individual-level socioeconomic variables to improve prediction accuracy and that their effect is larger for machine learning methods. However, we find that the predictions used for funding allocations are sensitive to model selection, highlighting the need for comprehensive robustness testing when estimating risk adjustment models used in applications.

Epidemiology of Carpal Tunnel Syndrome and Trigger Finger in South Korea: A Nationwide Population-Based Study.

Carpal tunnel syndrome (CTS) and trigger finger are representative pathologic conditions of the hand. Although several studies have evaluated the epidemiology of these diseases as nationwide population-based research, they had several limitations including old data and short study period. We conducted a retrospective cohort study of patients aged ≥ 20 years diagnosed with CTS or trigger finger between 2009 and 2019 using the Korean Health Insurance Review and Assessment Service database. The annual incidence of these diseases was standardized based on age and sex. The proportion of patients who received corticosteroid injections or surgery within 1 year of their diagnoses was calculated annually. The mean annual incidence of CTS was 360.26 per 100,000 person-years and that of trigger finger was 63.09 per 100,000 person-years. The annual incidence of CTS (incidence rate ratio [IRR], 0.979; 95% confidence interval [CI], 0.972-0.985; p < 0.001) and trigger finger (IRR, 0.976; 95% CI, 0.967-0.985; p < 0.001) significantly decreased. The proportion of patients who received corticosteroid injections for CTS significantly increased (relative risk [RR], 1.025; 95% CI, 1.020-1.031; p < 0.001), while the number of surgeries significantly decreased (RR, 0.949; 95% CI, 0.940-0.957; p < 0.001). The proportion of patients who received corticosteroid injections for trigger finger significantly increased (RR, 1.021; 95% CI, 1.009-1.033; p < 0.001), while the number of surgeries did not change significantly (RR, 1.006; 95% CI, 0.988-1.023; p = 0.523). In the past 10 years, the incidence of CTS and trigger finger decreased. The portion of patients who received corticosteroid injections increased for both diseases, but the portion of patients who had surgery decreased for CTS within 1 year after diagnosis. This study provides insight into the epidemiology of these diseases in an Asian population and may inform estimates of healthcare costs.

Cost-Effectiveness of Performing Reference Ultrasonography in Patients with Deep Vein Thrombosis.

The diagnosis of recurrent ipsilateral deep vein thrombosis (DVT) with compression ultrasonography (CUS) may be hindered by residual intravascular obstruction after previous DVT. A reference CUS, an additional ultrasound performed at anticoagulant discontinuation, may improve the diagnostic work-up of suspected recurrent ipsilateral DVT by providing baseline images for future comparison. To evaluate the cost-effectiveness of routinely performing reference CUS in DVT patients. Patient-level data (n = 96) from a prospective management study (Theia study; NCT02262052) and claims data were used in a decision analytic model to compare 12 scenarios for diagnostic management of suspected recurrent ipsilateral DVT. Estimated health care costs and mortality due to misdiagnosis, recurrent venous thromboembolism, and bleeding during the first year of follow-up after presentation with suspected recurrence were compared. All six scenarios including reference CUS had higher estimated 1-year costs (€1,763-€1,913) than the six without reference CUS (€1,192-€1,474). Costs were higher because reference CUS results often remained unused, as 20% of patients (according to claims data) would return with suspected recurrent DVT. Estimated mortality was comparable in scenarios with (14.8-17.9 per 10,000 patients) and without reference CUS (14.0-18.5 per 10,000). None of the four potentially most desirable scenarios included reference CUS. One-year health care costs of diagnostic strategies for suspected recurrent ipsilateral DVT including reference CUS are higher compared to strategies without reference CUS, without mortality benefit. These results can inform policy-makers regarding use of health care resources during follow-up after DVT. From a cost-effectiveness perspective, the findings do not support the routine application of reference CUS.

Medical Costs Estimation Using Linear Regression Method

Medical costs are a significant issue in the health sector. High healthcare cost lead to the need to anticipate financial risks for individuals and insurance providers. Therefore, medical cost data analysis is necessary to estimate future medical expenses. This research implements data mining techniques using Simple and Multiple Linear Regression methods to estimate medical costs. The dataset used consists of insurance claim data obtained from Kaggle, which includes attributes such as age, gender, body mass index, number of children, smoking habits, region, and medical charges. The research findings that Multiple Linear Regression outperforms Simple Linear Regression in estimating the provided dataset, with R2 value of 80% and lower ?? MSE and MAE values than Simple Linear Regression. The application of linear regression in insurance claim data analysis can provide significant benefits for patients, hospitals, and insurance providers. Overall, this research highlights the effectiveness of data mining techniques, specifically linear regression, in estimating healthcare costs.

EVALUATE THE IMPACT OF INTERDISCIPLINARY EDUCATION AND TELEHEALTH PRIMARY CARE: QUALITY AND EFFICIENCY

Abstract In a provider shortage area, an Interprofessional Education and Telehealth Primary Care (IPETC) for geriatrics workforce was developed in 2020. To analyze the impact of IPETC on quality and efficiency of care, we measured quality outcomes defined by the CMS defined quality measures - dementia caregiver education/referral and advance care plan, and efficiency outcomes by estimating healthcare cost savings from reducing hospitalization. Two-hundred forty-four community-dwelling adults aged 60 to 97 with mild to moderate dementia were selected in an urban safety-net primary care clinic. Propensity - demographics and comorbidity was matched. Main outcomes were (A) number of hospitalization and 90-day rehospitalization rate, hospitalization-related healthcare cost estimates from the State Inpatient Dataset using the ICD-10 codes of principal diagnosis and hospital length of stay between January-December 2021. One-hundred twenty-two patients were cared by primary care providers who received the IPETC;122 patients were by those who did not have the IPETC; (2) CMS quality measures were compared between 2019 (baseline) and 2021 of patients cared by providers with IPETC. Number of hospitalization with IPETC was fewer than those without IPETC (0.72 vs. 1.38, p &amp;lt; .01). Number of 90-day rehospitalization with IPETC was fewer than those without IPETC (0.14 vs. 0.30, p &amp;lt; .01). An average cost-saving of $20,289 per patient was observed among those with IPETC than those without IPETC (p &amp;lt; .001). CMS quality measures improved from 15.6% to 51.0% in dementia caregiver education/referral; 10.2% to 24.7% in documented advance care plans.

EVALUATE THE IMPACT OF INTERDISCIPLINARY EDUCATION AND TELEHEALTH PRIMARY CARE: QUALITY AND EFFICIENCY

Abstract In a provider shortage area, an Interprofessional Education and Telehealth Primary Care (IPETC) for geriatrics workforce was developed in 2020. To analyze the impact of IPETC on quality and efficiency of care, we measured quality outcomes defined by the CMS defined quality measures - dementia caregiver education/referral and advance care plan, and efficiency outcomes by estimating healthcare cost savings from reducing hospitalization. Fifty eight community-dwelling adults aged 67 to 94 with mild to moderate dementia were selected in an urban safety-net primary care clinic. Propensity - demographics and level of physical impairment was matched. Main outcomes were (A) hospitalization-related healthcare cost estimates from the State Inpatient Dataset using the ICD-10 codes of principal diagnosis and hospital length of stay between January-December 2021. Twenty nine patients were cared by primary care providers who received the IPETC;29 patients were by those who did not have the IPETC; (2) CMS quality measures were compared between 2019 (baseline) and 2021. An average cost-saving of $22,135 per patient was observed among those treated by the healthcare providers who received the IPE/telehealth curriculum training than those treated by the providers without the training. CMS quality measures improved from 15.6% to 51.0% in dementia caregiver education/referral; 10.8% to 42.8% in documented advance care plans. Innovative interdisciplinary education and telehealth primary care has shown improvement of quality and efficiency of dementia care in a provider shortage area.

Implementation of VA care coordination program to improve transitional care for veterans post-non-VA hospital discharge: an incremental cost analysis.

The Veterans Affairs (VA) Healthcare System Community Hospital Transitions Program (CHTP) was implemented as a nurse-led intervention to reduce barriers that patients experience when transitioning from community hospitals to VA primary care settings. A previous analysis indicated that veterans who enrolled in CHTP received timely follow-up care and communications that improved care coordination, but did not examine cost implications for the VA. A budget impact analysis used the VA (payer) perspective. CHTP implementation team members and study records identified key resources required to initially implement and run the CHTP. Statistical analysis of program participants and matched controls at two study sites was used to estimate incremental VA primary care costs per veteran. Using combined program implementation, operations, and healthcare cost estimates to guide key model assumptions, overall CHTP costs were estimated for a 5-year time horizon, including a discount rate of 3%, annual inflation of 2.5%, and a sensitivity analysis that considered two options for staffing the program at VA Medical Center (VAMC) sites. Implementation at two VAMCs required 3 months, including central program support and site-level onboarding, with costs of $34,094 (range: $25,355-$51,602), which included direct and indirect resource costs of personnel time, materials, space, and equipment. Subsequent annual costs to run the program at each site depended heavily on the staffing mix and caseload of veterans, with a baseline estimate of $193,802 to $264,868. Patients enrolled in CHTP had post-hospitalization VA primary care costs that were higher than matched controls. Over 5 years, CHTP sites staffed to serve 25-30 veterans per full-time equivalent transition team member per month had an estimated budget impact of $625 per veteran served if the transitional team included a medical social worker to support veterans with more social behavioral needs and less complex medical cases or $815 per veteran if nurses served all cases. Evidence-based care coordination programs that support patients' return to VA primary care after a community hospital stay are feasible to implement and run. Further, flexibility in staffing this type of program is increasingly relevant as the VA and other healthcare systems consider methods to reduce provider burnout, optimize staffing, reduce costs, and address other staffing challenges while improving patient care.

Estimating Costs Associated with Disease Model States Using Generalized Linear Models: A Tutorial.

Estimates of costs associated with disease states are required to inform decision analytic disease models to evaluate interventions that modify disease trajectory. Increasingly, decision analytic models are developed using patient-level data with a focus on heterogeneity between patients, and there is a demand for costs informing such models to reflect individual patient costs. Statistical models of health care costs need to recognize the specific features of costs data which typically include a large number of zero observations for non-users, and a skewed and heavy right-hand tailed distribution due to a small number of heavy healthcare users. Different methods are available for modelling costs, such as generalized linear models (GLMs), extended estimating equations and latent class approaches. While there are tutorials addressing approaches to decision modelling, there is no practical guidance on the cost estimation to inform such models. Therefore, this tutorial aims to provide a general guidance on estimating healthcare costs associated with disease states in decision analytic models. Specifically, we present a step-by-step guide to how individual participant data can be used to estimate costs over discrete periods for participants with particular characteristics, based on the GLM framework. We focus on the practical aspects of cost modelling from the conceptualization of the research question to the derivation of costs for an individual in particular disease states. We provide a practical example with step-by-step R code illustrating the process of modelling the hospital costs associated with disease states for a cardiovascular disease model.