Journal of managed care & specialty pharmacy最新文献

{"title":"The burden of heart failure in the United States: Medical costs and health-related quality of life.","authors":"Maria Alva, Sarahfaye Dolman, Slaven Sikirica, Paul Kolm, Katherine Andrade, Zugui Zhang, William S Weintraub","doi":"10.18553/jmcp.2026.32.6.670","DOIUrl":"10.18553/jmcp.2026.32.6.670","url":null,"abstract":"<p><strong>Background: </strong>Heart failure (HF) is a leading cause of morbidity, mortality, and health care utilization in the United States. Its burden is expected to increase with population aging and the growing prevalence of diabetes, yet comprehensive estimates of health care costs and health-related quality of life (HRQoL) stratified by age and diabetes status-2 key drivers of HF risk and resource use-remain limited.</p><p><strong>Objective: </strong>To quantify the economic burden and HRQoL impact of HF in the United States, stratified by age and diabetes status.</p><p><strong>Methods: </strong>Using a micro-level, bottom-up prevalence-based approach from a payer perspective, we analyzed health care costs from the Optum Research Database. HF prevalence and HRQoL via EuroQol 5-Dimensions and Healthy Days instruments were estimated using the National Health and Nutrition Examination Survey.</p><p><strong>Results: </strong>The average annual direct health care cost per patient with HF was approximately $31,464 at baseline, rising to $45,893 in the first year after diagnosis before stabilizing around $37,500 annually. Inpatient and emergency care accounted for the largest cost share. Extrapolating at the national level, expenditures exceeded $227 billion at baseline and peaked at $332 billion in the year following an HF hospitalization. Individuals without diabetes had the highest quality-adjusted life-years (QALYs) and lowest costs, whereas patients with type 1 diabetes had the lowest QALYs and highest costs. Patients with type 2 diabetes represented the largest subgroup with intermediate QALYs but substantial costs.</p><p><strong>Conclusions: </strong>HF imposes a significant, sustained economic and quality-of-life burden, highlighting the need for targeted management strategies, especially for older adults and those with diabetes.</p>","PeriodicalId":16170,"journal":{"name":"Journal of managed care & specialty pharmacy","volume":"32 6","pages":"670-678"},"PeriodicalIF":3.3,"publicationDate":"2026-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13193315/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147987900","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Health care costs associated with disease progression of untreated chronic hepatitis C in the United States.","authors":"Suk-Chan Jang, Ji Haeng Heo, Shao-Hsuan Chang, Mahek Garg, Ikenna Unigwe, Haesuk Park","doi":"10.18553/jmcp.2026.32.6.643","DOIUrl":"10.18553/jmcp.2026.32.6.643","url":null,"abstract":"<p><strong>Background: </strong>Despite effective direct-acting antiviral therapies, two-thirds of US patients with chronic hepatitis C remain untreated, leading to significant public health and economic challenges. However, data on the economic burden of untreated chronic hepatitis C in the direct-acting antiviral era remain limited.</p><p><strong>Objective: </strong>To estimate health care costs related to disease progression among untreated, newly diagnosed adults with chronic hepatitis C in the United States.</p><p><strong>Methods: </strong>We conducted a retrospective observational study using US national commercial insurance data from January 2013 to December 2023. The cohort included adults aged 18 years or older with newly diagnosed, treatment-naive, and untreated chronic hepatitis C. Patients were categorized by liver disease stage-specific periods (chronic hepatitis C, compensated cirrhosis, decompensated cirrhosis, hepatocellular carcinoma, and liver transplantation), defined by the earliest recorded diagnosis of each stage and censored at progression. Liver disease-related costs, defined as costs with a primary diagnosis corresponding to these stages, were estimated using a 2-part model to account for excess zero costs. All-cause costs were estimated using generalized linear models with a γ distribution. Costs were calculated per person per month in 2023 US dollars.</p><p><strong>Results: </strong>Among 36,923 untreated patients with chronic hepatitis C, adjusted all-cause health care costs per patient per month increased substantially with disease progression: $4,483 (95% CI = $4,326-$4,640) for chronic hepatitis C, $6,240 ($5,570-$6,910) for compensated cirrhosis, $14,166 ($12,259-$16,073) for decompensated cirrhosis, $19,021 ($15,283-$22,758) for hepatocellular carcinoma, and $27,836 ($9,325-$46,348) at the liver transplant stage (<i>P</i> < 0.001). Liver-related costs rose from 1.6% ($70) at the chronic hepatitis C stage to 30.4% ($5,791) at hepatocellular carcinoma, and 57.4% ($15,986) of all-cause costs at the liver transplant stage (<i>P</i> < 0.001).</p><p><strong>Conclusions: </strong>These findings highlight the critical importance of early treatment to reduce health care costs and improve clinical outcomes. Early screening and treatment can prevent progression to high-cost advanced liver disease.</p>","PeriodicalId":16170,"journal":{"name":"Journal of managed care & specialty pharmacy","volume":"32 6","pages":"643-650"},"PeriodicalIF":3.3,"publicationDate":"2026-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13193320/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147987802","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Clinical and economic burden of recurrence among older patients with locoregionally advanced head and neck squamous cell carcinoma in the United States.","authors":"Dandan Zheng, Su Zhang, Behzad Bidadi, Nati Lerman, Yan Song, Yuexin Tang, Rui Song, Jiayang Li, Anyu Zhu, James Signorovitch, Sanjay Merchant, Glenn J Hanna","doi":"10.18553/jmcp.2026.32.6.704","DOIUrl":"10.18553/jmcp.2026.32.6.704","url":null,"abstract":"<p><strong>Background: </strong>There is limited prior literature comparing survival and economic outcomes between those with and without recurrent disease among older individuals aged at least 66 years with locoregionally advanced head and neck squamous cell carcinoma (LA HNSCC).</p><p><strong>Objective: </strong>To estimate the burden of recurrence among older patients with LA HNSCC in the United States.</p><p><strong>Methods: </strong>Older patients diagnosed with LA HNSCC (2007-2019) from the linked Surveillance, Epidemiology, and End Results (SEER)-Medicare data were included. Overall survival (OS), health care resource utilization (HCRU), and health care costs were compared between patients with or without recurrence, separately for patients receiving surgical (resected) vs nonsurgical (unresected) primary treatment.</p><p><strong>Results: </strong>In the resected group (n = 502), 333 patients experienced recurrence and had a 63% increased risk of death vs nonrecurrent patients (adjusted hazard ratio [aHR] = 1.63; 95% confidence interval [CI] = 1.24-2.15; P < 0.001). In those unresected (n = 1,217), 791 patients experienced recurrence and had a 77% increased risk of death (aHR = 1.77; 95% CI = 1.49-2.10; P < 0.001). Recurrence was associated with higher HCRU and monthly health care costs in both resected ($3,831; 95% CI = $2,319-$5,360) and unresected ($4,730; 95% CI = $3,611-$5,870) groups (P < 0.001).</p><p><strong>Conclusions: </strong>Recurrence in older patients with LA HNSCC is associated with shorter OS and higher HCRU/health care costs.</p>","PeriodicalId":16170,"journal":{"name":"Journal of managed care & specialty pharmacy","volume":"32 6","pages":"704-716"},"PeriodicalIF":3.3,"publicationDate":"2026-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13193321/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147987708","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"ICER report demonstrates both the value and challenges in financing of weight loss medications.","authors":"Sujith Ramachandran, Ben Urick, Tara Thomas","doi":"10.18553/jmcp.2026.32.6.753","DOIUrl":"10.18553/jmcp.2026.32.6.753","url":null,"abstract":"<p><p>Two out of 5 US adults live with obesity, generating substantial clinical and economic burden. Recent glucagon-like peptide-1 receptor agonists (GLP-1 RAs), including semaglutide and tirzepatide, demonstrate significant weight loss and cardiometabolic benefits and were found by the Institute for Clinical and Economic Review (ICER) to be cost-effective compared with lifestyle modifications alone. However, even limited uptake exceeds ICER's annual budget impact threshold, prompting access concerns. The latest real-world evidence demonstrates that persistence for these drugs is lower than in clinical trials, resulting in frequent weight regain after discontinuation, tempering expectations of long-term medical cost offsets. Evidence on medical spending impact is mixed, with cost-offset signals only observed among patients with obesity and diabetes receiving high-potency injectable agents, whereas obesity-only populations often show spending increases. Given current coverage restrictions, this commentary recommends combining drug coverage with lifestyle management programs, avoiding arbitrary duration limits, using targeted prior authorization, and exploring innovative payment models to improve access while managing budget impact.</p>","PeriodicalId":16170,"journal":{"name":"Journal of managed care & specialty pharmacy","volume":"32 6","pages":"753-757"},"PeriodicalIF":3.3,"publicationDate":"2026-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13193314/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147987857","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Predicting pharmacy choice for managed care network design.","authors":"Michael Irungu, Suhila Sawesi, Mohamed Rashrash, Pranitha Presingu, Kyle Kane, Jon Schommer, Lawrence Brown","doi":"10.18553/jmcp.2026.32.6.679","DOIUrl":"10.18553/jmcp.2026.32.6.679","url":null,"abstract":"<p><strong>Background: </strong>Pharmacy type selection is a key component of medication access and use. Prior studies have commonly used logistic regression to examine pharmacy type choice, but this approach may not fully capture complex relationships among patient characteristics.</p><p><strong>Objective: </strong>To examine patient characteristics associated with pharmacy type selection and to compare the performance of traditional logistic regression with ensemble machine learning models for predicting pharmacy type selection.</p><p><strong>Methods: </strong>We conducted a cross-sectional analysis of adults participating in the 2021 National Consumer Survey on Medication Experience (NCSME-PR; n = 1,502). The outcome was the pharmacy type selected when a prescription medication was needed, categorized as chain, independent, supermarket, mass merchandise, mail-order, or clinic-based pharmacy. Predictors included patient characteristics defined by the Andersen Behavioral Model of Health Services Use, encompassing predisposing, enabling, and need factors. We compared logistic regression with random forest and extreme gradient boosting (XGBoost) models using 5-fold cross-validation and held-out test data. Model discrimination was assessed using the area under the receiver operating characteristic curve.</p><p><strong>Results: </strong>Across pharmacy types, ensemble models demonstrated higher discrimination than logistic regression, with XGBoost achieving the highest area under the receiver operating characteristic curve values. Prior mail-order pharmacy use, number of chronic conditions, income, and US region were consistently associated with the selection of pharmacy type. Ensemble models captured nonlinear patterns in these associations that were not fully reflected in logistic regression models.</p><p><strong>Conclusions: </strong>Pharmacy type selection varies by patient characteristics and pharmacy type, and predictive performance differs by analytic approach. Comparative modeling indicates that conclusions about pharmacy choice may depend on the modeling framework used. These findings contribute to pharmacy choice research and highlight considerations for future studies using managed care administrative data.</p>","PeriodicalId":16170,"journal":{"name":"Journal of managed care & specialty pharmacy","volume":"32 6","pages":"679-690"},"PeriodicalIF":3.3,"publicationDate":"2026-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13193322/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147987902","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Effect of the initial combination approach vs initial monotherapy approach on 1-year trajectories of adherence in drug-naive patients with type 2 diabetes.","authors":"Bilqees Fatima, Sai S Cheruvu, Zahra Majd, Susan Abughosh","doi":"10.18553/jmcp.2026.32.6.717","DOIUrl":"10.18553/jmcp.2026.32.6.717","url":null,"abstract":"<p><strong>Background: </strong>The choice of initial pharmacotherapy approach may influence the medication-taking behavior of patients with type 2 diabetes (T2D). However, there remains a notable gap in the literature to assess the longitudinal adherence pattern of 2 treatment approaches, initial combination vs initial monotherapy with as-needed intensification.</p><p><strong>Objective: </strong>To assess the impact of the initial combination therapy approach vs the initial monotherapy approach with as-needed intensification on adherence trajectories and factors associated with the trajectories.</p><p><strong>Methods: </strong>Retrospective study using Merative MarketScan research databases (2017-2019). We have included continuously enrolled drug-naive patients with T2D who received initial monotherapy with as-needed intensification or initial combination therapy. Adherence was measured 12 months after the index date using the proportion of days covered (PDC). Monthly PDC was incorporated into a logistic group-based trajectory model, and patients were categorized into trajectory groups. A multinomial logistic regression model was conducted to examine the association of the diabetes management approach (combination vs initial monotherapy with as-needed intensification) on resultant adherence trajectory, adjusting for baseline characteristics.</p><p><strong>Results: </strong>We identified 116,597 Commercial/Medicare and 18,295 patients with Medicaid insurance. The 4-group and 3-group trajectory models for Commercial/Medicare and Medicaid patients, respectively, were selected. Within 1-year follow-up period, odds of lower adherence trajectories were higher for patients receiving initial combination therapy vs initial monotherapy with as-needed intensification group in both populations (Commercial/Medicare; rapid decline: odds ratio [OR] = 1.73, 95% CI = 1.65-1.8; gradual decline: OR = 1.50, 95% CI = 1.41-1.60; gaps in adherence: OR = 1.40, 95% CI = 1.31-1.45; Medicaid; rapid decline trajectory: OR = 1.32, 95% CI = 1.16-1.50).</p><p><strong>Conclusions: </strong>Findings highlighted better adherence patterns among patients receiving initial monotherapy with as-needed intensification compared with initial combination therapy during 1-year post-treatment initiation.</p>","PeriodicalId":16170,"journal":{"name":"Journal of managed care & specialty pharmacy","volume":"32 6","pages":"717-734"},"PeriodicalIF":3.3,"publicationDate":"2026-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13193323/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147987750","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Prevalence, adherence, and health care resource utilization in schizophrenia: A national and state-level analysis of US Medicaid Beneficiaries.","authors":"Joseph Parks, Pin Xiang, Ravi Patel, Kaitlyn McBride, Halley Costantino, Sana Mirza, Kinga Borsos","doi":"10.18553/jmcp.2026.32.6.691","DOIUrl":"10.18553/jmcp.2026.32.6.691","url":null,"abstract":"&lt;p&gt;&lt;strong&gt;Background: &lt;/strong&gt;Schizophrenia is a chronic and debilitating mental disorder that imposes substantial health care challenges, particularly among Medicaid beneficiaries. Despite the vulnerability of this population, a comprehensive understanding of national and state-level prevalence, adherence, and health care resource utilization (HCRU) remains limited.&lt;/p&gt;&lt;p&gt;&lt;strong&gt;Objective: &lt;/strong&gt;To estimate the prevalence of schizophrenia among Medicaid beneficiaries at national and state levels and to characterize their sociodemographic profiles, medication adherence, and HCRU across care settings.&lt;/p&gt;&lt;p&gt;&lt;strong&gt;Methods: &lt;/strong&gt;This retrospective cohort study used the Transformed Medicaid Statistical Information System Analytic Files from 2016 to 2022. Adults aged 18 years and older with at least 2 schizophrenia claims on separate dates were included. National and state-level prevalence analyses were conducted among all Medicaid beneficiaries, including Medicaid-only (beneficiaries enrolled exclusively in Medicaid) and dual-eligible beneficiaries (those enrolled in both Medicaid and Medicare). Descriptive analyses were conducted among Medicaid-only beneficiaries in the most recent study period (2022) to assess sociodemographic characteristics, adherence to antipsychotics (measured using the proportion of days covered [PDC], with adherence defined as PDC≥80%), and HCRU across settings, including inpatient and outpatient services, emergency department visits, and home health.&lt;/p&gt;&lt;p&gt;&lt;strong&gt;Results: &lt;/strong&gt;From 2016 to 2022, the national prevalence of schizophrenia among all Medicaid beneficiaries decreased from 2.6% to 1.7%; however, the absolute number of affected individuals increased from 834,920 to 956,023, with California and New York reporting the largest patient populations. In 2022, a total of 143,970 Medicaid-only beneficiaries with schizophrenia were identified. The mean age was 41.9 years, with the largest proportion being male (56.4%) and non-Hispanic White (41.8%). Medication adherence was low, with fewer than 30% of patients with any antipsychotic prescription achieving a PDC greater than or equal to 80%. During the 12-month follow-up period, 44.9% of patients had at least 1 inpatient admission, and 54.6% of those hospitalized had at least 1 mental health-related admission. During the same 12-month period, 68.8% of patients had at least 1 mental health outpatient visit, with a mean of 30.6 visits among those with any mental health outpatient care.&lt;/p&gt;&lt;p&gt;&lt;strong&gt;Conclusions: &lt;/strong&gt;Schizophrenia remains highly prevalent in the Medicaid population at both national and state levels and continues to place substantial demands on the health care system. Low medication adherence and high HCRU among this population highlight ongoing unmet needs. These findings emphasize the need for targeted, system-level strategies to improve access, adherence, and coordinated care for individuals with schizophrenia within Medicaid programs.&lt;/p","PeriodicalId":16170,"journal":{"name":"Journal of managed care & specialty pharmacy","volume":"32 6","pages":"691-703"},"PeriodicalIF":3.3,"publicationDate":"2026-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13193317/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147987981","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Assessing the impact of pharmacist-led interventions on glucagon-like peptide 1 receptor agonist access and treatment outcomes.","authors":"Haley Huddleston, Jodi Martinez, Jerilyn Cook, Melissa Trapp, Nai-Chia Chen, Kelsey Schwander, Sarah Moss, Surabhi Palkimas","doi":"10.18553/jmcp.2026.32.6.651","DOIUrl":"10.18553/jmcp.2026.32.6.651","url":null,"abstract":"<p><strong>Background: </strong>Glucagon-like peptide 1 receptor agonists (GLP-1 RAs) have gained popularity because of their demonstrated efficacy in weight loss, resulting in access barriers such as delays due to prior authorizations (PAs), insurance coverage restrictions, and limited availability. The national average for PA turnaround times is currently 72 hours. To offer solutions to these barriers, the University of Colorado Hospital (UCHealth) has integrated a pharmacy team into their primary care practice setting to provide specialized support to enhance access.</p><p><strong>Objective: </strong>To evaluate how pharmacist-led interventions affected PA turnaround times for GLP-1 RAs prescribed for weight loss. Additionally, we aimed to characterize these interventions to better understand the pharmacist's role in integrated care teams for weight management.</p><p><strong>Methods: </strong>This retrospective cohort study used UCHealth electronic health records to evaluate pharmacist-led interventions identified by multistep order transmittal workflow in September 2024. The primary endpoint was PA turnaround time. The secondary endpoints included time to GLP-1 RA initiation, qualitative assessments of pharmacist-led interventions, and dosing optimizations. Survival analyses and descriptive analyses were conducted for time-to-event and qualitative endpoints.</p><p><strong>Results: </strong>A total of 142 patients were included in this study. Fifty-six patients were observed in the PA-approved group and 86 patients in the PA-denied group. The median turnaround time for any PA decision was 19.87 hours (95% CI = 6.88-23.58). PA approvals had a median turnaround time of 47.1 hours (95% CI = 23.4-69.6), whereas PA denials had 3.6 hours (95% CI = 2.4-16.7) (<i>P</i> = 0.0072). Documented interventions included patient updates on PA status, insurance plan criteria reviews, provider collaboration, alternative therapy recommendations, copay resources, insurance outreach, and dose clarification.</p><p><strong>Conclusions: </strong>Integrating pharmacists into care teams can enhance GLP-1 RA PA turnaround times while improving medication access, safety, and continuity of care. These findings support further research and policy development in pharmacist interventions in PA process and GLP-1 RA management.</p>","PeriodicalId":16170,"journal":{"name":"Journal of managed care & specialty pharmacy","volume":"32 6","pages":"651-659"},"PeriodicalIF":3.3,"publicationDate":"2026-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13193319/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147987777","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"The effectiveness and value of cytisinicline for smoking cessation: A summary from the institute for clinical and economic review's midwest comparative effectiveness public advisory council.","authors":"Dmitriy Nikitin, Jeffrey A Tice, Kangho Suh, Sol Sanchez, Marina Richardson, Marie Phillips, Josh J Carlson, Hui-Hsuan Chan, David M Rind, Foluso Agboola","doi":"10.18553/jmcp.2026.32.6.748","DOIUrl":"10.18553/jmcp.2026.32.6.748","url":null,"abstract":"","PeriodicalId":16170,"journal":{"name":"Journal of managed care & specialty pharmacy","volume":"32 6","pages":"748-752"},"PeriodicalIF":3.3,"publicationDate":"2026-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13193316/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147987954","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Machine learning evaluation of racial and ethnic inclusion under alternative cost-based approaches to Medicare Medication Therapy Management eligibility.","authors":"Chi Chun Steve Tsang, Yan Cui, William C Cushman, Junling Wang","doi":"10.18553/jmcp.2026.32.6.736","DOIUrl":"10.18553/jmcp.2026.32.6.736","url":null,"abstract":"<p><strong>Background: </strong>The eligibility framework for the Medicare Medication Therapy Management (MTM) program has been associated with a lower likelihood of meeting enrollment criteria among racial and ethnic minority beneficiaries compared with their non-Hispanic White (White) counterparts. To optimize the MTM program design, the Centers for Medicare and Medicaid Services launched the Enhanced MTM demonstration, granting Part D plans greater flexibility to test alternative eligibility strategies. Many plans have adopted predictive modeling and cost-based criteria; however, their equity implications remain unclear.</p><p><strong>Objective: </strong>To assess and compare how alternative cost-based eligibility schemes, implemented using machine learning models, influence predicted racial and ethnic inclusion in potential MTM eligibility.</p><p><strong>Methods: </strong>A retrospective, cross-sectional analysis was conducted using a 10% national sample of Medicare fee-for-service beneficiaries in 2019. Two binary outcomes were defined using the top quartile of total health care costs and combined hospitalization and emergency department (ED) costs as eligibility thresholds. Five machine learning algorithms, including regularized logistic regression, random forest, gradient-boosted trees, support vector machines, and multilayer perceptron, were developed for each cost-based scheme. Their predicted probabilities were combined using a soft-voting ensemble to generate consensus estimates of potential eligibility. A multinomial logistic regression model was then used to assess associations between race and ethnicity and predicted inclusion across the 2 cost-based schemes, adjusting for predisposing, enabling, and need factors based on the Gelberg-Andersen model.</p><p><strong>Results: </strong>The analytic sample included 1,848,654 Medicare beneficiaries, with 75% designated as the training population and the remaining 25% as the test population. Racial and ethnic differences in predicted eligibility varied by cost-based scheme. Compared with White beneficiaries, Black (relative risk ratio [RRR] = 4.31; 95% CI = 3.92-4.75) and Hispanic (RRR = 2.28; 95% CI = 2.04-2.56) beneficiaries had a higher likelihood of inclusion under the hospitalization and ED-based scheme only, relative to inclusion under the total health care cost-based scheme only, whereas Asian (RRR = 0.24; 95% CI = 0.19-0.29) and Other (RRR = 0.43; 95% CI = 0.36-0.52) racial groups had lower likelihoods.</p><p><strong>Conclusions: </strong>Alternative cost-based definitions of MTM eligibility identify different beneficiary populations across racial and ethnic groups. Incorporating hospitalization and ED costs may improve representation of Black and Hispanic beneficiaries in potential MTM eligibility. These findings highlight the need for transparency and continued evaluation of algorithmic eligibility frameworks to ensure equitable access to medication management services.</p>","PeriodicalId":16170,"journal":{"name":"Journal of managed care & specialty pharmacy","volume":"32 6","pages":"736-747"},"PeriodicalIF":3.3,"publicationDate":"2026-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13193318/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147987975","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}