Cost-Effectiveness Evaluation of Oral CGRP Antagonists, Atogepant and Rimegepant, for the Preventative Treatment of Episodic Migraine: Results from a US Societal Perspective Model.

BACKGROUND AND OBJECTIVES: Two oral calcitonin gene-related peptide (CGRP) antagonists, atogepant and rimegepant, were approved in 2021 for the preventive treatment of episodic migraine (EM), yet no formal cost-effectiveness analysis has been published. The objective of this study was to evaluate the cost-effectiveness of atogepant 60 mg and rimegepant 75 mg compared with placebo. METHODS: A decision tree model was constructed over a 1-year time horizon from a US societal perspective. Patient cohorts were simulated using baseline and change from baseline monthly migraine days (MMDs) reported in the trials to incorporate responder rates and within patient response into the model. Due to heterogeneity between the trial populations, each medication was compared with its respective trial's placebo group. Direct healthcare resource costs, productivity costs, acute medication costs, and quality-of-life values were obtained from the literature. RESULTS: The atogepant cohort experienced an incremental increase in healthcare plus productivity costs of $11,978 when compared with placebo, with a gain of 0.026 quality-adjusted life-years (QALYs). This yielded an incremental cost-effectiveness ratio (ICER) of more than $450,000/QALY. The rimegepant cohort experienced an incremental increase of $21,692 when compared with placebo, with a gain of 0.024 QALYs. This yields an ICER of more than $890,000/QALY when comparing rimegepant with placebo. Cost savings between atogepant and atogepant placebo were greatest with respect to acute medication costs at $735 of savings over 1 year, followed by savings of $135 for healthcare resource utilization and $34 for productivity costs. A similar relationship was seen between rimegepant and rimegepant placebo. One-way deterministic sensitivity analysis found that monthly acquisition costs of atogepant and rimegepant had the largest impact on the ICER, respectively. CONCLUSIONS: Atogepant and rimegepant were both unable to meet generally accepted cost-effectiveness thresholds < 150,0000/QALY. Additional studies are needed to better guide decision making regarding oral CGRPs' place in therapy.

Use of machine learning to predict bladder cancer survival outcomes: a systematic literature review.

INTRODUCTION: The objective of this systematic review is to summarize the use of machine learning (ML) in predicting overall survival (OS) in patients with bladder cancer. METHODS: Search terms for bladder cancer, ML algorithms, and mortality were used to identify studies in PubMed and Web of Science as of February 2022. Notable inclusion/exclusion criteria contained the inclusion of studies that utilized patient-level datasets and exclusion of primary gene expression-related dataset studies. Study quality and bias were assessed using the International Journal of Medical Informatics (IJMEDI) checklist. RESULTS: Of the 14 included studies, the most common algorithms were artificial neural networks (n = 8) and logistic regression (n = 4). Nine articles described missing data handling, with five articles removing patients with missing data entirely. With respect to feature selection, the most common sociodemographic variables were age (n = 9), gender (n = 9), and smoking status (n = 3), with clinical variables most commonly including tumor stage (n = 8), grade (n = 7), and lymph node involvement (n = 6). Most studies (n = 10) were of medium IJMEDI quality, with common areas of improvement being the descriptions of data preparation and deployment. CONCLUSIONS: ML holds promise for optimizing bladder cancer care through accurate OS predictions, but challenges related to data processing, feature selection, and data source quality must be resolved to develop robust models. While this review is limited by its inability to compare models across studies, this systematic review will inform decision-making by various stakeholders to improve understanding of ML-based OS prediction in bladder cancer and foster interpretability of future models.

An analysis type known as machine learning has recently become popular to predict survival in bladder cancer patients. However, there is debate on how to best use this method, as well as how to report the results of studies. This review looks at recently published machine learning studies, comparing various model details. Most studies found used hospital data, were clear about model factors, and used a model type called artificial neural networks. While these studies may be better at prediction compared to previous methods, there are consistency and clarity issues. Future studies should ensure that models are explainable and relevant to healthcare leaders.

Hospital outcomes and costs for prostate cancer patients with comorbid heart failure by age group: An analysis of the US Nationwide Inpatient Sample.

RATIONALE, AIMS, AND OBJECTIVES: The prevalence of patients hospitalized with comorbid prostate cancer (PC) and heart failure (HF) has been steadily increasing. Both diseases share a set of common risk factors, with the most prominent being age. This study aimed to examine the outcomes and costs for patients with comorbid PC and HF, stratified by age. METHODS: We analyzed 41,340 hospitalization events of patients with PC using the US National Inpatient Sample from 2015 to 2018. Associations of HF with in-hospital mortality, length of stay (LOS), and hospital costs per hospitalization were measured using multivariable logistic regression, negative binomial regression, and generalized linear regression with log-link and gamma distribution, respectively, controlling for covariates. Subgroup analyses were performed for age groups <65 and ≥65. RESULTS: Visits of comorbid HF patients made up 2.3% (n = 952) of the PC study sample. Compared with PC patients without HF, those with HF had higher in-hospital mortality rates (odds ratio = 1.33, 95% confidence interval [CI] = 0.96-1.84, p = 0.085), longer hospital stays (incidence rate ratio = 1.32, 95% CI = 1.21-1.44, p < 0.001), and higher hospital costs (cost ratio = 1.17, 95% CI = 1.07-1.27, p = 0.001), controlling for covariates. On average, this amounted to a higher in-hospital mortality rate of 2.10%, an increased LOS of 1.73 days, and higher hospital costs of $2110 per patient. While in-hospital mortality did not differ significantly in patients aged <65 (p = 0.900), patients aged ≥65 had a 41% increased risk of in-hospital mortality compared with those without HF (p = 0.047). CONCLUSIONS: In comparison to those without HF, PC patients with comorbid HF showed higher rates of in-hospital mortality, LOS, and hospital costs, with mortality showing a significant difference exclusively in the ≥65 population. Effective management of older patients with PC is needed to improve outcomes and decrease costs.