Application of machine learning in affordable and accessible insulin management for type 1 and 2 diabetes: A comprehensive review.

Proper insulin management is vital for maintaining stable blood sugar levels and preventing complications associated with diabetes. However, the soaring costs of insulin present significant challenges to ensuring affordable management. This paper conducts a comprehensive review of current literature on the application of machine learning (ML) in insulin management for diabetes patients, particularly focusing on enhancing affordability and accessibility within the United States. The review encompasses various facets of insulin management, including dosage calculation and response, prediction of blood glucose and insulin sensitivity, initial insulin estimation, resistance prediction, treatment adherence, complications, hypoglycemia prediction, and lifestyle modifications. Additionally, the study identifies key limitations in the utilization of ML within the insulin management literature and suggests future research directions aimed at furthering accessible and affordable insulin treatments. These proposed directions include exploring insurance coverage, optimizing insulin type selection, assessing the impact of biosimilar insulin and market competition, considering mental health factors, evaluating insulin delivery options, addressing cost-related issues affecting insulin usage and adherence, and selecting appropriate patient cost-sharing programs. By examining the potential of ML in addressing insulin management affordability and accessibility, this work aims to envision improved and cost-effective insulin management practices. It not only highlights existing research gaps but also offers insights into future directions, guiding the development of innovative solutions that have the potential to revolutionize insulin management and benefit patients reliant on this life-saving treatment.

A short-term economic evaluation of early insulin therapy compared to oral anti-diabetic drugs in order to reduce the major adverse events in type 2 diabetes patients in Iran.

OBJECTIVE: While there are some recommendations about early insulin therapy in newly diagnosed Type 2 Diabetes Mellitus (T2DM) patients, there is not sufficient evidence on this strategy's cost-effectiveness. This study compared early insulin therapy versus oral anti-diabetic drugs (OADs) for managing T2DMusing a cost-effectiveness analysis approach in Iran. METHODS: In this economic evaluation, a decision analytic model was designed. The target population was newly diagnosed type 2 diabetic patients, and the study was carried out from the perspective of Iran's healthcare system with a one-year time horizon. Basal insulin, Dipeptidyl peptidase-4 (DPP-4) inhibitors, and Thiazolidinediones (TZDs) were compared in this evaluation. The main outcome for assessing the effectiveness of each intervention was the reduction in the occurrence of diabetes complications. Strategies were compared using the incremental cost-effectiveness ratio (ICER), and deterministic and probabilistic sensitivity analyses were carried out. RESULTS: The DPP-4 inhibitors strategy was the dominant strategy with the highest effectiveness and the lowest cost. Early insulin therapy was dominated (ICER: $-53,703.18), meaning that it was not cost-effective. The sensitivity analyses consistently affirmed the robustness of the base case findings. The probabilistic sensitivity analysis indicated probabilities of 77%, 22%, and 1% for DPP-4 inhibitors, TZDs strategies, and early insulin therapy, respectively, in terms of being cost-effective. CONCLUSION: In terms of cost-effectiveness, early insulin therapy was not cost-effective compared to OADs for managing newly diagnosed T2DM patients. Future studies in this regard, utilizing more comprehensive evidence, can yield more accurate results.

The impact of a statewide insulin copay cap policy for insured patients with diabetes in Utah.

BACKGROUND: Insulin affordability is a huge concern for patients with diabetes in the United States. On March 30, 2020, Utah signed House Bill 207 into law, aimed at capping copayments for insulin at $30 for a 30-day supply. The bill was enacted on January 1, 2021. OBJECTIVE: To assess patient basal insulin adherence, out-of-pocket costs, health plan costs, total costs on insulin, and hemoglobin A1c (A1c) in prepolicy vs postpolicy periods. METHODS: This study is a retrospective analysis using data from a regional health plan in Utah from October 1, 2019, to September 30, 2021. Inclusion criteria were fully enrolled members of all ages, under commercial insurance, with at least 1 fill for any type of insulin in both the preperiod and the postperiod. Adherence was measured by proportion of days covered (PDC). Paired t-tests and Wilcoxon sign rank tests were conducted to compare the health and economic outcomes. RESULTS: Out of 24,150 commercially insured individuals, a total of 244 patients were included. Across all 244 patients, there was a significant decline in monthly median out-of-pocket costs of insulin by 58.5% (P < 0.001), whereas the monthly median health plan costs of insulin increased by 22.0% (P < 0.001). The total monthly costs of insulin (the sum of out-of-pocket and health plan costs) were unchanged (P = 0.115). Only 74 patients with enough basal insulin fills in both periods were included in the analysis for PDC changes. PDC change was not statistically significant (P = 0.43). Among the 74 patients with PDC calculations, 29 patients had A1c recorded in both periods. The change in A1c was not statistically significant (P = 0.23). CONCLUSIONS: An insulin copayment max of $30 in Utah demonstrated lower patient out-of-pocket costs, subsidized by the health plan. PDC did not change, and HbA1c did not improve. An assessment of a longer period and on a larger population is needed.

The Cost-Effectiveness of an Advanced Hybrid Closed-Loop System Compared to Standard Management of Type 1 Diabetes in a Singapore Setting.

Background: Despite advances in technology, glycemic outcomes in people with type 1 diabetes (T1D) remain suboptimal. The MiniMed 780G (MM780G) advanced hybrid closed-loop (AHCL) system is the latest technology for T1D management with established safety and efficacy. This study explores the cost-effectiveness of MM780G AHCL compared against multiple daily injections (MDI) plus intermittently scanned continuous glucose monitor (isCGM). Methods: A cost-utility analysis was conducted, simulating lifetime outcomes for 1000 T1D individuals, with baseline hemoglobin A1c of 8.4%, using the IQVIA Core Diabetes Model (CDM) v9.5. A Singapore health care payer perspective was taken with 2023 costs applied. Treatment effects were taken from the ADAPT study and treatment-related events from a combination of sources. T1D complication costs were derived from local literature, and health state utilities and disutilities from published literature. Scenario analyses and probabilistic sensitivity analyses (PSAs) explored uncertainty. Cost-effectiveness was assessed based on willingness-to-pay (WTP) thresholds set to Singapore Dollars (SGD) 45,000 (United States Dollars [USD] 33,087) per quality-adjusted life year (QALY) and Singapore's gross domestic product (GDP) per capita of SGD 114,165 (USD 83,941) per QALY. Results: A switch from MDI plus isCGM to MM780G resulted in expected gains in life-years (+0.78) and QALYs (+1.45). Cost savings through reduction in T1D complications (SGD 25,465; USD 18,723) partially offset the higher treatment costs in the AHCL arm (+SGD 74,538; +USD 54,805), resulting in an estimated incremental cost-effectiveness ratio of SGD 33,797 (USD 24,850) per QALY gained. Findings were robust, with PSA outputs indicating 81% and 99% probabilities of cost-effectiveness at the stated WTP thresholds. Conclusion: MM780G is a cost-effective option for people with T1D managed in a Singapore setting.

Insulin Fills by Medicare Enrollees and Out-of-Pocket Caps Under the Inflation Reduction Act.

This study uses data from IQVIA's National Prescription Audit to assess the association of the Inflation Reduction Act's cap on cost sharing with insulin fills by Medicare beneficiaries.

Assessment of Commercial and Mandatory Discounts in the Gross-to-Net Bubble for the Top Insulin Products From 2012 to 2019.

Importance: Insulin list prices have grown substantially since 2010, but net prices have declined since 2015 because of manufacturer discounts, leading to an increasingly large difference between list and net prices of drugs often called the gross-to-net bubble. It remains unclear to what extent the gross-to-net bubble represents voluntary manufacturer discounts negotiated in commercial and Medicare Part D markets (hereafter called commercial discounts) vs mandatory discounts under the Medicare Part D coverage gap, Medicaid, and the 340B program. Objective: To decompose the overall gross-to-net bubble of leading insulin products into discount types. Design, Setting, and Participants: This economic evaluation obtained data from Medicare and Medicaid claims and spending dashboards, Medicare Part D Prescriber Public Use File, and SSR Health for the top 4 commonly used insulin products: Lantus, Levemir, Humalog, and Novolog. The gross-to-net bubble, which represents total discounts, was estimated for each insulin product and year (from 2012 to 2019). Analyses were conducted in June to December 2022. Main Outcomes and Measures: The gross-to-net bubble was decomposed into 4 discount types: (1) Medicare Part D coverage gap discounts, (2) Medicaid discounts, (3) 340B discounts, and (4) commercial discounts. Coverage gap discounts were estimated using Medicare Part D claims data. Medicaid and 340B discounts were estimated using a novel algorithm that accounted for best prices set by commercial discounts. Results: Total discounts for the 4 insulin products increased from $4.9 billion to $22.0 billion. Commercial discounts represented a majority of all discounts, increasing from 71.7% of the gross-to-net bubble in 2012 ($3.5 billion) to 74.3% ($16.4 billion) in 2019. Among mandatory discounts, coverage gap discounts remained relatively consistent as a proportion of discounts (5.4% in 2012 vs 5.3% in 2019). Medicaid rebates decreased as a proportion of total discounts, from 19.7% in 2012 to 10.6% in 2019. The 340B discounts increased as a proportion of total discounts from 3.3% in 2012 to 9.8% in 2019. Results for the contribution of discount types to the gross-to-net bubble were consistent across insulin products. Conclusions and Relevance: Results of a decomposition of the gross-to-net bubble for leading insulin products suggest that commercial discounts play a growing role in lowering net sales compared with mandatory discounts.

Cost-Related Insulin Rationing in US Adults Younger Than 65 Years With Diabetes.

This study uses 2021 National Health Interview Survey data to examine the prevalence of insulin rationing among adults younger than 65 years in the US by demographic characteristics.

Clinical, Economic, and Patient-Reported Benefits of Connected Insulin Pen Systems: A Systematic Literature Review.

INTRODUCTION: The objective of this systematic literature review was to evaluate the available literature concerning the clinical, economic, and patient-reported benefits of insulin pen platforms, including connected insulin pens/caps/sleeves and insulin platforms, as well as mobile apps capable of receiving near real-time insulin dosing information. METHODS: Medline and Embase databases and the Cochrane Library were searched for published literature between January 2015 and May 2021, and manual searches for conference abstracts from 2018 to May 2021 were performed. These searches were supplemented by internet searches for relevant literature and clinical trials. Study selection involved the population, intervention, comparator, outcomes, time frame, and study design outline. Included studies investigated connected insulin systems or connected caps/sleeves enabling pens to be connected, or apps able to connect to these systems, in individuals of all ages with type 1 or type 2 diabetes mellitus. RESULTS: Searches identified a total of 26 publications (mostly observational studies and conference abstracts) for inclusion, representing ten unique, predominantly small studies. Evidence in this field is still in its early stages, and only two randomized controlled trials met our inclusion criteria. Available results showed that connected insulin pens and their systems potentially helped reduce suboptimal insulin use and may therefore improve glycemic control. Satisfaction of people with diabetes with the technologies used was high, and economic benefits were noted. Features of effective connected insulin pen devices include simplicity of use and data upload/sharing, useful "point-of-care" alerts, and simple and understandable data presentation to facilitate more effective consultations. CONCLUSIONS: Connected insulin pen systems could be increasingly considered as part of routine clinical care for insulin-treated persons with diabetes who must manage the complexity of their daily insulin routine. Future research focusing on the way data obtained from these devices can be most effectively used alongside other information is urgently needed.

Digital health tools, like text message reminders and mobile apps, are being used more often to help people with diabetes improve their health in a way that works for them. For people who take insulin to treat their diabetes, what has been missing is a way to track insulin doses alongside other diabetes information in an app. Connected insulin pens, also called smart pens, are able to do this. In this article we have looked at the evidence available on the benefits of connected insulin pens. We found that while information on connected insulin pens is limited at the moment, what there is shows that using a connected insulin pen can help people remember to take their insulin and give themselves the right dose and that those who have used a connected insulin pen or related technology are happy with it. Useful features of connected insulin pens include being easy to use, having an alert function, and being able to share the insulin information with the user's doctor. Connected insulin pens may also reduce diabetes-related costs. Connected insulin pens are likely to become more common for people with diabetes who take insulin, but there is a need for more research on how best to use them to improve the treatment of people with diabetes.

Incentivizing Prescription Drug Switching to Reduce Patient and Health Plan Spending: A Microsimulation Model.

OBJECTIVES: Most spending for prescription drugs is on branded drugs that do not have direct generic equivalents but many of these drugs do have therapeutic alternatives within class. We estimate the potential savings from providing patients a financial incentive to switch from a higher cost drug to a lower cost, therapeutic alternative drug. METHODS: We used individual state-transition microsimulations to model medication use and spending with and without financial incentives over a 12-month time horizon with a healthcare sector perspective. Costs and utilization inputs were from individuals on branded insulins or multiple sclerosis drugs enrolled in a regional mixed-model health maintenance organization. Base-case model used a one-time financial incentive of $83 and $250 offered to patients on higher cost insulin and multiple sclerosis treatments, respectively, to switch to lower cost drugs within class. RESULTS: Savings per individual offered an incentive in the insulin and multiple sclerosis classes were, respectively, $84 (95% CI $46-$122) and $2,127 (95% CI $267-$3,987). Varying the incentive size and switch probability resulted in maximum savings of $712 at elasticity of 0.2 and incentive size $250 for the insulin drug class. For the multiple sclerosis drug class, maximum savings of $5945 was at elasticity of 0.2 and incentive size of $1000. Short time horizon makes our savings estimates conservative. CONCLUSIONS: If programs such as financial incentives could encourage even a small proportion of patients to switch among drugs within therapeutic class, then substantial savings could be generated.

The impact of biosimilar insulins on the diabetes landscape.

The cost of diabetes care in the United States continues to rise, with insulin costs growing rapidly. Accessibility and affordability of these life-saving medications are concerns for providers and patients that need to be addressed. Availability of biosimilar insulin products may help address these issues by introducing additional competition to the insulin market, but they may also face adoption challenges from patients and health care providers alike. In addition, policymakers at state and federal levels are examining and addressing rising insulin costs through legislative and administrative actions. The purpose of this paper is to review the current US diabetes landscape, highlight the differences between biosimilar insulins and follow-on insulins and considerations for successful adoption of biosimilar insulins, and review the current policy landscape regarding rising insulin costs. DISCLOSURES: This Viewpoints article was supported by Sandoz, Inc. Wagner and Patel are employees of Sandoz, Inc. White was employed by Sandoz, Inc., at the time of this study.

A century past the discovery of insulin: global progress and challenges for type 1 diabetes among children and adolescents in low-income and middle-income countries.

Type 1 diabetes is on the rise globally; however, the burden of mortality remains disproportionate in low-income and middle-income countries (LMICs). As 2021 marks 100 years since the discovery of insulin, we revisit progress, global burden of type 1 diabetes trends, and understanding of the pathogenesis and management practices related to the disease. Despite much progress, inequities in access and availability of insulin formulations persist and are reflected in differences in survival and morbidity patterns related to the disease. Some of these inequities have also been exacerbated by health-system challenges during the COVID-19 pandemic. There is a clear opportunity to improve access to insulin and related essential technologies for improved management of type 1 diabetes in LMICs, especially as a part of universal health coverage. These improvements will require concerted action and investments in human resources, community engagement, and education for the timely diagnosis and management of type 1 diabetes, as well as adequate health-care financing. Further research in LMICs, especially those in Africa, is needed to improve our understanding of the burden, risk factors, and implementation strategies for managing type 1 diabetes.

Availability, affordability and price components of insulin products in different-level hospital pharmacies: Evidence from two cross-sectional surveys in Nanjing, China.

The essential medicine--insulin cannot be easily accessed and afforded in many countries. To help address this issue, we evaluated the availability, affordability and price of insulin products in Nanjing, eastern China. Two cross-sectional studies were conducted in 2016 and 2018. A total of 56 hospital pharmacies were sampled, using a simplified and adapted World Health Organization/Health Action International (WHO/HAI) methodology. Prices were expressed as Median Price Ratios (MPRs) to Australian Pharmaceutical Benefit Scheme (PBS) prices. In addition, we investigated the price components of seven selected insulin products as a case study before and after the Online Centralized Procurement Policy for Hospital Drugs in May, 2018. Affordability was presented as the number of daily wages of the lowest paid unskilled government worker (LPGW) required to purchase 1000IU of insulin based on the average courses of treatment, approximately 30 days' treatment. The availability of insulin products was very high in secondary hospitals and tertiary hospitals both in 2016 and 2018, but in community hospitals was very low. In 2018, the availability of prandial insulin products showed fluctuation compared to 2016. The availability of pre-mixed human insulin products was over 95% overall, and also very high (80%) in community hospitals in 2018. The prices of insulin products were much lower than PBS prices of Australian in this study, with the MPRs less than 1 (0.32 to 0.71 in 2016 vs. 0.30 to 0.68 in 2018) for all insulin types. But insulin products in Nanjing in 2016 and 2018 were considered unaffordable, because the number of daily wages of the LPGW needed to purchase for the 30 days treatment of insulin products ranged from 2.26 to 8.49 in 2016 and 1.88 to 7.09 in 2018. The manufacturers' selling price contributed the main part (74.15% to 77.70% before and 74.86% to 91.51% after the implementation of the bidding policy) of the price components of target insulin brands. The availability of insulin products was high in secondary hospitals and tertiary hospitals, but lower in community hospitals. However, the affordability in community hospitals was better than other hospitals, but the insulin products were still unaffordable for patients on low incomes. Further improvements of the availability accessibility and affordability of medicines in advancing health insurance policies and lowering drug prices should be put forward.

Use of the Whole Country Insulin Consumption Data in Israel to Determine the Prevalence of Type 1 Diabetes in Children <5 Years of Age Before and During Rotavirus Vaccination.

BACKGROUND: Recent studies showed that rotavirus vaccination may affect the prevalence of type 1 diabetes (T1D). The aim of the study was to determine the prevalence of early childhood (<5 years) T1D before and during the introduction of rotavirus vaccination in Israel by syndromic surveillance. METHODS: Data on insulin purchases reported by Israel's four Health Maintenance Organizations (HMOs) were retrieved from the National Program for Quality Indicators in Community Healthcare. RESULTS: During the prevaccination years (2002-2007), a steady increase in insulin purchases was reported in the young (<5 years). The period percent change (PC) of children <5 years old diagnosed with T1D inferred from purchased insulin prescriptions increased by 50.0%, and the annual percent change (APC) increased by 10.0% (p = 0.01). During the period of free, universal Rotavirus vaccination (2011-2018), the PC for T1D diagnoses among children <5 years of age decreased by 3.8% with an APC of -2.5% (p = 0.14). There was a significant difference (p = 0.002) between the increasing trend in insulin use before vaccination versus the decreasing trend after vaccination. CONCLUSION: Rotavirus vaccination correlated with attenuation of the increasing rate in the prevalence of T1D in <5-year-old children in Israel.

Changes in Type 2 Diabetes Medication Utilization and Costs in the United States, 2014-2019.

OBJECTIVE: The objective of this study was to describe national changes in utilization and associated costs of antidiabetic medications in the United States from 2014 to 2019, across different drug classes and insurance plans. RESEARCH DESIGN AND METHODS: This retrospective, cross-sectional study examined administrative claims from a large national pharmacy benefits manager from January 1, 2014, to December 31, 2019. Patients aged 18 years and above enrolled in commercial, Medicare, or Medicaid health plans who filled ≥1 prescription claim for an antidiabetic medication(s) during the 6-year period were included. Utilization was examined as the total number of 30-day adjusted prescription fills per user per month (PUPM). Gross costs were calculated as the sum of plan costs (net of rebates) and member out-of-pocket costs. Differences in mean utilization and costs PUPM between 2014 and 2019 for each medication class were calculated. RESULTS: The final analytic sample increased from 745,290 patients in 2014 to 1,596,006 in 2019. Antidiabetic medication utilization increased by 8.8% from 2014 to 2019, driven by increases in sodium-glucose cotransporter 2 inhibitor (48.7%; P<0.001), glucagon-like peptide 1 receptor agonist (11.8%; P<0.001), insulin (8.1%; P<0.001), and metformin (2.9%; P<0.05) utilization. Average costs PUPM rose 47.5% (P<0.001), from $126.52 in 2014 to $186.58 in 2019. Sodium-glucose cotransporter 2 inhibitors, glucagon-like peptide 1 receptor agonists, and combination drugs contributed significantly to these increased costs, with 6-year cost differences of 57.3%, 46.9%, and 47.2%, respectively (all P<0.001). CONCLUSION: Our study demonstrates a shift in antidiabetic medication class utilization from 2014 to 2019, where associated costs net of rebates significantly increased to a disproportionately greater extent than the significant increase in utilization PUPM.