Nonfasting, Telehealth-Ready LDL-C Testing With Machine Learning to Improve Cardiovascular Access and Equity

Importance Current LDL-C testing requires 9–12 hour fasting and in-person visits, creating an access crisis: 40% of lipid panels occur outside fasting windows (yielding unreliable results), 60% of US counties lack cardiology services, and millions of patients with diabetes cannot safely fast. Meanwhile, telehealth infrastructure expanded 38-fold post-COVID, yet lipid workflows remain anchored to 1970s protocols. This mismatch drives ~ 20 million unnecessary repeat visits annually, disproportionately burdening Medicaid populations, essential workers, and rural communities.

To demonstrate that machine learning can transform lipid testing from a fasting-dependent, clinic-based bottleneck into an accurate, equitable, telehealth-ready service—eliminating three structural barriers simultaneously: fasting requirements, in-person visits, and racial algorithmic bias. Design, Setting, and Participants Cross-sectional analysis of All of Us Research Program (n=3,477; test n=696). Crucially, 40.1% were tested outside traditional fasting windows, reflecting real-world practice. We evaluated performance stratified by fasting status, telehealth feasibility (labs-only configuration), racial equity metrics, and economic impact. Main Outcomes and Measures Primary: MAE and calibration in non-fasting states. Secondary: Labs-only non-inferiority (±0.5 mg dL−1margin); racial equity (Black-White performance gap); economic savings from eliminated repeat visits; and classification accuracy at treatment thresholds (70, 100, 130 mg dL−1).

The ML system demonstrated paradoxical superiority in non-fasting conditions—precisely when needed most. While equations deteriorated (Friedewald MAE 29.1 vs 25.9 mg dL−1fasting, slopes 0.58–0.61), ML maintained accuracy (24.0 vs 23.2 mg dL−1, slopes 0.99–1.07), achieving 17.2% improvement over Friedewald when non-fasting vs 10.4% fasting. Labs-only configuration proved non-inferior (MAE=-0.12, p<0.001), enabling national retail-pharmacy and home-testing workflows. The system achieved racial equity without race input (Black-White gap −0.19 mg dL−1, CI includes zero) while providing greatest improvement for Black patients (19% vs 11% for White). Economically, eliminating 4,000 repeat visits per 10,000 tests helps address an estimated $2 billion annual repeat-testing cost burden and yields $815,000 total savings per 10,000 tests ($245,000 direct healthcare, $570,000 patient costs), with break-even at just 750 tests.

and Relevance This ML approach helps address an estimated $2 billion annual problem of repeat testing while tackling three critical quality gaps in cardiovascular prevention: delayed treatment initiation, poor monitoring adherence, and specialty access barriers. By enabling accurate non-fasting, telehealth-compatible, race-free LDL-C estimation, it transforms lipid testing from an access barrier into an access enabler—particularly for the Medicaid, Medicare Advantage, and rural populations who drive both cost and outcomes in value-based care. From a technical standpoint, implementation requires only routine labs and <100 ms computation, making deployment feasible with existing infrastructure. Competing Interest Statement The authors have declared no competing interest. Funding Statement This work was supported in part by the National Institute on Minority Health and Health Disparities of the National Institutes of Health (Award 2U54MD007597). The funder had no role in the study design, data collection, data monitoring, analysis, interpretation, manuscript preparation, or the decision to submit. No author or author institution received payments, services, or other support from any third party for any aspect of the submitted work beyond this grant. The content is solely the responsibility of the authors and does not necessarily represent the official views of the NIH. Author Declarations I confirm all relevant ethical guidelines have been followed, and any necessary IRB and/or ethics committee approvals have been obtained. Yes The details of the IRB/oversight body that provided approval or exemption for the research described are given below: Ethics Committee/Institutional Review Board of Howard University determined that this analysis was exempt from additional review (Category 4) because it used de-identified human data from the NIH All of Us Research Program (controlled tier). The All of Us Research Program operates under a single IRB protocol approved by the U.S. National Institutes of Health, and all participants provided informed consent at enrollment. I confirm that all necessary patient/participant consent has been obtained and the appropriate institutional forms have been archived, and that any patient/participant/sample identifiers included were not known to anyone (e.g., hospital staff, patients or participants themselves) outside the research group so cannot be used to identify individuals. Yes I understand that all clinical trials and any other prospective interventional studies must be registered with an ICMJE-approved registry, such as ClinicalTrials.gov. I confirm that any such study reported in the manuscript has been registered and the trial registration ID is provided (note: if posting a prospective study registered retrospectively, please provide a statement in the trial ID field explaining why the study was not registered in advance). Yes I have followed all appropriate research reporting guidelines, such as any relevant EQUATOR Network research reporting checklist(s) and other pertinent material, if applicable. Yes Footnotes ronald.doku{at}howard.edu | nanayaw.osafo{at}bison.howard.edu | jkwagyan{at}howard.edu | wsoutherland{at}howard.edu This revision clarifies why the work is needed now by linking non fasting LDL C testing to post COVID telehealth growth, expanding use of modern therapies, and current efforts to remove race based adjustments from clinical algorithms. We better quantify how often tests are non fasting, how this drives repeat visits and delays, and which groups are most affected, including rural, Medicaid, essential workers, and people with diabetes. We simplify and clarify the economic analysis and equity framing, and we made minor edits to improve clarity and remove nonstandard symbols without changing any results. Data Availability This study used de-identified data from the NIH All of Us Research Program (version 7), available through the All of Us Researcher Workbench (https://www.researchallofus.org ). Access is granted to qualified investigators at institutions with an active Data Use Agreement who complete the required training and registration. No new datasets were generated outside this platform. Data Availability De-identified data are available via controlled access through the All of Us Researcher Workbench (https://www.researchallofus.org) for investigators at institutions with an active All of Us Data Use Agreement who complete required training.