Navitskas, Serena D.

Abstract Background Interpretation of multi-analyte laboratory profiles, such as lupus anticoagulant (LAC) testing, requires integration of numerous test results and clinical information. However, this process is time-consuming, requires domain knowledge, and has limited scalability. Given that rule-based systems are rigid and difficult to maintain and large language models pose risks of “hallucinations,” we developed and evaluated a novel retrieval-based approach to automate LAC profile interpretation to improve efficiency while maintaining fidelity and reliability for clinical use. Methods Our method processes laboratory values through ensemble random forest (RF) models to retrieve the most similar expert interpretation from a curated database of 347 previously interpreted LAC profiles. The system's performance was assessed through technical accuracy metrics, a work flow efficiency timing study, and expert review of interpretation accuracy for held-out cases. Results Technical validation demonstrated high accuracy in retrieving correct interpretative elements (median: 93% accuracy, interquartile range [IQR]: 67% to 100%). Retrieval accuracy was highly correlated with the prevalence of a given element (ρ = 0.8307). In a timing study of 93 consecutive LAC profiles, ensemble-assisted interpretation achieved a median time of 22 s per report (IQR: 16 s to 31 s), representing a 78.6% total reduction compared to manual interpretation (median: 118 s, IQR: 96 s to 172 s; t = 18.61, P < 0.001). Furthermore, 92.5% of AI-assisted interpretations were completed within 60 s, exceeding the target of 85%. Expert review confirmed 100% concordance for LAC presence/absence. Conclusions The proposed approach significantly improves efficiency of complex laboratory interpretation for LAC profiles, while maintaining consistency and high fidelity. Future studies will explore the method’s inherent extensibility to the interpretation of other multi-analyte laboratory profiles.

AbstractHospitalized patients with COVID‐19 infection frequently have coagulopathy resembling disseminated intravascular coagulation (DIC). An elevation of D‐dimer level is associated with a poor prognosis; however, the role of other fibrin degradation products, such as soluble fibrin monomers (SFMC), is not known.The objective of the study was to investigate the frequency and prognostic role of elevated SFMC in patients with COVID‐19. In this retrospective cohort study, patients hospitalized between April 1, 2020 and December 14, 2020 at Mayo Clinic with COVID‐19 infection who underwent DIC panel testing were identified. Results of laboratory tests and outcomes (thrombosis and death) within 40 days of testing were obtained via medical record review.Of 108 patients, D‐dimer was elevated in 82 (75.9%) patients. Of those with elevated D‐dimer, SFMC was elevated in 19/82 (23%) patients. There were 16 thrombotic events and 16 deaths during the 40‐day follow‐up. The incidence of overt‐DIC was 4.6%. In univariate analysis, D‐dimer ≥5 x highest upper limit normal (ULN) and elevated SFMC were each associated with higher 40‐day mortality. However, when used in combination with D‐dimer ≥5 x highest ULN, an elevated SFMC provided no further mortality predictive value.Compared to 75.9% of patients with elevated D‐dimers, of those tested, only 23% had elevated SFMC. These results support the hypothesis that elevated D‐dimer in COVID‐19 infection is a direct consequence of endothelial damage and not overt‐DIC.