AI-assisted warfarin dose optimisation with CURATE.AI for clinical impact: Retrospective data analysis

Abstract

Background: Standard-of-care for warfarin dose titration is conventionally based on physician-guided drug dosing. This may lead to frequent deviations from target international normalized ratio (INR) due to inter- and intra-patient variability and may potentially result in adverse events including recurrent thromboembolism and life-threatening hemorrhage.

Objectives: We aim to employ CURATE.AI, a small-data, artificial intelligence-derived platform that has been clinically validated in a range of indications, to optimize and guide warfarin dosing.

Patients/methods: A personalized CURATE.AI response profile was generated using warfarin dose (inputs) and corresponding change in INR between two consecutive days (phenotypic outputs) and used to identify and recommend an optimal dose to achieve target treatment outcomes. CURATE.AI's predictive performance was then evaluated with a set of metrics that assessed both technical performance and clinical relevance.

Results and conclusions: In this retrospective study of 127 patients, CURATE.AI fared better in terms of Percentage Absolute Prediction Error and Percentage Prediction Error of 20% compared to other models in the literature. It also had negligible underprediction bias, potentially translating into lower bleeding risk. Modeled potential time in therapeutic range with CURATE.AI was not significantly different from physician-guided dosing, so it is on-par yet provides a systematic approach to warfarin dosing, easing the mental-burden on guesswork by physicians.This study lays the groundwork for the prospective study of CURATE.AI as a clinical decision support system. CURATE.AI may facilitate the effective use of affordable warfarin with a well-established safety profile, without the need for costly, new oral anticoagulants. This can have significant impact both on the individual and public health.

Keywords: artificial intelligence; blood coagulation; clinical; decision support systems; precision medicine; warfarin.

FIGURE 1

CURATE.AI quadratic and linear process with simulated data. Simulated records of patient's prescribed warfarin doses and their corresponding INR measurements were used. CURATE.AI Quadratic (a, b) The patient's initial profile (blue) was calibrated using dose–response data pairs on days 1 to 3. The profile was used to predict the patient's ∆INR and INR response to the warfarin dose given on day 4. Numbers within the circles correspond to the dosing days with the given warfarin dose. (a) Initial calibrated profile (blue) using the dose–response data pairs from days 1 to 3. (b) Assuming no systemic and regimen changes, the profile evolves to include the observed dose–response data pair on day 4. CURATE.AI Linear (c and d): The patient's initial profile (blue) was calibrated using dose response data pairs on days 1 and 2. The profile was used to predict the patient's ∆INR and INR response to the warfarin dose given on day 3. Numbers within the circles correspond to the dosing days with the given warfarin dose. (c) Initial calibrated profile (blue) using the dose–response data pairs from days 1 and 2. (d) With no systemic and regimen changes, the profile evolves to include the observed dose–response data pair on day 3.

FIGURE 2

Decision flowchart of modeled potential TTR. Each prediction instance is first determined if they count as a success instance using an algorithm.

FIGURE 3

Internal validation data screening flow. A total of N = 127 de‐identified patient data were retrieved from the Discovery.AI Platform. N = 92 and N = 118 patient data met the requirements of a minimum of 3 and 2 modulated doses and corresponding response readout for CURATE.AI Quadratic and CURATE.AI Linear profile analysis, respectively. N = 9 patient data did not meet the requirement and were excluded from the analysis. N = number of patients.

FIGURE 4

INR distribution. Raw and predicted INR boxplots for INR measured in patients in standard of care (N = 118, n = 1507) and predicted using CURATE.AI Quadratic (N = 92, n = 777) and CURATE.AI Linear (N = 118, n = 1016). Interquartile ranges are 0.98, 0.95, and 0.94 for standard of care, CURATE.AI Quadratic and CURATE.AI Linear, respectively. The lower bar and upper bar indicate median ± 1.5*IQR. Dashed lines represent the assumed 2–3 therapeutic range. N = number of patients, n = total number of measured events or predicted events.

FIGURE 5

Serial Percentage Absolute Prediction Error (PAPE). Median PAPE for the first four serial INR predictions for CURATE.AI Quadratic (N = 62) CURATE.AI Linear (N = 75) and Vadher et al.'s Bayesian PKPD model (N = 74). The error bar represents 95% confidence interval. Comparison rests on the assumption that the underlying samples validated for each model are representative of a sample of patient population. N = number of patients.

FIGURE 6

Percentage prediction error (PPE). INR PPE for both CURATE.AI quadratic (n = 777) and linear (n = 1016). Interquartile ranges (IQR) are 31.2 and 29.7 for CURATE.AI quadratic and linear, respectively. The lower bar and upper bar indicate median ± 1.5*IQR. Dashed lines represent the ±20% threshold for ideal predictions. n = total number of prediction events.

FIGURE 7

(a) INR clinical prediction error (CPE). CPE, in terms of INR units for both CURATE.AI quadratic (n = 614) and CURATE.AI linear (n = 774). Interquartile ranges (IQR) are 0.64 and 0.61 for CURATE.AI quadratic and linear, respectively. The lower bar and upper bar indicate median ± 1.5*IQR. Dashed lines represent the ±2.0 and ±0.5 threshold for ideal predictions. (b) Bias (INR units). Bias, expressed as prediction error for CURATE.AI quadratic (n = 614) and CURATE.AI linear (n = 774). The lower bar and upper bar represent the lower and upper range of 95% CI, respectively. (c, d) Modeled potential TTR (%). Modeled potential TTR expressed as percentage, for both (c) CURATE.AI quadratic (N = 91) and (d) CURATE.AI linear (N = 118) against physician‐guided dosing. The error bar represents the lower and upper range of 95% confidence interval, respectively. Normality testing performed using Shapiro–Wilk at 0.05 level of significance. Statistical comparison was performed with Wilcoxon signed rank test at 0.05 level of significance. N = number of patients. n = total number of prediction events.

FIGURE 8

Bar plots comparing between CURATE.AI quadratic and linear in terms of precision, bias and modeled potential TTR (%). (a) PAPE for both CURATE.AI quadratic and linear (n = 777). (b) PPE for both CURATE.AI quadratic and linear (n = 777). (c) Modeled potential TTR (%) for CURATE.AI Quadratic and Linear (N = 91). The lower bar and upper error bar represents 95% confidence interval. Comparison rests on the assumption that the underlying samples validated for each model are representative of a sample of patient population. No statistically significant difference was detected between the conditions t with Wilcoxon signed rank test at α = 0.05. N = number of patients. n = total number of prediction events.

FIGURE 9

Proposed CURATE.AI Integration into a Clinical Workflow. Standard of care: Warfarin dose and corresponding INR response for a patient on anticoagulation therapy are charted and dose decision by the clinician is heavily relied on clinical experience. CURATE.AI: CURATE.AI maps the warfarin (inputs) dose and corresponding INR response (outputs) for that individual to calibrate a personalized dose–response profile. From this profile, CURATE.AI will recommend optimal doses to achieve the target INR to the clinician and, as a future possibility, potentially to patients for self‐management of oral anticoagulation.