Objective:To evaluate an anticoagulation management method based on mobile health technology and artificial intelligence.Methods:The study was a single-center, prospective, randomized, controlled, non-inferiority clinical trial. From November 2017 to September 2018, 67 patients who received warfarin therapy after mechanical valve replacement were consecutively enrolled and randomized into two groups: 34 were randomized to intervention group and 33 to control group. The intervention group was managed via Anticlot Assistant and the control group was handled as routine care. Evaluations were performed at least 3 months after enrollment and ended on 30 September 2019. Non-inferiority was evaluated using one-sided tests with a non-inferiority margin set 11.0% for time in therapeutic range (TTR) and 10.0% for the percentage of international normalized ratio (INR) in the therapeutic range.Results:The mean TTR was (58.2±23.4)% in the intervention group and (54.8±23.6)% in the control (the difference: 3.4%; low limit of one-side 95% confidence interval for the difference: -6.4%; and P value for non-inferiority was 0.009). The percentage of INR in the therapeutic range was (55.4±21.9)% in the intervention group and (52.8±22.5)% in the control (the difference: 2.6%, low limit of one-side 95% confidence interval for the difference: -6.6%; and P value for non-inferiority was 0.012). Conclusion:The outcomes of patients managed via the anticoagulation management method base on mobile health technology and artificial intelligence are not inferior to those handled as routine care.

Objective    To verify the reliability of Anticlot Assistant, a patient self-management system for warfarin therapy assisted by artificial intelligence. Methods    It was a single-center, prospective cohort study. The eligible 34 participants were recruited consecutively between November 29, 2017 to September 27, 2018 and managed by warfarin therapy via Anticlot Assistant. The recommendations of Anticlot Assistant were examined and verified by the doctors to ensure the security. Medical records were exported from the the background management system. An univariate analysis compared the outcomes between accepted and overridden records and a logistic regression model was built to determine independent predictors of the outcomes. The research team analyzed 153 medical records, which were from 18 participants and were input by 19 doctors. There were 97 records with doctor accepting the suggestion and 56 records with doctor rejecting the suggestion . Results    When the doctors accepted the recommendations, the percentage of the next-test international normalized ratio (INR) in the therapeutic range was higher (64.95% vs. 44.64%, RR=2.298, 95%CI 1.173 to 4.499, P=0.014). The logistic regression analysis revealed that accepting the recommendations was an independent predictor for the next-test INR being in the therapeutic range after controlling potentially confounding factors (OR=2.446, 95%CI 1.103 to 5.423, P=0.028). Conclusion    The algorithm of Anticlot Assistant is reasonable and reliable.