Journal Article

Autonomous artificial intelligence prescribing a drug to prevent severe acute graft-versus-host disease in HLA-haploidentical transplants

Li, Xueqian, Niu, Mingming, Zhao, Ningning, Wang, Mingyang, Cao, Yigeng, Xu, Mingyue, Song, Zhen, Xu, Yunqiang, Jiang, Erlie, Qi, Saibing, Liu, Sichang, Zhu, Xiaofan, Feng, Yahui, Zhai, Xiaolin, Shen, Qiujin, Chen, Junren, Feng, Sizhou, Han, Mingzhe, Yang, Donglin, Gong, Xiaowen, Chen, Mengyun, Zhang, Rongli, Li, Ruixin, Zhang, Dong, Wei, Jialin, Liu, Xueou, Zhang, Wei, Pan, Pan, Shao, Xianfeng, Yan, Wen, Zhai, Weihua, Gale, Robert Peter, Zhang, Xianjing, Liang, Chen, Guo, Ye, Zhai, Wangsong, Wang, Hong, Pang, Aiming, Luo, Jieya, Hu, Yu

2025

Overview

Autonomous artificial intelligence (AI) models for deciding treatment strategies are available but rarely applied prospectively in clinical settings. Here we present a prospective study of deploying daGOAT, an algorithm we have developed, as a conditional autonomous AI agent to prescribe a drug to prevent severe (grade 3−4) acute graft-versus-host disease (acute GvHD) following human leukocyte antigen (HLA)-mismatched haematopoietic cell transplantation (ClinicalTrials.gov, NCT05600855). During the enrollment period physicians invite 85% of eligible patients to participate and 88% of the invited patients agree. Among the 110 enrolled participants who receive HLA-haploidentical transplants, daGOAT predicts intermediate to high risk of severe acute GvHD in 57 participants between days +17 and +23 posttransplant and prescribes ruxolitinib in addition to the existing regimen to intensify immune suppression. The initial compliance with AI prescription is 98% (56/57), with dose and/or schedule deviating from the AI prescription within one month in a total of eight participants. In conclusion, we show that many physicians and patients are receptive to using conditional autonomous AI to prescribe a drug and that the decision for pharmaceutical intervention could be facilitated by autonomous AI. Autonomous artificial intelligence (AI) models to replace human decision-making in medical intervention need thorough testing. Here authors present the results of a clinical trial, NCT05600855, in which daGOAT, a conditional autonomous artificial intelligence agent successfully makes the decision whether to prescribe an immune suppressive drug to prevent severe acute graft-versus-host disease following HLA-mismatched haematopoietic cell transplantation.

• Publisher: Nature Publishing Group UK,Nature Publishing Group,Nature Portfolio
• Subject: 631/250/249/1529 / 639/705/1042 / 692/308/575 / Adolescent / Adult / Algorithms / Antigens / Artificial Intelligence / Biochemistry / Blood / Decision making / Disease prevention / Drug dosages / Female / Flow cytometry / Graft versus host disease / Graft vs Host Disease - immunology / Graft vs Host Disease - prevention & control / Graft-versus-host reaction / Grafting / Hematopoietic Stem Cell Transplantation - adverse effects / Hematopoietic stem cells / Histocompatibility antigen HLA / HLA Antigens - genetics / HLA Antigens - immunology / Hospitals / Humanities and Social Sciences / Humans / Hypothesis testing / Immunosuppressive Agents - therapeutic use / Information systems / Intervention / Leukocytes / Male / Middle Aged / multidisciplinary / Nitriles / Patients / Physicians / Prospective Studies / Pyrazoles / Pyrimidines / Science / Science (multidisciplinary) / Transplantation / Transplantation, Haploidentical - adverse effects / Transplants / Transplants & implants / Young Adult