Kumar Sumeet, Rayal Snehil, Bommaraju Raghuram, Varasala Navya Pratyusha, Papineni Sirisha, Deo Sarang
Indian School of Business, Gachibowli, ISB Road, Hyderabad, India, +91 7075969318.
JMIR Form Res. 2025 Feb 10;9:e54156. doi: 10.2196/54156.
Tuberculosis (TB) is a major global health concern, causing 1.5 million deaths in 2020. Diagnostic tests for TB are often inaccurate, expensive, and inaccessible, making chest x-rays augmented with artificial intelligence (AI) a promising solution. However, whether providers are willing to adopt AI is not apparent.
The study seeks to understand the attitude of Ayurveda, Yoga and Naturopathy, Unani, Siddha, and Homoeopathy (AYUSH) and informal health care providers, who we jointly call AIPs, toward adopting AI for TB diagnosis. We chose to study these providers as they are the first point of contact for a majority of TB patients in India.
We conducted a cross-sectional survey of 406 AIPs across the states of Jharkhand (162 participants) and Gujarat (244 participants) in India. We designed the survey questionnaire to assess the AIPs' confidence in treating presumptive TB patients, their trust in local radiologists' reading of the chest x-ray images, their beliefs regarding the diagnostic capabilities of AI, and their willingness to adopt AI for TB diagnosis.
We found that 93.7% (270/288) of AIPs believed that AI could improve the accuracy of TB diagnosis, and for those who believed in AI, 71.9% (194/270) were willing to try AI. Among all AIPs, 69.4% (200/288) were willing to try AI. However, we found significant differences in AIPs' willingness to try AI across the 2 states. Specifically, in Gujarat, a state with better and more accessible health care infrastructure, 73.4% (155/211) were willing to try AI, and in Jharkhand, 58.4% (45/77) were willing to try AI. Moreover, AIPs in Gujarat who showed higher trust in the local radiologists were less likely to try AI (odds ratio [OR] 0.15, 95% CI 0.03-0.69; P=.02). In contrast, in Jharkhand, those who showed higher trust in the local radiologists were more likely to try AI (OR 2.11, 95% CI 0.9-4.93; P=.09).
While most AIPs believed in the potential benefits of AI-based TB diagnoses, many did not intend to try AI, indicating that the expected benefits of AI measured in terms of technological superiority may not directly translate to impact on the ground. Improving beliefs among AIPs with poor access to radiology services or those who are less confident of diagnosing TB is likely to result in a greater impact of AI on the ground. Additionally, tailored interventions addressing regional and infrastructural differences may facilitate AI adoption in India's informal health care sector.
结核病是全球主要的健康问题，2020年导致150万人死亡。结核病的诊断测试往往不准确、昂贵且难以获得，这使得借助人工智能（AI）辅助的胸部X光检查成为一个有前景的解决方案。然而，医疗服务提供者是否愿意采用人工智能尚不明朗。
本研究旨在了解阿育吠陀、瑜伽与自然疗法、尤纳尼、悉达和顺势疗法（AYUSH）从业者以及非正式医疗服务提供者（我们统称为AIPs）对采用人工智能进行结核病诊断的态度。我们选择研究这些提供者，因为他们是印度大多数结核病患者的首要接触点。
我们对印度贾坎德邦（162名参与者）和古吉拉特邦（244名参与者）的406名AIPs进行了横断面调查。我们设计了调查问卷，以评估AIPs对治疗疑似结核病患者的信心、他们对当地放射科医生解读胸部X光图像的信任度、他们对人工智能诊断能力的看法，以及他们采用人工智能进行结核病诊断的意愿。
我们发现，93.7%（270/288）的AIPs认为人工智能可以提高结核病诊断的准确性，而在那些相信人工智能的人中，71.9%（194/270）愿意尝试使用人工智能。在所有AIPs中，69.4%（200/288）愿意尝试使用人工智能。然而，我们发现两个邦的AIPs在尝试使用人工智能的意愿上存在显著差异。具体而言，在医疗保健基础设施更好且更易获得的古吉拉特邦，73.4%（155/211）愿意尝试使用人工智能，而在贾坎德邦，这一比例为58.4%（45/77）。此外，在古吉拉特邦，对当地放射科医生信任度较高的AIPs尝试使用人工智能的可能性较小（优势比[OR]为0.15，95%置信区间为0.03 - 0.69；P = 0.02）。相比之下，在贾坎德邦，对当地放射科医生信任度较高的人更有可能尝试使用人工智能（OR为2.11，95%置信区间为0.9 - 4.93；P = 0.09）。
虽然大多数AIPs相信基于人工智能的结核病诊断的潜在益处，但许多人并不打算尝试使用人工智能，这表明从技术优势衡量的人工智能预期益处可能不会直接转化为实际影响。提高那些难以获得放射学服务或对结核病诊断信心不足的AIPs的信念，可能会使人工智能在实际应用中产生更大影响。此外，针对地区和基础设施差异的定制干预措施可能有助于印度非正式医疗保健部门采用人工智能。
