JMIR Publications

ABSTRACT

Background:

Due to the large population of hypertensives in Shanghai, the limited manpower of community health services, and the uneven level of management services, the follow-up of hypertensives in the community is inefficient and lacks quality, especially the telephone follow-up. Improving the blood pressure control rate and management is challenging.

Objective:

To evaluate the efficiency and reliability of artificial intelligence (AI) telephone follow-up in the management of hypertension.

Methods:

During May 18 and June 30, 2020, 350 hypertensives managed by the Pengpu Community Health Service Center of Jingan District in Shanghai were recruited for follow-up, once by AI and once by a human. The second follow-up was conducted within 3~7 days (mean 5.5 days) after the first survey. Cohen's Kappa coefficient was used to evaluate the reliability of the results between the two follow-up visits.

Results:

The mean length time of AI calls was shorter (4.15 minutes) than that of manual calls (5.22 minutes). The answers related to the hypertension symptoms showed moderate to substantial consistency (Kappa coefficient: 0.482–0.642), and those related to the complications showed fair consistency (Kappa coefficient: 0.363). In terms of lifestyle, the answer related to smoking showed a very high consistency (Kappa coefficient: 0.918), while those addressing salt consumption, alcohol consumption, and exercise showed moderate to substantial consistency (Kappa coefficient: 0.405–0.640). There was substantial consistency in regular usage of medication (Kappa coefficient: 0.609). The overall satisfaction of AI and manual follow-up was 93.1% and 99.5%, respectively.

Conclusions:

These results indicate that AI telephone follow-up takes less time and is equivalent to manual follow-up to a high degree. Residents have high satisfaction, and AI telephone follow-up is reliable for the follow-up and management of hypertension patients.