4 December 2023 in Journal of Medical Internet Research
Background: The advantages of multimodal digitally transformed mobile health management for patients diagnosed with mild to moderate hypertension are not yet established. Objective: We aim to evaluate the therapeutic benefits of a novel WeChat-based multimodal digital transforming management model in mobile health blood pressure (BP) management. Methods: This randomized controlled clinical trial included 175 individuals with new-onset mild to moderate hypertension who were admitted to our center between September and October 2022. The patients were randomly assigned to either the multimodal intervention group (n=88) or the usual care group (n=87). The primary composite outcome was home and office BP differences after 6 months. The major secondary outcomes were 6-month quality-of-life scores, including the self-rating anxiety scale, self-rating depression scale, and Pittsburgh Sleep Quality Index. Results: The mean home BP decreased from 151.74 (SD 8.02)/94.22 (SD 9.32) to 126.19 (SD 8.45)/82.28 (SD 9.26) mm Hg in the multimodal intervention group and from 150.78 (SD 7.87)/91.53 (SD 9.78) to 133.48 (SD 10.86)/84.45 (SD 9.19) mm Hg in the usual care group, with a mean difference in systolic blood pressure and diastolic blood pressure of –8.25 mm Hg (95% CI –11.71 to –4.78 mm Hg; P<.001) and –4.85 mm Hg (95% CI –8.41 to –1.30 mm Hg; P=.008), respectively. The mean office BP decreased from 153.64 (SD 8.39)/93.56 (SD 8.45) to 127.81 (SD 8.04)/ 82.16 (SD 8.06) mm Hg in the multimodal intervention group and from 151.48 (SD 7.14)/(91.31 (SD 9.61) to 134.92 (SD 10.11)/85.09 (SD 8.26) mm Hg in the usual care group, with a mean difference in systolic blood pressure and diastolic blood pressure of –9.27 mm Hg (95% CI –12.62 to –5.91 mm Hg; P<.001) and –5.18 mm Hg (95% CI –8.47 to –1.89 mm Hg; P=.002), respectively. From baseline to 6 months, home BP control <140/90 mm Hg was achieved in 64 (72.7%) patients in the multimodal intervention group and 46 (52.9%) patients in the usual care group (P=.007). Meanwhile, home BP control <130/80 mm Hg was achieved in 32 (36.4%) patients in the multimodal intervention group and 16 (18.4%) patients in the usual care group (P=.008). After 6 months, there were significant differences in the quality-of-life total and graded scores, including self-rating anxiety scale scores (P=.04), self-rating depression scale scores (P=.03), and Pittsburgh Sleep Quality Index scores (P<.001), in the multimodal intervention group compared with the usual care group. Conclusions: The WeChat-based multimodal intervention model improved the BP control rates and lowered the BP levels more than the usual care approach. The multimodal digital transforming management model for hypertension represents an emerging medical practice that utilizes the individual’s various risk factor profiles for primary care and personalized therapy decision-making in patients with hypertension. Trial Registration: Chinese Clinical Trial Registry ChiCTR2200063550; https://www.chictr.org.cn/showproj.html?proj=175816
1 January 2026 in Hypertension
BACKGROUND: The effectiveness of Large Language Model agent frameworks for hypertension screening and personalized health management has not been fully studied. This study aimed to develop and evaluate a Large Language Model–based Agent, called the Cascade Framework, and assess its effectiveness in hypertension education and clinical decision support. METHODS: The Cascade Framework was developed utilizing the Dify platform, and its performance was tested via a robust 2-phase evaluation protocol from August 2024 to June 2025. The first phase involved systematic performance benchmarking of 6 configurations: 3 foundational Large Language Models (Chat Generative Pretrained Transformer [ChatGPT]-4o, ChatGPT-4oMini, and DeepSeek-V3) and their respective Cascade-enhanced versions. The second phase included an external validation in a cohort of patients with suspected hypertension. RESULTS: Cascade integration yielded significant performance improvements across all models. For ChatGPT-4o, educational outcomes improved (Accuracy: 3.87→4.10, P =0.02; Comprehensiveness: 4.07→4.32, P =0.16; Credibility: 3.79→4.03, P <0.001; Understandability: 3.90→3.96, P =0.005; Emotional Support: 3.87→4.01, P <0.001). Blood pressure classification accuracy rose from 62.5% to 87.0% ( P <0.001) and risk factor stratification from 60.4% to 98.6% ( P <0.001). Clinical decision-making improved, with accuracy of 72.0% to 92.5%. A similar trend of performance improvement was observed in the external validation cohort, where the 4o-Cascade model achieved increases in blood pressure classification accuracy (58.9%→95.3%), risk stratification accuracy (71.0%→90.7%), and clinical decision appropriateness (66.4%→92.5%), all with P <0.001 and surpassing the performance of the 3 physicians. CONCLUSIONS: Cascade Framework can improve the management of hypertension. Its extensible architecture allows integration with existing clinical workflows while providing transparent reasoning pathways.
5 September 2023 in JMIR Preprints
BACKGROUND The advantages of multimodal digitally transformed mobile health management for patients diagnosed with mild to moderate hypertension are not yet established. OBJECTIVE We aim to evaluate the therapeutic benefits of a novel WeChat-based multimodal digital transforming management model in mobile health blood pressure (BP) management. METHODS This randomized controlled clinical trial included 175 individuals with new-onset mild to moderate hypertension who were admitted to our center between September and October 2022. The patients were randomly assigned to either the multimodal intervention group (n=88) or the usual care group (n=87). The primary composite outcome was home and office BP differences after 6 months. The major secondary outcomes were 6-month quality-of-life scores, including the self-rating anxiety scale, self-rating depression scale, and Pittsburgh Sleep Quality Index. RESULTS The mean home BP decreased from 151.74 (SD 8.02)/94.22 (SD 9.32) to 126.19 (SD 8.45)/82.28 (SD 9.26) mm Hg in the multimodal intervention group and from 150.78 (SD 7.87)/91.53 (SD 9.78) to 133.48 (SD 10.86)/84.45 (SD 9.19) mm Hg in the usual care group, with a mean difference in systolic blood pressure and diastolic blood pressure of –8.25 mm Hg (95% CI –11.71 to –4.78 mm Hg; P<.001) and –4.85 mm Hg (95% CI –8.41 to –1.30 mm Hg; P=.008), respectively. The mean office BP decreased from 153.64 (SD 8.39)/93.56 (SD 8.45) to 127.81 (SD 8.04)/ 82.16 (SD 8.06) mm Hg in the multimodal intervention group and from 151.48 (SD 7.14)/(91.31 (SD 9.61) to 134.92 (SD 10.11)/85.09 (SD 8.26) mm Hg in the usual care group, with a mean difference in systolic blood pressure and diastolic blood pressure of –9.27 mm Hg (95% CI –12.62 to –5.91 mm Hg; P<.001) and –5.18 mm Hg (95% CI –8.47 to –1.89 mm Hg; P=.002), respectively. From baseline to 6 months, home BP control <140/90 mm Hg was achieved in 64 (72.7%) patients in the multimodal intervention group and 46 (52.9%) patients in the usual care group (P=.007). Meanwhile, home BP control <130/80 mm Hg was achieved in 32 (36.4%) patients in the multimodal intervention group and 16 (18.4%) patients in the usual care group (P=.008). After 6 months, there were significant differences in the quality-of-life total and graded scores, including self-rating anxiety scale scores (P=.04), self-rating depression scale scores (P=.03), and Pittsburgh Sleep Quality Index scores (P<.001), in the multimodal intervention group compared with the usual care group. CONCLUSIONS The WeChat-based multimodal intervention model improved the BP control rates and lowered the BP levels more than the usual care approach. The multimodal digital transforming management model for hypertension represents an emerging medical practice that utilizes the individual’s various risk factor profiles for primary care and personalized therapy decision-making in patients with hypertension. CLINICALTRIAL Chinese Clinical Trial Registry ChiCTR2200063550; https://www.chictr.org.cn/showproj.html?proj=175816