Abstract Background The mAFA-II cluster randomised trial demonstrated the efficacy of a mobile health-technology implemented ‘Atrial fibrillation Better Care’ (ABC) pathway (mAFA intervention) for integrated care management of patients with AF. Objective To evaluate the effect of mAFA intervention across phenotypes of patients with AF. Design We conducted a latent-class analysis (LCA) according to eight variables, including age and comorbidities. Participants The mAFA-II trial enrolled AF patients between June 2018 and August 2019 across 40 centres in China. Main Measures We evaluated the interaction between the groups identified through LCA, and the effect of mAFA intervention on the risk of the primary composite outcome of all-cause death, stroke/thromboembolism, and rehospitalisations. Results were expressed as adjusted hazard ratio (aHR) and 95% confidence intervals (95% CI). Key Results Across the 3324 patients included in the trial (mean age 68.5 ± 13.9 years, 38.0% females), we identified three phenotypes: (i) low morbidity phenotype (n = 1234, 37.1%), (ii) hypertensive/coronary artery disease (CAD) phenotype (n = 1534, 46.2%), and (iii) mixed morbidity phenotype (n = 556, 16.7%). The effect of mAFA intervention on the primary outcome appeared greater in the low morbidity phenotype (aHR, 0.08; 95% CI 0.02–0.33) compared to the hypertensive/CAD (aHR, 0.30; 95% CI 0.16–0.58) and the mixed morbidity phenotype (aHR, 0.68; 95% CI 0.37–1.24), with a statistically significant interaction (pint = 0.004). Conclusions In patients with AF, the ABC pathway improved prognosis across different comorbidity phenotypes, although with some differences in the magnitude of risk reduction. Patients with more complex phenotypes require further efforts to improve their outcomes, considering their high baseline risk of adverse events. Trial Registration WHO International Clinical Trials Registry Platform (ICTRP) Registration number: ChiCTR-OOC-17014138.