RESUMO
Artificial intelligence (AI) models have shown great accuracy in health screening. However, for real-world implementation, high accuracy may not guarantee cost-effectiveness. Improving AI's sensitivity finds more high-risk patients but may raise medical costs while increasing specificity reduces unnecessary referrals but may weaken detection capability. To evaluate the trade-off between AI model performance and the long-running cost-effectiveness, we conducted a cost-effectiveness analysis in a nationwide diabetic retinopathy (DR) screening program in China, comprising 251,535 participants with diabetes over 30 years. We tested a validated AI model in 1100 different diagnostic performances (presented as sensitivity/specificity pairs) and modeled annual screening scenarios. The status quo was defined as the scenario with the most accurate AI performance. The incremental cost-effectiveness ratio (ICER) was calculated for other scenarios against the status quo as cost-effectiveness metrics. Compared to the status quo (sensitivity/specificity: 93.3%/87.7%), six scenarios were cost-saving and seven were cost-effective. To achieve cost-saving or cost-effective, the AI model should reach a minimum sensitivity of 88.2% and specificity of 80.4%. The most cost-effective AI model exhibited higher sensitivity (96.3%) and lower specificity (80.4%) than the status quo. In settings with higher DR prevalence and willingness-to-pay levels, the AI needed higher sensitivity for optimal cost-effectiveness. Urban regions and younger patient groups also required higher sensitivity in AI-based screening. In real-world DR screening, the most accurate AI model may not be the most cost-effective. Cost-effectiveness should be independently evaluated, which is most likely to be affected by the AI's sensitivity.
RESUMO
OBJECTIVES: To explore the characteristics of the low-income elderly who underwent free cataract surgery and to determine the degree of patient satisfaction with the free cataract surgery programme in urban China. METHODS: A free cataract surgery management workflow was designed as a poverty relief project in Guangzhou. In this study, participants who underwent free cataract surgery between January and August 2014 received a telephone interview based on a structured questionnaire. Data were collected on patient demographics, resources, health conditions, reasons for undergoing the free surgery and overall evaluation of the free cataract surgery programme. RESULTS: Among the 833 participants, the mean surgical age was 76.85±7.46â years (95% CI 76.34 to 77.36), and the male to female ratio was 385:448. The majority (94.31%, 746/791) of patients resided in the main urban districts. Patients underwent surgery 61.08±60.15â months (95% CI 56.17 to 66.00) after becoming aware of the cataract, although 66.83% of them reported that their daily lives were influenced by cataracts. Only 21.5% of the respondents underwent physical examinations that included regular eye screening, and only 6.30% were highly educated patients. Financial problems were the primary reason cited by patients for participating in the free surgery programme. Those patients with a monthly family income of 1000-2999¥ (US$161-482) per capita constituted the largest patient population. The free clinics in the parks and the free cataract surgery were highly rated (9.46 and 9.11 of 10 points) by the beneficiaries. CONCLUSIONS: The telephone survey revealed a high level of patient satisfaction regarding the free cataract surgery programme. Most of the patients who participated in the programme resided in major urban districts and had poor health awareness and a low level of education. The information provided by this study is crucial for improving and expanding the management of free cataract surgery programmes. TRIAL REGISTRATION NUMBER: NCT02633865; Post-results.