Cost-effectiveness of Artificial Intelligence-Based Retinopathy of Prematurity Screening.

Importance: Artificial intelligence (AI)-based retinopathy of prematurity (ROP) screening may improve ROP care, but its cost-effectiveness is unknown. Objective: To evaluate the relative cost-effectiveness of autonomous and assistive AI-based ROP screening compared with telemedicine and ophthalmoscopic screening over a range of estimated probabilities, costs, and outcomes. Design, Setting, and Participants: A cost-effectiveness analysis of AI ROP screening compared with ophthalmoscopy and telemedicine via economic modeling was conducted. Decision trees created and analyzed modeled outcomes and costs of 4 possible ROP screening strategies: ophthalmoscopy, telemedicine, assistive AI with telemedicine review, and autonomous AI with only positive screen results reviewed. A theoretical cohort of infants requiring ROP screening in the United States each year was analyzed. Main Outcomes and Measures: Screening and treatment costs were based on Current Procedural Terminology codes and included estimated opportunity costs for physicians. Outcomes were based on the Early Treatment of ROP study, defined as timely treatment, late treatment, or correctly untreated. Incremental cost-effectiveness ratios were calculated at a willingness-to-pay threshold of $100 000. One-way and probabilistic sensitivity analyses were performed comparing AI strategies to telemedicine and ophthalmoscopy to evaluate the cost-effectiveness across a range of assumptions. In a secondary analysis, the modeling was repeated and assumed a higher sensitivity for detection of severe ROP using AI compared with ophthalmoscopy. Results: This theoretical cohort included 52 000 infants born 30 weeks' gestation or earlier or weighed 1500 g or less at birth. Autonomous AI was as effective and less costly than any other screening strategy. AI-based ROP screening was cost-effective up to $7 for assistive and $34 for autonomous screening compared with telemedicine and $64 and $91 compared with ophthalmoscopy in the primary analysis. In the probabilistic sensitivity analysis, autonomous AI screening was more than 60% likely to be cost-effective at all willingness-to-pay levels vs other modalities. In a second simulated cohort with 99% sensitivity for AI, the number of late treatments for ROP decreased from 265 when ROP screening was performed with ophthalmoscopy to 40 using autonomous AI. Conclusions and Relevance: AI-based screening for ROP may be more cost-effective than telemedicine and ophthalmoscopy, depending on the added cost of AI and the relative performance of AI vs human examiners detecting severe ROP. As AI-based screening for ROP is commercialized, care must be given to appropriately price the technology to ensure its benefits are fully realized.

Is the presence of tumor-infiltrating lymphocytes predictive of outcomes in patients with melanoma?

BACKGROUND: The significance of tumor-infiltrating lymphocytes (TILs) in melanoma is debated. This article presents a multicenter, retrospective study assessing the predictive and prognostic value of TILs. METHODS: The Sentinel Lymph Node Working Group database was queried from 1993 to 2018 for cases with known TIL data. TILs were categorized as absent or present, which included nonbrisk (NB), brisk (B), and present but unspecified TIL levels. Clinicopathologic factors were correlated with TILs, sentinel lymph node (SLN) status, and melanoma-specific survival (MSS). RESULTS: Overall, 3203 patients were included. The median thickness was 1.5 mm, and 469 cases had SLN metastases. TILs were present in 2458 cases (76.7%), with NB, B, and unspecified TILs seen in 1691 (68.8%), 691 (28.1%), and 76 (3.1%), respectively. Multivariable analysis showed that the presence of TILs significantly predicted a negative SLN biopsy (P < .05). The median follow-up was 25.2 months. MSS was significantly better for cases with TILs than cases without TILs (P < .001). According to multivariable analysis, age, gender, thickness, mitotic rate, ulceration, lymphovascular invasion, and SLN status were significantly prognostic of MSS (all P values < .05). Although TILs were not prognostic of MSS, when multiple imputation was used and the SLN status was excluded, the presence of TILs was significantly prognostic of improved MSS (hazard ratio, 0.78; 95% confidence interval, 0.64-0.95; P = .0154). CONCLUSIONS: TILs are a favorable marker because their presence significantly predicts a negative SLN, and the absence of TILs may be a prognostic marker of worse survival in patients with a positive SLN but not a negative SLN. TILs may also serve as a prognostic marker of survival when the SLN status is not considered.