A scoping review of artificial intelligence applications in thoracic surgery.

OBJECTIVES: Machine learning (ML) has great potential, but there are few examples of its implementation improving outcomes. The thoracic surgeon must be aware of pertinent ML literature and how to evaluate this field for the safe translation to patient care. This scoping review provides an introduction to ML applications specific to the thoracic surgeon. We review current applications, limitations and future directions. METHODS: A search of the PubMed database was conducted with inclusion requirements being the use of an ML algorithm to analyse patient information relevant to a thoracic surgeon and contain sufficient details on the data used, ML methods and results. Twenty-two papers met the criteria and were reviewed using a methodological quality rubric. RESULTS: ML demonstrated enhanced preoperative test accuracy, earlier pathological diagnosis, therapies to maximize survival and predictions of adverse events and survival after surgery. However, only 4 performed external validation. One demonstrated improved patient outcomes, nearly all failed to perform model calibration and one addressed fairness and bias with most not generalizable to different populations. There was a considerable variation to allow for reproducibility. CONCLUSIONS: There is promise but also challenges for ML in thoracic surgery. The transparency of data and algorithm design and the systemic bias on which models are dependent remain issues to be addressed. Although there has yet to be widespread use in thoracic surgery, it is essential thoracic surgeons be at the forefront of the eventual safe introduction of ML to the clinic and operating room.

Outcomes of vitrectomy for diabetic tractional retinal detachment in Chicago's county health system.

PURPOSE: To examine outcomes of 23-gauge (23G) pars plana vitrectomy (PPV) for complex diabetic tractional retinal detachment (TRD) in Chicago's Cook County Health and Hospitals System (CCHHS). MATERIALS AND METHODS: This is a retrospective noncomparative study of diabetic TRD cases that underwent PPV at CCHHS. Primary retinal reattachment rate, visual function, and postoperative complications were analyzed. RESULTS: Sixty nine consecutive cases were included. Primary reattachment and final attachment were achieved in 68/69 eyes (98.6%). Secondary retinal detachment was noted in 1 eye (1.4%). Vitreous hemorrhage requiring repeat PPV developed in 5 eyes (7.2%) and reoperation due to other complications was required in 4/69 eyes (5.8%). Perfluoropropane (C3F8) gas tamponade was used in 91.3% of eyes and silicone oil in 8.7% of eyes. Mean LogMAR visual acuity significantly improved from 1.84 ± 0.61 to 0.93 ± 0.66, (P<0.0001). Vision was stabilized or improved in 66 eyes (95.7%). Visual acuity of 20/200 or better was achieved in 49/69 eyes (71.0%) and 20/50 or better in 16/69 eyes (23.2%). CONCLUSIONS: Even in patients with severe and advanced diabetic TRD pathology and unique demographics as seen in CCHHS, modern vitrectomy techniques can provide excellent anatomical and visual outcomes.

Macular Hole Formation After Pars Plana Vitrectomy for Diabetic Tractional Retinal Detachment.

BACKGROUND AND OBJECTIVE: To investigate the incidence, clinical features, and outcomes of patients with macular hole (MH) formation after pars plana vitrectomy (PPV) for diabetic tractional retinal detachment (TRD). PATIENTS AND METHODS: We conducted a retrospective review of all cases of PPV for diabetic TRD performed by a surgeon (DS) at a large county hospital between November 2013 and August 2016. RESULTS: Ninety consecutive eyes of 79 patients were included in this case series, of which four eyes developed MH, yielding an incidence of 4.4% (95% confidence interval [CI], 1.2%-11.0%). The mean interval between PPV for TRD and MH formation was 7.0 ± 5.5 (mean ± 1 standard deviation) months, and mean follow-up time was 29.6 months ± 6.9 months. Three of the four eyes that developed MH underwent intervention, and of the three that underwent intervention, all had successful hole closure. CONCLUSION: In this case series, the incidence of MH after PPV for TRD is 4.4% (95% CI, 1.2%-11.0%). The mechanism of MH formation after diabetic TRD repair is not certain but may be related to a taut internal limiting membrane, epiretinal membrane formation, macular edema, or residual vitreous contraction. [Ophthalmic Surg Lasers Imaging Retina. 2018;49:e256-e262.].