Artificial Intelligence-Augmented Propensity Score, Cost Effectiveness and Computational Ethical Analysis of Cardiac Arrest and Active Cancer with Novel Mortality Predictive Score.

Background and objectives: Little is known about outcome improvements and disparities in cardiac arrest and active cancer. We performed the first known AI and propensity score (PS)-augmented clinical, cost-effectiveness, and computational ethical analysis of cardio-oncology cardiac arrests including left heart catheterization (LHC)-related mortality reduction and related disparities. Materials and methods: A nationally representative cohort analysis was performed for mortality and cost by active cancer using the largest United States all-payer inpatient dataset, the National Inpatient Sample, from 2016 to 2018, using deep learning and machine learning augmented propensity score-adjusted (ML-PS) multivariable regression which informed cost-effectiveness and ethical analyses. The Cardiac Arrest Cardio-Oncology Score (CACOS) was then created for the above population and validated. The results informed the computational ethical analysis to determine ethical and related policy recommendations. Results: Of the 101,521,656 hospitalizations, 6,656,883 (6.56%) suffered cardiac arrest of whom 61,300 (0.92%) had active cancer. Patients with versus without active cancer were significantly less likely to receive an inpatient LHC (7.42% versus 20.79%, p < 0.001). In ML-PS regression in active cancer, post-arrest LHC significantly reduced mortality (OR 0.18, 95%CI 0.14−0.24, p < 0.001) which PS matching confirmed by up to 42.87% (95%CI 35.56−50.18, p < 0.001). The CACOS model included the predictors of no inpatient LHC, PEA initial rhythm, metastatic malignancy, and high-risk malignancy (leukemia, pancreas, liver, biliary, and lung). Cost-benefit analysis indicated 292 racial minorities and $2.16 billion could be saved annually by reducing racial disparities in LHC. Ethical analysis indicated the convergent consensus across diverse belief systems that such disparities should be eliminated to optimize just and equitable outcomes. Conclusions: This AI-guided empirical and ethical analysis provides a novel demonstration of LHC mortality reductions in cardio-oncology cardiac arrest and related disparities, along with an innovative predictive model that can be integrated within the digital ecosystem of modern healthcare systems to improve equitable clinical and public health outcomes.

Microinvasive tumor endoresection in combination with ocular stereotactic radiosurgery.

OBJECTIVE The use of Gamma Knife radiosurgery (GKRS) as monotherapy in the treatment of uveal melanoma (UM) allows clinicians to achieve high local tumor control with low recurrence but does not prevent secondary enucleation due to glaucoma in cases of large tumors. The authors analyzed indications for tumor endoresection (ER), the time interval between irradiation and surgery, and the features and results of performing ER for UM after GKRS. METHODS Thirty-seven patients between 28 and 78 years of age (16 male and 11 female patients) with UM underwent GKRS with a dose of 70 to 80 Gy that was applied to the center of the tumor with complete immobilization of the eye during the procedure. Tumor resection with histological investigation was performed in 24 eyes (transscleral resection was performed in 3 eyes, and ER was performed in 21 eyes) at 3 to 97 days after GKRS, mainly during the first 2 or 3 weeks. As a rule, ER (21 eyes) was performed to treat large, centrally localized, or equatorial UMs with exudative macula-on retinal detachment that reduced vision. The average tumor height was 8.9 mm, and the average width was 13.7 mm at the base. ER for UM included phacoemulsification, microinvasive vitrectomy with transretinal tumor resection, laser photocoagulation, and application of a temporary silicone oil tamponade. Seven patients received intraocular injections of inhibitors of angiogenesis for the prevention and treatment of radiation neuroretinopathy. The follow-up period ranged from 8 to 41 months. RESULTS Preservation of the eyes without tumor recurrence was achieved in all 37 patients after GKRS (monotherapy and combined therapy). One patient died of liver metastases at 21 months after GKRS. In the ER group (21 eyes), drug-resistant glaucoma with low visual acuity appeared in 4 eyes (19%) with long-existing total exudative retinal detachment and delayed operations. Severe radiation neuroretinopathy with macular edema occurred in 4 of 21 cases (19%). Intraocular injections of inhibitors of angiogenesis significantly decreased retinal edema. Residual rhegmatogenous retinal detachment was revealed in 1 eye (4.8%). The conservation of the patient's primary vision or its improvement were observed in 11 eyes (52.4%). Useful vision more than 0.1 was achieved in 12 cases (57%), and more than 0.3 was achieved in 8 cases (38%). CONCLUSIONS As a result of this research, ER for UM after GKRS proved to be an effective method of combined eye-conserving treatment for large centrally localized or equatorial tumors at high risk of the emergence and development of toxic tumor syndrome. Perfect eye immobilization, timely ER, and multiple intraocular injections of inhibitors of angiogenesis saved not only the eye in all cases, but also useful vision in many cases. Close cooperation among radiosurgeons, ophthalmologists, and vitreoretinal surgeons is the key to effective treatment.