Artificial neural network based prediction of the lung tissue involvement as an independent in-hospital mortality and mechanical ventilation risk factor in COVID-19.

INTRODUCTION: During COVID-19 pandemic, artificial neural network (ANN) systems have been providing aid for clinical decisions. However, to achieve optimal results, these models should link multiple clinical data points to simple models. This study aimed to model the in-hospital mortality and mechanical ventilation risk using a two step approach combining clinical variables and ANN-analyzed lung inflammation data. METHODS: A data set of 4317 COVID-19 hospitalized patients, including 266 patients requiring mechanical ventilation, was analyzed. Demographic and clinical data (including the length of hospital stay and mortality) and chest computed tomography (CT) data were collected. Lung involvement was analyzed using a trained ANN. The combined data were then analyzed using unadjusted and multivariate Cox proportional hazards models. RESULTS: Overall in-hospital mortality associated with ANN-assigned percentage of the lung involvement (hazard ratio [HR]: 5.72, 95% confidence interval [CI]: 4.4-7.43, p < 0.001 for the patients with >50% of lung tissue affected by COVID-19 pneumonia), age category (HR: 5.34, 95% CI: 3.32-8.59 for cases >80 years, p < 0.001), procalcitonin (HR: 2.1, 95% CI: 1.59-2.76, p < 0.001, C-reactive protein level (CRP) (HR: 2.11, 95% CI: 1.25-3.56, p = 0.004), glomerular filtration rate (eGFR) (HR: 1.82, 95% CI: 1.37-2.42, p < 0.001) and troponin (HR: 2.14, 95% CI: 1.69-2.72, p < 0.001). Furthermore, the risk of mechanical ventilation is also associated with ANN-based percentage of lung inflammation (HR: 13.2, 95% CI: 8.65-20.4, p < 0.001 for patients with >50% involvement), age, procalcitonin (HR: 1.91, 95% CI: 1.14-3.2, p = 0.14, eGFR (HR: 1.82, 95% CI: 1.2-2.74, p = 0.004) and clinical variables, including diabetes (HR: 2.5, 95% CI: 1.91-3.27, p < 0.001), cardiovascular and cerebrovascular disease (HR: 3.16, 95% CI: 2.38-4.2, p < 0.001) and chronic pulmonary disease (HR: 2.31, 95% CI: 1.44-3.7, p < 0.001). CONCLUSIONS: ANN-based lung tissue involvement is the strongest predictor of unfavorable outcomes in COVID-19 and represents a valuable support tool for clinical decisions.

The Impact of Progesterone and Estrogen on the Tooth Mobility.

Background and Objectives: Progesterone and estrogen modify the bone metabolism directly related to the periodontium, this study aimed at answering the question whether fluctuations in the levels of these hormones or the use of their synthetic equivalents in modern contraceptives have a significant impact on the natural tooth mobility (TM) in its alveolus. Materials and Methods: Sixty healthy women who had never been pregnant and when interviewed reported either (1) having regular menstruations every 28-30 days or (2) taking oral two-phase two-ingredient hormonal contraceptives formed, respectively, groups M and S in the study. TM evaluated as the Periotest value (PTV) was checked in the menstruation, ovulation, and luteal phases of the menstrual cycle (group M) and on the days corresponding to the moment of the menstrual cycle in group S. Results: Although the PTV-s were within the limits of norm, the canines and the molars were always more stable than the other teeth. In group M, the TM was statistically comparable (p > 0.05) in the menstrual and ovulation phases, thus significantly increased (p < 0.001) in the luteal phase. The TM remained constant (p = 0.758) in all studies in group S. The results demonstrated that the canines and the molars in the luteal phase were significantly more mobile in group M than in group S (p < 0.001), although increased mobility of the teeth in group M affected the canines and the first molars to a significantly lesser degree than the other teeth. Conclusions: However, since women between 20 and 30 years old constitute the majority of ortho-dontic patients, possible determination of the optimum moment of force application in relation to the sex hormones cycle, namely, to its luteal phase, is clinically very promising.

Remplissage May Decrease the Redislocation Rate After Arthroscopic Bankart Repair in Patients With an Engaging Hill-Sachs Defect: A Systematic Review and Meta-analysis of Studies With Minimal 2-Year Follow-up.

BACKGROUND: The redislocation rate after arthroscopic Bankart repair (BR) among patients with a Hill-Sachs lesion (HSL) may be reduced with the use of remplissage. PURPOSE: To investigate the outcomes of adding remplissage to an arthroscopic BR in patients with concomitant HSL. STUDY DESIGN: Meta-analysis; Level of evidence, 3. METHODS: PubMed and ScienceDirect databases were searched between February 2022 and April 2023 with the terms "remplissage" and "shoulder instability" according to PRISMA (Preferred Reporting Items for Systematic Reviews and Meta-Analyses) guidelines. The inclusion criteria were formed using the population, intervention, control, and outcome method; the investigation included studies that compared BR with and without remplissage and had ≥24 months of follow-up. RESULTS: From 802 articles found during the initial search, 7 studies with a total of 837 patients-558 receiving isolated BR (BR group) and 279 receiving BR with remplissage (BR+REMP)-were included. The probability of recurrence of instability among patients with an engaging HSL was significantly diminished in the BR+REMP group compared with the BR group (odds ratio, 0.11; 95% CI, 0.05 to 0.24; P < .001). Regarding shoulder range of motion, the BR+REMP group achieved increased forward flexion (mean difference [MD], 1.97°; 95% CI, 1.49° to 2.46°; P < .001) and decreased external rotation in adduction (MD, -1.43°; 95% CI, -2.40° to -0.46°; P = .004) compared with the BR group. Regarding patient-reported outcome measures, the BR+REMP group had Rowe (MD, 2.53; 95% CI, -1.48 to 6.54; P = .21) and Western Ontario Shoulder Instability Index (WOSI) (MD, -61.60; 95% CI, -148.03 to 24.82; P = .162) scores that were comparable with those of the BR group. CONCLUSION: Remplissage resulted in a 9-fold decrease in the recurrence of instability after arthroscopic BR in patients with HSL. Remplissage not only led to an increase in forward flexion but also only slightly limited patients' external rotation in adduction. WOSI and Rowe scores after remplissage at the final 24-month follow-up were comparable with those obtained after isolated Bankart repair.