Prediction of post-delivery hemoglobin levels with machine learning algorithms.

Predicting postpartum hemorrhage (PPH) before delivery is crucial for enhancing patient outcomes, enabling timely transfer and implementation of prophylactic therapies. We attempted to utilize machine learning (ML) using basic pre-labor clinical data and laboratory measurements to predict postpartum Hemoglobin (Hb) in non-complicated singleton pregnancies. The local databases of two academic care centers on patient delivery were incorporated into the current study. Patients with preexisting coagulopathy, traumatic cases, and allogenic blood transfusion were excluded from all analyses. The association of pre-delivery variables with 24-h post-delivery hemoglobin level was evaluated using feature selection with Elastic Net regression and Random Forest algorithms. A suite of ML algorithms was employed to predict post-delivery Hb levels. Out of 2051 pregnant women, 1974 were included in the final analysis. After data pre-processing and redundant variable removal, the top predictors selected via feature selection for predicting post-delivery Hb were parity (B: 0.09 [0.05-0.12]), gestational age, pre-delivery hemoglobin (B:0.83 [0.80-0.85]) and fibrinogen levels (B:0.01 [0.01-0.01]), and pre-labor platelet count (B*1000: 0.77 [0.30-1.23]). Among the trained algorithms, artificial neural network provided the most accurate model (Root mean squared error: 0.62), which was subsequently deployed as a web-based calculator: https://predictivecalculators.shinyapps.io/ANN-HB . The current study shows that ML models could be utilized as accurate predictors of indirect measures of PPH and can be readily incorporated into healthcare systems. Further studies with heterogenous population-based samples may further improve the generalizability of these models.

Impact of Depression on Postoperative Medical and Surgical Outcomes in Spine Surgeries: A Systematic Review and Meta-Analysis.

Introduction: The relationship between psychiatric disorders, including depression, and invasive interventions has been a topic of debate in recent literature. While these conditions can impact the quality of life and subjective perceptions of surgical outcomes, the literature lacks consensus regarding the association between depression and objective perioperative medical and surgical complications, especially in the neurosurgical domain. Methods: MEDLINE (PubMed), EMBASE, PsycINFO, and the Cochrane Library were queried in a comprehensive manner from inception until 10 November 2023, with no language restrictions, for citations investigating the association between depression and length of hospitalization, medical and surgical complications, and objective postoperative outcomes including readmission, reoperation, and non-routine discharge in patients undergoing spine surgery. Results: A total of 26 articles were considered in this systematic review. Upon pooled analysis of the primary outcome, statistically significantly higher rates were observed for several complications, including delirium (OR:1.92), deep vein thrombosis (OR:3.72), fever (OR:6.34), hematoma formation (OR:4.7), hypotension (OR:4.32), pulmonary embolism (OR:3.79), neurological injury (OR:6.02), surgical site infection (OR:1.36), urinary retention (OR:4.63), and urinary tract infection (OR:1.72). While readmission (OR:1.35) and reoperation (OR:2.22) rates, as well as non-routine discharge (OR:1.72) rates, were significantly higher in depressed patients, hospitalization length was comparable to non-depressed controls. Conclusions: The results of this review emphasize the significant increase in complications and suboptimal outcomes noted in patients with depression undergoing spinal surgery. Although a direct causal relationship may not be established, addressing psychiatric aspects in patient care is crucial for providing comprehensive medical attention.

Efficacy and utility of antifibrinolytics in pediatric spine surgery: a systematic review and network meta-analysis.

Antifibrinolytics have gained increasing attention in minimizing blood loss and mitigating the risks associated with massive transfusions, including infection and coagulopathy in pediatric patients undergoing spine surgery. Nevertheless, the selection of optimal agent is still a matter of debate. We aim to review the utility of these agents and compare the efficacy of antifibrinolytics in pediatric and adolescent spine surgeries. A comprehensive search was performed in Scopus, Web of Science, and MEDLINE databases for relevant works. Studies providing quantitative data on predefined outcomes were included. Primary outcome was perioperative bleeding between the groups. Secondary outcomes included transfusion volume, rate of complications, and operation time. Twenty-eight studies were included in the meta-analysis incorporating 2553 patients. The use of Tranexamic acid (RoM: 0.71, 95%CI: [0.62-0.81], p < 0.001, I2 = 88%), Aprotinin (RoM: 0.54, 95%CI: [0.46-0.64], p < 0.001, I2 = 0%), and Epsilon-aminocaproic acid (RoM: 0.71, 95%CI: [0.62-0.81], p < 0.001, I2 = 60%) led to a 29%, 46%, and 29% reduction in perioperative blood loss, respectively. Network meta-analysis revealed higher probability of efficacy with Tranexamic acid compared to Epsilon-aminocaproic acid (P score: 0.924 vs. 0.571). The rate of complications was not statistically different between each two antifibrinolytic agent or antifibrinolytics compared to placebo or standard of care. Our network meta-analysis suggests a superior efficacy of all antifibrinolytics compared to standard of care/placebo in reducing blood loss and transfusion rate. Further adequately-powered randomized clinical trials are recommended to reach definite conclusion on comparative performance of these agents and to also provide robust objective assessments and standardized outcome data and safety profile on antifibrinolytics in pediatric and adolescent pediatric surgeries.

The effect of COVID-19 on Multiple Sclerosis relapse: A systematic review and meta-analysis.

BACKGROUND: Multiple Sclerosis (MS) is a chronic autoimmune disease, affecting over 2.5 million people worldwide. There has been growing concern about the impact of COVID-19 on the clinical course of MS. However, these findings remain controversial, and there is a lack of high-quality evidence to establish the relationship between COVID-19 and MS. METHODS: A comprehensive search was done to identify relevant studies reporting relapse rate in patients with MS (pwMS), those comparing the relapse rate of COVID-19 pwMS and MS controls, and studies investigating the effect of COVID-19 on relapse rate of pwMS. The results were presented as proportion of COVID-19 pwMS experiencing relapse and odds ratio determining the impact of COVID-19 on relapse rate. RESULTS: Fourteen studies were included in the analyses. The proportion of COVID-19 positive pwMS with relapse was 7.71 per 100 cases (95 % confidence interval, CI: 4.41-13.89, I2=96 %). Quantitative evaluation of studies with pwMS without COVID-19 did not demonstrate a statistically significant difference in relapse rate of patients with COVID-19 (OR: 0.75, 95 %CI: 0.44-1.29, I2= 54 %). Subgroup and sensitivity analyses did not alter the lack of significance of association between COVID-19 and MS relapse. Sensitivity analysis excluding the outlying study was largely in favor of no difference between the groups (OR:1.00, 95 %CI: 0.72-1.38, I2=34 %) CONCLUSION: The results of this review does not suggest that COVID-19 influences the relapse rate in pwMS. While the findings alleviate the concerns regarding the co-occurrence of the diseases, further studies are needed to investigate the effects of confounding factors.