De-biased Disentanglement Learning for Pulmonary Embolism Survival Prediction on Multimodal Data.

Health disparities among marginalized populations with lower socioeconomic status significantly impact the fairness and effectiveness of healthcare delivery. The increasing integration of artificial intelligence (AI) into healthcare presents an opportunity to address these inequalities, provided that AI models are free from bias. This paper aims to address the bias challenges by population disparities within healthcare systems, existing in the presentation of and development of algorithms, leading to inequitable medical implementation for conditions such as pulmonary embolism (PE) prognosis. In this study, we explore the diversity of biases in healthcare systems, which highlights the need for a holistic framework to reduce bias by complementary aggregation. By leveraging de-biasing deep survival prediction models, we propose a framework that disentangles identifiable information from images, text reports, and clinical variables to mitigate potential biases within multimodal datasets. Our study offers several advantages over traditional clinical-based survival prediction methods, including richer survival-related characteristics and bias-complementary predicted results. By improving the robustness of survival analysis through this framework, we aim to benefit patients, clinicians, and researchers by improving fairness and accuracy in healthcare AI systems. The code is available at https://github.com/zzs95/fairPE-SA.

Conversion Rate of Abstracts Presented at Plastic Surgery The Meeting From 2010 to 2019: A 10-Year Analysis of Factors for Success.

BACKGROUND: Presentations are an important means of knowledge generation. Publication of these studies is important for dissemination of findings beyond meeting attendees. We analyzed a 10-year sample of presented abstracts at Plastic Surgery The Meeting and describe factors that improve rate and speed of conversion to peer-reviewed publication. METHODS: Abstracts presented between 2010 and 2019 at Plastic Surgery The Meeting were sourced from the American Society of Plastic Surgery Abstract Archive. A random sample of 100 abstracts from each year was evaluated. Abstract information and demographics were recorded. The title or author and keywords of each abstract were searched using a standardized workflow to find a corresponding published paper on PubMed, Google Scholar, and Google. Data were analyzed for trends and factors affecting conversion rate. RESULTS: A total of 983 presented abstracts were included. The conversion rate was 54.1%. Residents and fellows constituted the largest proportion of presenters (38.4%). There was a significant increase in medical student and research fellow presenters during the study period (P < 0.001). Conversion rate was not affected by the research rank of a presenter's affiliated institution (ß = 1.001, P = 0.89), geographic location (P = 0.60), or subspecialty tract (P = 0.73). US academics had a higher conversion rate (61.8%) than US nonacademics (32.7%) or international presenters (47.1%) (P < 0.001). Medical students had the highest conversion rate (65.6%); attendings had the lowest (45.0%). Research fellows had the lowest average time to publication (11.6 months, P = 0.007). CONCLUSIONS: Lower levels of training, factors associated with increased institution-level support, and research quality affect rate and time to publication. These findings highlight the success of current models featuring medical student and research fellow-led projects with strong resident and faculty mentorship.

Predicting Acute Brain Injury in Venoarterial Extracorporeal Membrane Oxygenation Patients with Tree-Based Machine Learning: Analysis of the Extracorporeal Life Support Organization Registry.

Objective: To determine if machine learning (ML) can predict acute brain injury (ABI) and identify modifiable risk factors for ABI in venoarterial extracorporeal membrane oxygenation (VA-ECMO) patients. Design: Retrospective cohort study of the Extracorporeal Life Support Organization (ELSO) Registry (2009-2021). Setting: International, multicenter registry study of 676 ECMO centers. Patients: Adults (≥18 years) supported with VA-ECMO or extracorporeal cardiopulmonary resuscitation (ECPR). Interventions: None. Measurements and Main Results: Our primary outcome was ABI: central nervous system (CNS) ischemia, intracranial hemorrhage (ICH), brain death, and seizures. We utilized Random Forest, CatBoost, LightGBM and XGBoost ML algorithms (10-fold leave-one-out cross-validation) to predict and identify features most important for ABI. We extracted 65 total features: demographics, pre-ECMO/on-ECMO laboratory values, and pre-ECMO/on-ECMO settings.Of 35,855 VA-ECMO (non-ECPR) patients (median age=57.8 years, 66% male), 7.7% (n=2,769) experienced ABI. In VA-ECMO (non-ECPR), the area under the receiver-operator characteristics curves (AUC-ROC) to predict ABI, CNS ischemia, and ICH was 0.67, 0.67, and 0.62, respectively. The true positive, true negative, false positive, false negative, positive, and negative predictive values were 33%, 88%, 12%, 67%, 18%, and 94%, respectively for ABI. Longer ECMO duration, higher 24h ECMO pump flow, and higher on-ECMO PaO2 were associated with ABI.Of 10,775 ECPR patients (median age=57.1 years, 68% male), 16.5% (n=1,787) experienced ABI. The AUC-ROC for ABI, CNS ischemia, and ICH was 0.72, 0.73, and 0.69, respectively. The true positive, true negative, false positive, false negative, positive, and negative predictive values were 61%, 70%, 30%, 39%, 29% and 90%, respectively, for ABI. Longer ECMO duration, younger age, and higher 24h ECMO pump flow were associated with ABI. Conclusions: This is the largest study predicting neurological complications on sufficiently powered international ECMO cohorts. Longer ECMO duration and higher 24h pump flow were associated with ABI in both non-ECPR and ECPR VA-ECMO.

Utilizing Machine Learning to Predict Neurological Injury in Venovenous Extracorporeal Membrane Oxygenation Patients: An Extracorporeal Life Support Organization Registry Analysis.

Background: Venovenous extracorporeal membrane oxygenation (VV-ECMO) is associated with acute brain injury (ABI), including central nervous system (CNS) ischemia (defined as ischemic stroke or hypoxic-ischemic brain injury) and intracranial hemorrhage (ICH). There is limited data on prediction models for ABI and neurological outcomes in VV-ECMO. Research Question: Can machine learning (ML) accurately predict ABI and identify modifiable factors of ABI in VV-ECMO? Study Design and Methods: We analyzed adult (≥18 years) VV-ECMO patients in the Extracorporeal Life Support Organization Registry (2009-2021) from 676 centers. ABI was defined as CNS ischemia, ICH, brain death, and seizures. Overall, 65 total variables were extracted including clinical characteristics and pre-ECMO and on-ECMO variables. Random Forest, CatBoost, LightGBM, and XGBoost ML algorithms (10-fold leave-one-out cross-validation) were used to predict ABI. Feature Importance Scores were used to pinpoint variables most important for predicting ABI. Results: Of 37,473 VV-ECMO patients (median age=48.1 years, 63% male), 2,644 (7.1%) experienced ABI: 610 (2%) and 1,591 (4%) experienced CNS ischemia and ICH, respectively. The median ECMO duration was 10 days (interquartile range=5-20 days). The area under the receiver-operating characteristics curves to predict ABI, CNS ischemia, and ICH were 0.67, 0.63, and 0.70, respectively. The accuracy, positive predictive, and negative predictive values for ABI were 79%, 15%, and 95%, respectively. ML identified pre-ECMO cardiac arrest as the most important risk factor for ABI while ECMO duration and bridge to transplantation as an indication for ECMO were associated with lower risk of ABI. Interpretation: This is the first study to use machine learning to predict ABI in a large cohort of VV-ECMO patients. Performance was sub-optimal due to the low reported prevalence of ABI with lack of standardization of neuromonitoring/imaging protocols and data granularity in the ELSO Registry. Standardized neurological monitoring and imaging protocols may improve machine learning performance to predict ABI.

Deglutarylation of glutaryl-CoA dehydrogenase by deacylating enzyme SIRT5 promotes lysine oxidation in mice.

A wide range of protein acyl modifications has been identified on enzymes across various metabolic processes; however, the impact of these modifications remains poorly understood. Protein glutarylation is a recently identified modification that can be nonenzymatically driven by glutaryl-CoA. In mammalian systems, this unique metabolite is only produced in the lysine and tryptophan oxidative pathways. To better understand the biology of protein glutarylation, we studied the relationship between enzymes within the lysine/tryptophan catabolic pathways, protein glutarylation, and regulation by the deglutarylating enzyme sirtuin 5 (SIRT5). Here, we identify glutarylation on the lysine oxidation pathway enzyme glutaryl-CoA dehydrogenase (GCDH) and show increased GCDH glutarylation when glutaryl-CoA production is stimulated by lysine catabolism. Our data reveal that glutarylation of GCDH impacts its function, ultimately decreasing lysine oxidation. We also demonstrate the ability of SIRT5 to deglutarylate GCDH, restoring its enzymatic activity. Finally, metabolomic and bioinformatic analyses indicate an expanded role for SIRT5 in regulating amino acid metabolism. Together, these data support a feedback loop model within the lysine/tryptophan oxidation pathway in which glutaryl-CoA is produced, in turn inhibiting GCDH function via glutaryl modification of GCDH lysine residues and can be relieved by SIRT5 deacylation activity.

An Accessible Laparoscope for Surgery in Low- and Middle- Income Countries.

Laparoscopic surgery is the standard of care in high-income countries for many procedures in the chest and abdomen. It avoids large incisions by using a tiny camera and fine instruments manipulated through keyhole incisions, but it is generally unavailable in low- and middle-income countries (LMICs) due to the high cost of installment, lack of qualified maintenance personnel, unreliable electricity, and shortage of consumable items. Patients in LMICs would benefit from laparoscopic surgery, as advantages include decreased pain, improved recovery time, fewer wound infections, and shorter hospital stays. To address this need, we developed an accessible laparoscopic system, called the ReadyView laparoscope for use in LMICs. The device includes an integrated camera and LED light source that can be displayed on any monitor. The ReadyView laparoscope was evaluated with standard optical imaging targets to determine its performance against a state-of-the-art commercial laparoscope. The ReadyView laparoscope has a comparable resolving power, lens distortion, field of view, depth of field, and color reproduction accuracy to a commercially available endoscope, particularly at shorter, commonly-used working distances (3-5 cm). Additionally, the ReadyView has a cooler temperature profile, decreasing the risk for tissue injury and operating room fires. The ReadyView features a waterproof design, enabling sterilization by submersion, as commonly performed in LMICs. A custom desktop software was developed to view the video on a laptop computer with a frame rate greater than 30 frames per second and to white balance the image, which is critical for clinical use. The ReadyView laparoscope is capable of providing the image quality and overall performance needed for laparoscopic surgery. This portable low-cost system is well suited to increase access to laparoscopic surgery in LMICs.