Background: Lactic acidosis is the most common cause of anion gap metabolic acidosis in the intensive care unit (ICU), associated with poor outcomes including mortality. We sought to compare machine learning (ML) approaches versus logistic regression analysis for prediction of mortality in lactic acidosis patients admitted to the ICU. Methods: We used the Medical Information Mart for Intensive Care (MIMIC-III) database to identify ICU adult patients with lactic acidosis (serum lactate ≥4 mmol/L). The outcome of interest was hospital mortality. We developed prediction models using four ML approaches consisting of random forest (RF), decision tree (DT), extreme gradient boosting (XGBoost), artificial neural network (ANN), and statistical modeling with forward stepwise logistic regression using the testing dataset. We then assessed model performance using area under the receiver operating characteristic curve (AUROC), accuracy, precision, error rate, Matthews correlation coefficient (MCC), F1 score, and assessed model calibration using the Brier score, in the independent testing dataset. Results: Of 1919 lactic acidosis ICU patients, 1535 and 384 were included in the training and testing dataset, respectively. Hospital mortality was 30%. RF had the highest AUROC at 0.83, followed by logistic regression 0.81, XGBoost 0.81, ANN 0.79, and DT 0.71. In addition, RF also had the highest accuracy (0.79), MCC (0.45), F1 score (0.56), and lowest error rate (21.4%). The RF model was the most well-calibrated. The Brier score for RF, DT, XGBoost, ANN, and multivariable logistic regression was 0.15, 0.19, 0.18, 0.19, and 0.16, respectively. The RF model outperformed multivariable logistic regression model, SOFA score (AUROC 0.74), SAP II score (AUROC 0.77), and Charlson score (AUROC 0.69). Conclusion: The ML prediction model using RF algorithm provided the highest predictive performance for hospital mortality among ICU patient with lactic acidosis.

Radiation-emitting devices are commonplace in the hospital with their ability to produce imaging for diagnoses, However, they hold a risk for device operators due to radiation exposure. Hospital systems have programs where physicians exposed to radiation are required to wear dosimeters to help record total radiation over time. Dosimetry readings over standardized recommendations can lead to hospital image issues and disciplinary action for physicians. This study aimed to discover the true values recorded on dosimeters with radiation exposure and discuss effective ways to encourage compliance with dosimeter usage. The study was completed over a course of 12 months with physicians from three different hospitals. Selection criteria included physicians considered to be “radiation workers” including those who operate x-ray machines, fluoroscopy units, unsealed and sealed isotopes, or those exposed to other sources of gamma or high-energy beta radiation. Two Plan-Do-Study-Act (PDSA) cycles were implemented. The first cycle was the first six months of the study and the second cycle was the second six months of the study. The first PDSA cycle had planned dosimeter reading check-ins every month. After this cycle ended, physicians were sent a survey anonymously asking if they had ever intentionally left behind their dosimeter. In the second PDSA cycle, a planned policy change was put into action where penalties for physicians who went over the recommended dosage were stopped. A monthly educational meeting where a discussion on the risks of radiation as well as protective mechanisms was implemented instead. The same monthly check-ins for dosimeter reading monitoring were employed again with the same survey regarding dosimeter adherence and usage being sent out at the end of the second cycle. Run charts were created to determine whether the policy change showed statistically significant differences in dosimetry readings. Protocol changes led to statistically significant (p<0.05) differences in radiation exposure recorded throughout the hospital systems. The primary PDSA cycle readings showed that hospital systems one (n=118), two (n=71), and three (n=32) had readings of 3.90 mSv, 2.55 mSv, and 2.02 mSv, respectively, which were all under the annual recommended dose limit of 10 mSv maximum per six months. However, an average of 94.4% (n=221) of physicians across all hospitals admitted to not using the dosimeter. In the second PDSA cycle after the policy change, the radiation doses were higher with an increase in the average cumulative dose at hospital system one of 255%, 328% at system two, and 323% at system three. Hospital systems one and two were both over the yearly limit of 20.0 mSv (7.70 mSv over for system one and 1.86 mSv over for system two) while system three remained under. The number of physicians who stated they always used the dosimeter during the second PDSA cycle increased to 83.9% in-hospital system one, 90.2% in-hospital system two, and 93.8% in-hospital system three. Creating a culture of safety is critical for physician compliance. A comfortable work environment without unreasonable consequences creates an environment where physicians can focus on their health and safety while also doing what is in the workplace’s best interest. This culture can best be made with more collaboration between administrative staff and workers to create a trustworthy experience in hospital systems.

Background: There have been concerns regarding increased perioperative mortality, length of hospital stay, and rates of graft loss in kidney transplant recipients with functional limitations. The application of machine learning consensus clustering approach may provide a novel understanding of unique phenotypes of functionally limited kidney transplant recipients with distinct outcomes in order to identify strategies to improve outcomes. Methods: Consensus cluster analysis was performed based on recipient-, donor-, and transplant-related characteristics in 3205 functionally limited kidney transplant recipients (Karnofsky Performance Scale (KPS) < 40% at transplant) in the OPTN/UNOS database from 2010 to 2019. Each cluster’s key characteristics were identified using the standardized mean difference. Posttransplant outcomes, including death-censored graft failure, patient death, and acute allograft rejection were compared among the clusters Results: Consensus cluster analysis identified two distinct clusters that best represented the clinical characteristics of kidney transplant recipients with limited functional status prior to transplant. Cluster 1 patients were older in age and were more likely to receive deceased donor kidney transplant with a higher number of HLA mismatches. In contrast, cluster 2 patients were younger, had shorter dialysis duration, were more likely to be retransplants, and were more likely to receive living donor kidney transplants from HLA mismatched donors. As such, cluster 2 recipients had a higher PRA, less cold ischemia time, and lower proportion of machine-perfused kidneys. Despite having a low KPS, 5-year patient survival was 79.1 and 83.9% for clusters 1 and 2; 5-year death-censored graft survival was 86.9 and 91.9%. Cluster 1 had lower death-censored graft survival and patient survival but higher acute rejection, compared to cluster 2. Conclusion: Our study used an unsupervised machine learning approach to characterize kidney transplant recipients with limited functional status into two clinically distinct clusters with differing posttransplant outcomes.

Background: Better understanding of the different phenotypes/subgroups of non-U.S. citizen kidney transplant recipients may help the transplant community to identify strategies that improve outcomes among non-U.S. citizen kidney transplant recipients. This study aimed to cluster non-U.S. citizen kidney transplant recipients using an unsupervised machine learning approach; Methods: We conducted a consensus cluster analysis based on recipient-, donor-, and transplant- related characteristics in non-U.S. citizen kidney transplant recipients in the United States from 2010 to 2019 in the OPTN/UNOS database using recipient, donor, and transplant-related characteristics. Each cluster’s key characteristics were identified using the standardized mean difference. Post-transplant outcomes were compared among the clusters; Results: Consensus cluster analysis was performed in 11,300 non-U.S. citizen kidney transplant recipients and identified two distinct clusters best representing clinical characteristics. Cluster 1 patients were notable for young age, preemptive kidney transplant or dialysis duration of less than 1 year, working income, private insurance, non-hypertensive donors, and Hispanic living donors with a low number of HLA mismatch. In contrast, cluster 2 patients were characterized by non-ECD deceased donors with KDPI <85%. Consequently, cluster 1 patients had reduced cold ischemia time, lower proportion of machine-perfused kidneys, and lower incidence of delayed graft function after kidney transplant. Cluster 2 had higher 5-year death-censored graft failure (5.2% vs. 9.8%; p < 0.001), patient death (3.4% vs. 11.4%; p < 0.001), but similar one-year acute rejection (4.7% vs. 4.9%; p = 0.63), compared to cluster 1; Conclusions: Machine learning clustering approach successfully identified two clusters among non-U.S. citizen kidney transplant recipients with distinct phenotypes that were associated with different outcomes, including allograft loss and patient survival. These findings underscore the need for individualized care for non-U.S. citizen kidney transplant recipients.