Background: The study developed accurate explainable machine learning (ML) models for predicting first-time acute exacerbation of chronic obstructive pulmonary disease (COPD, AECOPD) at an individual level. Methods: We conducted a retrospective case–control study. A total of 606 patients with COPD were screened for eligibility using registry data from the COPD Pay-for-Performance Program (COPD P4P program) database at Changhua Christian Hospital between January 2017 and December 2019. Recursive feature elimination technology was used to select the optimal subset of features for predicting the occurrence of AECOPD. We developed four ML models to predict first-time AECOPD, and the highest-performing model was applied. Finally, an explainable approach based on ML and the SHapley Additive exPlanations (SHAP) and a local explanation method were used to evaluate the risk of AECOPD and to generate individual explanations of the model’s decisions. Results: The gradient boosting machine (GBM) and support vector machine (SVM) models exhibited superior discrimination ability (area under curve [AUC] = 0.833 [95% confidence interval (CI) 0.745–0.921] and AUC = 0.836 [95% CI 0.757–0.915], respectively). The decision curve analysis indicated that the GBM model exhibited a higher net benefit in distinguishing patients at high risk for AECOPD when the threshold probability was <0.55. The COPD Assessment Test (CAT) and the symptom of wheezing were the two most important features and exhibited the highest SHAP values, followed by monocyte count and white blood cell (WBC) count, coughing, red blood cell (RBC) count, breathing rate, oral long-acting bronchodilator use, chronic pulmonary disease (CPD), systolic blood pressure (SBP), and others. Higher CAT score; monocyte, WBC, and RBC counts; BMI; diastolic blood pressure (DBP); neutrophil-to-lymphocyte ratio; and eosinophil and lymphocyte counts were associated with AECOPD. The presence of symptoms (wheezing, dyspnea, coughing), chronic disease (CPD, congestive heart failure [CHF], sleep disorders, and pneumonia), and use of COPD medications (triple-therapy long-acting bronchodilators, short-acting bronchodilators, oral long-acting bronchodilators, and antibiotics) were also positively associated with AECOPD. A high breathing rate, heart rate, or systolic blood pressure and methylxanthine use were negatively correlated with AECOPD. Conclusions: The ML model was able to accurately assess the risk of AECOPD. The ML model combined with SHAP and the local explanation method were able to provide interpretable and visual explanations of individualized risk predictions, which may assist clinical physicians in understanding the effects of key features in the model and the model’s decision-making process.

Background: Nutrition and inflammation have been implicated in predicting mortality in patients on peritoneal dialysis (PD). Serum albumin and globulin can be regarded for the nutritional and inflammatory status. However, there is lack of data to evaluate the synergistic effect of albumin and globulin on mortality prediction. Methods: In 554 patients initiating PD from January 2001 to July 2016, we divided them into four groups by the combination of two categories of low vs. high albumin and low vs. high globulin. The median values for albumin and globulin were chosen to classify them into low or high groups. Their associations with all-cause and cardiovascular (CV) mortality were examined in Cox regression models adjusted for confounding clinical and laboratory data. Results: Patients, 52.91 ± 15.2 years old and 47.8% men, had a median (interquartile range) value of 3.3 (2.9–3.8) g/dL for albumin and 2.8 (2.5–3.2) g/dL for globulin, respectively. Patients with low albumin and high globulin had the highest all-cause mortality and CV mortality, with adjusted hazard ratios of 3.87 (95% CI 1.83–8.20, p < 0.001) and 5.65 (95% CI 2.23–14.34, p < 0.001), respectively, compared with those with a high albumin and low globulin having the lowest mortality rate. Sensitivity analyses further confirmed this relationship. Conclusions: A patient profile of either low albumin or high globulin is linked to a higher risk for mortality, particularly for a profile of both low albumin and high globulin compared with one without either of them. Further studies are needed to explore the mechanisms underlying this phenomenon and how to improve clinical outcomes in those high-risk patients.

In this study, we established an explainable and personalized risk prediction model for in-hospital mortality after continuous renal replacement therapy (CRRT) initiation. This retrospective cohort study was conducted at Changhua Christian Hospital (CCH). A total of 2932 consecutive intensive care unit patients receiving CRRT between 1 January 2010, and 30 April 2021, were identified from the CCH Clinical Research Database and were included in this study. The recursive feature elimination method with 10-fold cross-validation was used and repeated five times to select the optimal subset of features for the development of machine learning (ML) models to predict in-hospital mortality after CRRT initiation. An explainable approach based on ML and the SHapley Additive exPlanation (SHAP) and a local explanation method were used to evaluate the risk of in-hospital mortality and help clinicians understand the results of ML models. The extreme gradient boosting and gradient boosting machine models exhibited a higher discrimination ability (area under curve [AUC] = 0.806, 95% CI = 0.770–0.843 and AUC = 0.823, 95% CI = 0.788–0.858, respectively). The SHAP model revealed that the Acute Physiology and Chronic Health Evaluation II score, albumin level, and the timing of CRRT initiation were the most crucial features, followed by age, potassium and creatinine levels, SPO2, mean arterial pressure, international normalized ratio, and vasopressor support use. ML models combined with SHAP and local interpretation can provide the visual interpretation of individual risk predictions, which can help clinicians understand the effect of critical features and make informed decisions for preventing in-hospital deaths.

Serum potassium (K+) levels between 3.5 and 5.0 mmol/L are considered safe for patients. The optimal serum K+ level for critically ill patients with acute kidney injury undergoing continuous renal replacement therapy (CRRT) remains unclear. This retrospective study investigated the association between ICU mortality and K+ levels and their variability. Patients aged >20 years with a minimum of two serum K+ levels recorded during CRRT who were admitted to the ICU in a tertiary hospital in central Taiwan between January 01, 2010, and April 30, 2021 were eligible for inclusion. Patients were categorized into different groups based on their mean K+ levels: <3.0, 3.0 to <3.5, 3.5 to <4.0, 4.0 to <4.5, 4.5 to <5.0, and ≥5.0 mmol/L; K+ variability was divided by the quartiles of the average real variation. We analyzed the association between the particular groups and in-hospital mortality by using Cox proportional hazard models. We studied 1991 CRRT patients with 9891 serum K+ values recorded within 24 h after the initiation of CRRT. A J-shaped association was observed between serum K+ levels and mortality, and the lowest mortality was observed in the patients with mean K+ levels between 3.0 and 4.0 mmol/L. The risk of in-hospital death was significantly increased in those with the highest variability (HR and 95% CI = 1.61 [1.13–2.29] for 72 h mortality; 1.39 [1.06–1.82] for 28-day mortality; 1.43 [1.11–1.83] for 90-day mortality, and 1.31 [1.03–1.65] for in-hospital mortality, respectively). Patients receiving CRRT may benefit from a lower serum K+ level and its tighter control. During CRRT, progressively increased mortality was noted in the patients with increasing K+ variability. Thus, the careful and timely correction of dyskalemia among these patients is crucial.

(1) Background: Little is known about the subsequent renal function change following incident infectious diseases in living-donor liver transplant (LT) recipients. (2) Methods: We studied patients who underwent living-donor LT from January 2003 to January 2019 to evaluate the association of incident hospitalization with major infections or pneumonia with adverse renal outcomes, including a sustained 40% reduction in estimated glomerular filtration rate (eGFR) and renal composite outcome (a 40% decline in eGFR, end-stage renal disease, or death.). Multivariable-adjusted time-dependent Cox models with infection as a time-varying exposure were used to estimate hazard ratio (HR) with 95% confidence interval (CI) for study outcomes. (3) Results: We identified 435 patients (mean age 54.6 ± 8.4 years and 76.3% men), of whom 102 had hospitalization with major infections during follow-up; the most common cause of infection was pneumonia (38.2%). In multiple Cox models, hospitalization with a major infection was associated with an increased risk of eGFR decline > 40% (HR, 3.32; 95% CI 2.13–5.16) and renal composite outcome (HR, 3.41; 95% CI 2.40–5.24). Likewise, pneumonia was also associated with an increased risk of eGFR decline > 40% (HR, 2.47; 95% CI 1.10–5.56) and renal composite outcome (HR, 4.37; 95% CI 2.39–8.02). (4) Conclusions: Our results illustrated the impact of a single infection episode on the future risk of adverse renal events in LT recipients. Whether preventive and prophylactic care bundles against infection and judicious modification of the immunosuppressive regimen benefit renal outcomes may deserve further study.

Background: This study aimed to determine the association between episodic or persistent hematuria after liver transplantation and long-term renal outcomes. Methods: Patients who underwent living donor liver transplantation between July 2005 and June 2019 were recruited and divided into two groups based on the finding of microscopic or gross hematuria after transplantation. All patients were followed up from the index date until the end date in May 2020. The risks of chronic kidney disease, death, and 30% and 50% declines in estimated glomerular filtration rate (eGFR) were compared between groups. Results: A total of 295 patients underwent urinalysis for various reasons after undergoing transplantation. Hematuria was detected in 100 patients (group A) but was not present in 195 patients (group B). Compared with group B, group A had a higher risk of renal progression, including eGFR decline >50% [aHR = 3.447 (95%CI: 2.24~5.30), p < 0.001] and worse survival. In addition, patients who took non-steroidal anti-inflammatory drugs (NSAIDs) continuously for over seven days within six months before transplant surgery had high risks of rapid renal progression, including a >30% decline in eGFR [aHR = 1.572 (95%CI: 1.12~2.21), p = 0.009)]. Conclusion: Development of hematuria after surgery in patients who underwent living donor liver transplant and were exposed to NSAIDs before surgery were associated with worse long-term renal dysfunction and survival.