Prediction of Acute Kidney Injury after Liver Transplantation: Machine Learning Approaches vs. Logistic Regression Model

Development of interpretable machine learning models for prediction of acute kidney injury after noncardiac surgery: a retrospective cohort study

BACKGROUND

Early identification of patients at high-risk of postoperative acute kidney injury (AKI) can facilitate the development of preventive approaches. This study aimed to develop prediction models for postoperative AKI in noncardiac surgery using machine learning algorithms. The authors also evaluated the predictive performance of models that included only preoperative variables or only important predictors.

MATERIALS AND METHODS

Adult patients undergoing noncardiac surgery were retrospectively included in the study (76 457 patients in the discovery cohort and 11 910 patients in the validation cohort). AKI was determined using the KDIGO criteria. The prediction model was developed using 87 variables (56 preoperative variables and 31 intraoperative variables). A variety of machine learning algorithms were employed to develop the model, including logistic regression, random forest, extreme gradient boosting, and gradient boosting decision trees. The performance of different models was compared using the area under the receiver operating characteristic curve (AUROC). Shapley Additive Explanations (SHAP) analysis was employed for model interpretation.

RESULTS

The patients in the discovery cohort had a median age of 52 years (IQR: 42-61 years), and 1179 patients (1.5%) developed AKI after surgery. The gradient boosting decision trees algorithm showed the best predictive performance using all available variables, or only preoperative variables. The AUROCs were 0.849 (95% CI: 0.835-0.863) and 0.828 (95% CI: 0.813-0.843), respectively. The SHAP analysis showed that age, surgical duration, preoperative serum creatinine, and gamma-glutamyltransferase, as well as American Society of Anesthesiologists physical status III were the most important five features. When gradually reducing the features, the AUROCs decreased from 0.852 (including the top 40 features) to 0.839 (including the top 10 features). In the validation cohort, the authors observed a similar pattern regarding the models' predictive performance.

CONCLUSIONS

The machine learning models the authors developed had satisfactory predictive performance for identifying high-risk postoperative AKI patients. Furthermore, the authors found that model performance was only slightly affected when only preoperative variables or only the most important predictive features were included.

Development and performance assessment of novel machine learning models for predicting postoperative pneumonia in aneurysmal subarachnoid hemorrhage patients: external validation in MIMIC-IV

Background

Postoperative pneumonia (POP) is one of the primary complications after aneurysmal subarachnoid hemorrhage (aSAH) and is associated with postoperative mortality, extended hospital stay, and increased medical fee. Early identification of pneumonia and more aggressive treatment can improve patient outcomes. We aimed to develop a model to predict POP in aSAH patients using machine learning (ML) methods.

Methods

This internal cohort study included 706 patients with aSAH undergoing intracranial aneurysm embolization or aneurysm clipping. The cohort was randomly split into a train set (80%) and a testing set (20%). Perioperative information was collected from participants to establish 6 machine learning models for predicting POP after surgical treatment. The area under the receiver operating characteristic curve (AUC), precision-recall curve were used to assess the accuracy, discriminative power, and clinical validity of the predictions. The final model was validated using an external validation set of 97 samples from the Medical Information Mart for Intensive Care IV (MIMIC-IV) database.

Results

In this study, 15.01% of patients in the training set and 12.06% in the testing set with POP after underwent surgery. Multivariate logistic regression analysis showed that mechanical ventilation time (MVT), Glasgow Coma Scale (GCS), Smoking history, albumin level, neutrophil-to-albumin Ratio (NAR), c-reactive protein (CRP)-to-albumin ratio (CAR) were independent predictors of POP. The logistic regression (LR) model presented significantly better predictive performance (AUC: 0.91) than other models and also performed well in the external validation set (AUC: 0.89).

Conclusion

A machine learning model for predicting POP in aSAH patients was successfully developed using a machine learning algorithm based on six perioperative variables, which could guide high-risk POP patients to take appropriate preventive measures.

Use of machine learning models for the prognostication of liver transplantation: A systematic review

BACKGROUND

Liver transplantation (LT) is a life-saving intervention for patients with end-stage liver disease. However, the equitable allocation of scarce donor organs remains a formidable challenge. Prognostic tools are pivotal in identifying the most suitable transplant candidates. Traditionally, scoring systems like the model for end-stage liver disease have been instrumental in this process. Nevertheless, the landscape of prognostication is undergoing a transformation with the integration of machine learning (ML) and artificial intelligence models.

AIM

To assess the utility of ML models in prognostication for LT, comparing their per formance and reliability to established traditional scoring systems.

METHODS

Following the Preferred Reporting Items for Systematic Reviews and Meta-Analysis guidelines, we conducted a thorough and standardized literature search using the PubMed/MEDLINE database. Our search imposed no restrictions on publication year, age, or gender. Exclusion criteria encompassed non-English stu dies, review articles, case reports, conference papers, studies with missing data, or those exhibiting evident methodological flaws.

RESULTS

Our search yielded a total of 64 articles, with 23 meeting the inclusion criteria. Among the selected studies, 60.8% originated from the United States and China combined. Only one pediatric study met the criteria. Notably, 91% of the studies were published within the past five years. ML models consistently demonstrated satisfactory to excellent area under the receiver operating characteristic curve values (ranging from 0.6 to 1) across all studies, surpassing the performance of traditional scoring systems. Random forest exhibited superior predictive capa bilities for 90-d mortality following LT, sepsis, and acute kidney injury (AKI). In contrast, gradient boosting excelled in predicting the risk of graft-versus-host disease, pneumonia, and AKI.

CONCLUSION

This study underscores the potential of ML models in guiding decisions related to allograft allocation and LT, marking a significant evolution in the field of prognostication.

Artificial Intelligence in Liver Diseases: Recent Advances

Liver diseases cause a significant burden on public health worldwide. In spite of great advances during recent years, there are still many challenges in the diagnosis and treatment of liver diseases. During recent years, artificial intelligence (AI) has been widely used for the diagnosis, risk stratification, and prognostic prediction of various diseases based on clinical datasets and medical images. Accumulative studies have shown its performance for diagnosing patients with nonalcoholic fatty liver disease and liver fibrosis and assessing their severity, and for predicting treatment response and recurrence of hepatocellular carcinoma, outcomes of liver transplantation recipients, and risk of drug-induced liver injury. Herein, we aim to comprehensively summarize the current evidence regarding diagnostic, prognostic, and/or therapeutic role of AI in these common liver diseases.

Quantitative methods for optimizing patient outcomes in liver transplantation

Liver transplantation (LT) is a lifesaving yet complex intervention with considerable challenges impacting graft and patient outcomes. Despite best practices, 5-year graft survival is only 70%. Sophisticated quantitative techniques offer potential solutions by assimilating multifaceted data into insights exceeding human cognition. Optimizing donor-recipient matching and graft allocation presents additional intricacies, involving the integration of clinical and laboratory data to select the ideal donor and recipient pair. Allocation must balance physiological variables with geographical and logistical constraints and timing. Quantitative methods can integrate these complex factors to optimize graft utilization. Such methods can also aid in personalizing treatment regimens, drawing on both pretransplant and posttransplant data, possibly using continuous immunological monitoring to enable early detection of graft injury or infected states. Advanced analytics is thus poised to transform management in LT, maximizing graft and patient survival. In this review, we describe quantitative methods applied to organ transplantation, with a focus on LT. These include quantitative methods for (1) utilizing and allocating donor organs equitably and optimally, (2) improving surgical planning through preoperative imaging, (3) monitoring graft and immune status, (4) determining immunosuppressant doses, and (5) establishing and maintaining the health of graft and patient after LT.

Predicting major adverse cardiovascular events after orthotopic liver transplantation using a supervised machine learning model: A cohort study

BACKGROUND

Liver transplant (LT) patients have become older and sicker. The rate of post-LT major adverse cardiovascular events (MACE) has increased, and this in turn raises 30-d post-LT mortality. Noninvasive cardiac stress testing loses accuracy when applied to pre-LT cirrhotic patients.

AIM

To assess the feasibility and accuracy of a machine learning model used to predict post-LT MACE in a regional cohort.

METHODS

This retrospective cohort study involved 575 LT patients from a Southern Brazilian academic center. We developed a predictive model for post-LT MACE (defined as a composite outcome of stroke, new-onset heart failure, severe arrhythmia, and myocardial infarction) using the extreme gradient boosting (XGBoost) machine learning model. We addressed missing data (below 20%) for relevant variables using the k-nearest neighbor imputation method, calculating the mean from the ten nearest neighbors for each case. The modeling dataset included 83 features, encompassing patient and laboratory data, cirrhosis complications, and pre-LT cardiac assessments. Model performance was assessed using the area under the receiver operating characteristic curve (AUROC). We also employed Shapley additive explanations (SHAP) to interpret feature impacts. The dataset was split into training (75%) and testing (25%) sets. Calibration was evaluated using the Brier score. We followed Transparent Reporting of a Multivariable Prediction Model for Individual Prognosis or Diagnosis guidelines for reporting. Scikit-learn and SHAP in Python 3 were used for all analyses. The supplementary material includes code for model development and a user-friendly online MACE prediction calculator.

RESULTS

Of the 537 included patients, 23 (4.46%) developed in-hospital MACE, with a mean age at transplantation of 52.9 years. The majority, 66.1%, were male. The XGBoost model achieved an impressive AUROC of 0.89 during the training stage. This model exhibited accuracy, precision, recall, and F1-score values of 0.84, 0.85, 0.80, and 0.79, respectively. Calibration, as assessed by the Brier score, indicated excellent model calibration with a score of 0.07. Furthermore, SHAP values highlighted the significance of certain variables in predicting postoperative MACE, with negative noninvasive cardiac stress testing, use of nonselective beta-blockers, direct bilirubin levels, blood type O, and dynamic alterations on myocardial perfusion scintigraphy being the most influential factors at the cohort-wide level. These results highlight the predictive capability of our XGBoost model in assessing the risk of post-LT MACE, making it a valuable tool for clinical practice.

CONCLUSION

Our study successfully assessed the feasibility and accuracy of the XGBoost machine learning model in predicting post-LT MACE, using both cardiovascular and hepatic variables. The model demonstrated impressive performance, aligning with literature findings, and exhibited excellent calibration. Notably, our cautious approach to prevent overfitting and data leakage suggests the stability of results when applied to prospective data, reinforcing the model's value as a reliable tool for predicting post-LT MACE in clinical practice.

Machine Learning Models for Prediction of Maternal Hemorrhage and Transfusion: Model Development Study

BACKGROUND

Current postpartum hemorrhage (PPH) risk stratification is based on traditional statistical models or expert opinion. Machine learning could optimize PPH prediction by allowing for more complex modeling.

OBJECTIVE

We sought to improve PPH prediction and compare machine learning and traditional statistical methods.

METHODS

We developed models using the Consortium for Safe Labor data set (2002-2008) from 12 US hospitals. The primary outcome was a transfusion of blood products or PPH (estimated blood loss of ≥1000 mL). The secondary outcome was a transfusion of any blood product. Fifty antepartum and intrapartum characteristics and hospital characteristics were included. Logistic regression, support vector machines, multilayer perceptron, random forest, and gradient boosting (GB) were used to generate prediction models. The area under the receiver operating characteristic curve (ROC-AUC) and area under the precision/recall curve (PR-AUC) were used to compare performance.

RESULTS

Among 228,438 births, 5760 (3.1%) women had a postpartum hemorrhage, 5170 (2.8%) had a transfusion, and 10,344 (5.6%) met the criteria for the transfusion-PPH composite. Models predicting the transfusion-PPH composite using antepartum and intrapartum features had the best positive predictive values, with the GB machine learning model performing best overall (ROC-AUC=0.833, 95% CI 0.828-0.838; PR-AUC=0.210, 95% CI 0.201-0.220). The most predictive features in the GB model predicting the transfusion-PPH composite were the mode of delivery, oxytocin incremental dose for labor (mU/minute), intrapartum tocolytic use, presence of anesthesia nurse, and hospital type.

CONCLUSIONS

Machine learning offers higher discriminability than logistic regression in predicting PPH. The Consortium for Safe Labor data set may not be optimal for analyzing risk due to strong subgroup effects, which decreases accuracy and limits generalizability.

Prediction of Complications and Prognostication in Perioperative Medicine: A Systematic Review and PROBAST Assessment of Machine Learning Tools

BACKGROUND

The utilization of artificial intelligence and machine learning as diagnostic and predictive tools in perioperative medicine holds great promise. Indeed, many studies have been performed in recent years to explore the potential. The purpose of this systematic review is to assess the current state of machine learning in perioperative medicine, its utility in prediction of complications and prognostication, and limitations related to bias and validation.

METHODS

A multidisciplinary team of clinicians and engineers conducted a systematic review using the Preferred Reporting Items for Systematic Review and Meta-Analysis (PRISMA) protocol. Multiple databases were searched, including Scopus, Cumulative Index to Nursing and Allied Health Literature (CINAHL), the Cochrane Library, PubMed, Medline, Embase, and Web of Science. The systematic review focused on study design, type of machine learning model used, validation techniques applied, and reported model performance on prediction of complications and prognostication. This review further classified outcomes and machine learning applications using an ad hoc classification system. The Prediction model Risk Of Bias Assessment Tool (PROBAST) was used to assess risk of bias and applicability of the studies.

RESULTS

A total of 103 studies were identified. The models reported in the literature were primarily based on single-center validations (75%), with only 13% being externally validated across multiple centers. Most of the mortality models demonstrated a limited ability to discriminate and classify effectively. The PROBAST assessment indicated a high risk of systematic errors in predicted outcomes and artificial intelligence or machine learning applications.

CONCLUSIONS

The findings indicate that the development of this field is still in its early stages. This systematic review indicates that application of machine learning in perioperative medicine is still at an early stage. While many studies suggest potential utility, several key challenges must be first overcome before their introduction into clinical practice.

EDITOR’S PERSPECTIVE

Clinical Deployment of Machine Learning Tools in Transplant Medicine: What Does the Future Hold?

Medical applications of machine learning (ML) have shown promise in analyzing patient data to support clinical decision-making and provide patient-specific outcomes. In transplantation, several applications of ML exist which include pretransplant: patient prioritization, donor-recipient matching, organ allocation, and posttransplant outcomes. Numerous studies have shown the development and utility of ML models, which have the potential to augment transplant medicine. Despite increasing efforts to develop robust ML models for clinical use, very few of these tools are deployed in the healthcare setting. Here, we summarize the current applications of ML in transplant and discuss a potential clinical deployment framework using examples in organ transplantation. We identified that creating an interdisciplinary team, curating a reliable dataset, addressing the barriers to implementation, and understanding current clinical evaluation models could help in deploying ML models into the transplant clinic setting.

Pulmonary artery catheter monitoring versus arterial waveform-based monitoring during liver transplantation: a retrospective cohort study

Although pulmonary artery catheter (PAC) has been used during liver transplantation surgery, the usefulness of PAC has rarely been investigated. We evaluated whether the use of PAC is associated with better clinical outcomes compared to arterial waveform-based monitoring after liver transplantation. A total of 1565 cases undergoing liver transplantation were reviewed. We determined whether patients received PAC or not and divided our cohort into the PAC with hemodynamic monitoring using PAC and the non-PAC with arterial waveform-based monitoring using FloTrac-Vigileo. Propensity score matching was performed. Acute kidney injury (AKI), early allograft dysfunction (EAD) and 1-year all-cause mortality or graft failure were compared in the matched cohorts. Logistic regression analysis was performed in the inverse probability of treatment-weighted (IPTW) cohort for postoperative EAD and AKI, respectively. Five-year overall survival was compared between the two groups. In the matched cohort, there was no significant difference in the incidence of AKI, EAD, length of hospital or ICU stay, and 1-year all-cause mortality between the groups. In the IPTW cohort, the use of PAC was not a significant predictor for AKI or EAD (AKI: odds ratio (95% confidence interval) of 1.20 (0.47-1.56), p = 0.229; EAD: 0.99 (0.38-1.14), p = 0.323). There was no significant difference in the survival between groups after propensity score matching (Log-rank test p = 0.578). In conclusion, posttransplant clinical outcomes were not significantly different between the groups with and without PAC. Anesthetic management without the use of PAC may be possible in low-risk patients during liver transplantation. The risk should be carefully assessed by considering MELD scores, ischemic time, surgical history, previous treatment of underlying liver disease, and degree of portal and pulmonary hypertension.Registration: https://clinicaltrials.gov/ct2/show/NCT05457114 (registration date: July 15, 2022).

Association between total bilirubin/Albumin ratio and all-cause mortality in acute kidney injury patients: A retrospective cohort study

BACKGROUND

The association between the total bilirubin/albumin (B/A) and the all-cause mortality of critically ill patients with acute kidney injury (AKI) remains unclear. This retrospective study aimed to investigate the relationship between B/A ratio and mortality in patients with AKI.

METHODS

The clinical data of AKI patients in the Medical Information Mart for Intensive Care III (MIMIC-III) database were retrospectively analyzed. Patients were divided into the low and high B/A groups (B/A ≤ 0.25 and B/A > 0.25, respectively). The primary outcome was 28-day all-cause mortality, and the secondary outcomes were 60-day, 1-year and 4-year all-cause mortality. Kaplan-Meier survival curves and Cox proportional risk models were constructed to evaluate the effect of B/A on survival outcomes.

RESULTS

The 28-day mortality rates were 18.00% and 25.10% in the low and high B/A groups, respectively (P < 0.001). The Kaplan-Meier analysis showed that patients with higher B/A values had higher all-cause mortality risk (log-rank P < 0.0001). The multivariate Cox proportional risk analysis showed that B/A was an independent risk predictor for death at 28 days, 60 days, 1 year, and 4 years.

CONCLUSION

B/A is an independent risk factor for increased mortality in patients with AKI and may be used as a predictor of clinical outcomes in AKI.

Machine-learning-based approach for nonunion prediction following osteoporotic vertebral fractures

PURPOSE

An osteoporotic vertebral fracture (OVF) is a common disease that causes disabilities in elderly patients. In particular, patients with nonunion following an OVF often experience severe back pain and require surgical intervention. However, nonunion diagnosis generally takes more than six months. Although several studies have advocated the use of magnetic resonance imaging (MRI) observations as predictive factors, they exhibit insufficient accuracy. The purpose of this study was to create a predictive model for OVF nonunion using machine learning (ML).

METHODS

We used datasets from two prospective cohort studies for OVF nonunion prediction based on conservative treatment. Among 573 patients with acute OVFs exceeding 65 years in age enrolled in this study, 505 were analyzed. The demographic data, fracture type, and MRI observations of both studies were analyzed using ML. The ML architecture utilized in this study included a logistic regression model, decision tree, extreme gradient boosting (XGBoost), and random forest (RF). The datasets were processed using Python.

RESULTS

The two ML algorithms, XGBoost and RF, exhibited higher area under the receiver operating characteristic curves (AUCs) than the logistic regression and decision tree models (AUC = 0.860 and 0.845 for RF and XGBoost, respectively). The present study found that MRI findings, anterior height ratio, kyphotic angle, BMI, VAS, age, posterior wall injury, fracture level, and smoking habit ranked as important features in the ML algorithms.

CONCLUSION

ML-based algorithms might be more effective than conventional methods for nonunion prediction following OVFs.

Adjustment of p-value expression to ontology using machine learning for genetic prediction, prioritization, interaction, and its validation in glomerular disease

The results of gene expression analysis based on p-value can be extracted and sorted by their absolute statistical significance and then applied to multiple similarity scores of their gene ontology (GO) terms to promote the combination and adjustment of these scores as essential predictive tasks for understanding biological/clinical pathways. The latter allows the possibility to assess whether certain aspects of gene function may be associated with other varieties of genes, to evaluate regulation, and to link them into networks that prioritize candidate genes for classification by applying machine learning techniques. We then detect significant genetic interactions based on our algorithm to validate the results. Finally, based on specifically selected tissues according to their normalized gene expression and frequencies of occurrence from their different biological and clinical inputs, a reported classification of genes under the subject category has validated the abstract (glomerular diseases) as a case study.

The effect of Shengmai injection in patients with coronary heart disease in real world and its personalized medicine research using machine learning techniques

Objective: Shengmai injection is a common treatment for coronary heart disease. The accurate dose regimen is important to maximize effectiveness and minimize adverse reactions. We aim to explore the effect of Shengmai injection in patients with coronary heart disease based on real-world data and establish a personalized medicine model using machine learning and deep learning techniques. Methods: 211 patients were enrolled. The length of hospital stay was used to explore the effect of Shengmai injection in a case-control study. We applied propensity score matching to reduce bias and Wilcoxon rank sum test to compare results between the experimental group and the control group. Important variables influencing the dose regimen of Shengmai injection were screened by XGBoost. A personalized medicine model of Shengmai injection was established by XGBoost selected from nine algorithm models. SHapley Additive exPlanations and confusion matrix were used to interpret the results clinically. Results: Patients using Shengmai injection had shorter length of hospital stay than those not using Shengmai injection (median 10.00 days vs. 11.00 days, p = 0.006). The personalized medicine model established via XGBoost shows accuracy = 0.81 and AUC = 0.87 in test cohort and accuracy = 0.84 and AUC = 0.84 in external verification. The important variables influencing the dose regimen of Shengmai injection include lipid-lowering drugs, platelet-lowering drugs, levels of GGT, hemoglobin, prealbumin, and cholesterol at admission. Finally, the personalized model shows precision = 75%, recall rate = 83% and F1-score = 79% for predicting 40 mg of Shengmai injection; and precision = 86%, recall rate = 79% and F1-score = 83% for predicting 60 mg of Shengmai injection. Conclusion: This study provides evidence supporting the clinical effectiveness of Shengmai injection, and established its personalized medicine model, which may help clinicians make better decisions.

Comparison and development of machine learning for thalidomide-induced peripheral neuropathy prediction of refractory Crohn’s disease in Chinese population

BACKGROUND

Thalidomide is an effective treatment for refractory Crohn’s disease (CD). However, thalidomide-induced peripheral neuropathy (TiPN), which has a large individual variation, is a major cause of treatment failure. TiPN is rarely predictable and recognized, especially in CD. It is necessary to develop a risk model to predict TiPN occurrence.

AIM

To develop and compare a predictive model of TiPN using machine learning based on comprehensive clinical and genetic variables.

METHODS

A retrospective cohort of 164 CD patients from January 2016 to June 2022 was used to establish the model. The National Cancer Institute Common Toxicity Criteria Sensory Scale (version 4.0) was used to assess TiPN. With 18 clinical features and 150 genetic variables, five predictive models were established and evaluated by the confusion matrix receiver operating characteristic curve (AUROC), area under the precision-recall curve (AUPRC), specificity, sensitivity (recall rate), precision, accuracy, and F1 score.

RESULTS

The top-ranking five risk variables associated with TiPN were interleukin-12 rs1353248 [P = 0.0004, odds ratio (OR): 8.983, 95% confidence interval (CI): 2.497-30.90], dose (mg/d, P = 0.002), brain-derived neurotrophic factor (BDNF) rs2030324 (P = 0.001, OR: 3.164, 95%CI: 1.561-6.434), BDNF rs6265 (P = 0.001, OR: 3.150, 95%CI: 1.546-6.073) and BDNF rs11030104 (P = 0.001, OR: 3.091, 95%CI: 1.525-5.960). In the training set, gradient boosting decision tree (GBDT), extremely random trees (ET), random forest, logistic regression and extreme gradient boosting (XGBoost) obtained AUROC values > 0.90 and AUPRC > 0.87. Among these models, XGBoost and GBDT obtained the first two highest AUROC (0.90 and 1), AUPRC (0.98 and 1), accuracy (0.96 and 0.98), precision (0.90 and 0.95), F1 score (0.95 and 0.98), specificity (0.94 and 0.97), and sensitivity (1). In the validation set, XGBoost algorithm exhibited the best predictive performance with the highest specificity (0.857), accuracy (0.818), AUPRC (0.86) and AUROC (0.89). ET and GBDT obtained the highest sensitivity (1) and F1 score (0.8). Overall, compared with other state-of-the-art classifiers such as ET, GBDT and RF, XGBoost algorithm not only showed a more stable performance, but also yielded higher ROC-AUC and PRC-AUC scores, demonstrating its high accuracy in prediction of TiPN occurrence.

CONCLUSION

The powerful XGBoost algorithm accurately predicts TiPN using 18 clinical features and 14 genetic variables. With the ability to identify high-risk patients using single nucleotide polymorphisms, it offers a feasible option for improving thalidomide efficacy in CD patients.

Artificial intelligence, machine learning, and deep learning in liver transplantation

Liver transplantation (LT) is a life-saving treatment for individuals with end-stage liver disease. The management of LT recipients is complex, predominantly because of the need to consider demographic, clinical, laboratory, pathology, imaging, and omics data in the development of an appropriate treatment plan. Current methods to collate clinical information are susceptible to some degree of subjectivity; thus, clinical decision-making in LT could benefit from the data-driven approach offered by artificial intelligence (AI). Machine learning and deep learning could be applied in both the pre- and post-LT settings. Some examples of AI applications pre-transplant include optimising transplant candidacy decision-making and donor-recipient matching to reduce waitlist mortality and improve post-transplant outcomes. In the post-LT setting, AI could help guide the management of LT recipients, particularly by predicting patient and graft survival, along with identifying risk factors for disease recurrence and other associated complications. Although AI shows promise in medicine, there are limitations to its clinical deployment which include dataset imbalances for model training, data privacy issues, and a lack of available research practices to benchmark model performance in the real world. Overall, AI tools have the potential to enhance personalised clinical decision-making, especially in the context of liver transplant medicine.

Characterization of Risk Prediction Models for Acute Kidney Injury: A Systematic Review and Meta-analysis

Importance

Despite the expansion of published prediction models for acute kidney injury (AKI), there is little evidence of uptake of these models beyond their local derivation nor data on their association with patient outcomes.

Objective

To systematically review published AKI prediction models across all clinical subsettings.

Data Sources

MEDLINE via PubMed (January 1946 to April 2021) and Embase (January 1947 to April 2021) were searched using medical subject headings and text words related to AKI and prediction models.

Study Selection

All studies that developed a prediction model for AKI, defined as a statistical model with at least 2 predictive variables to estimate future occurrence of AKI, were eligible for inclusion. There was no limitation on study populations or methodological designs.

Data Extraction and Synthesis

Two authors independently searched the literature, screened the studies, and extracted and analyzed the data following the Preferred Reporting Items for Systematic Review and Meta-analyses guideline. The data were pooled using a random-effects model, with subgroups defined by 4 clinical settings. Between-study heterogeneity was explored using multiple methods, and funnel plot analysis was used to identify publication bias.

Main Outcomes and Measures

C statistic was used to measure the discrimination of prediction models.

Results

Of the 6955 studies initially identified through literature searching, 150 studies, with 14.4 million participants, met the inclusion criteria. The study characteristics differed widely in design, population, AKI definition, and model performance assessments. The overall pooled C statistic was 0.80 (95% CI, 0.79-0.81), with pooled C statistics in different clinical subsettings ranging from 0.78 (95% CI, 0.75-0.80) to 0.82 (95% CI, 0.78-0.86). Between-study heterogeneity was high overall and in the different clinical settings (eg, contrast medium-associated AKI: I2 = 99.9%; P < .001), and multiple methods did not identify any clear sources. A high proportion of models had a high risk of bias (126 [84.4%]) according to the Prediction Model Risk Of Bias Assessment Tool.

Conclusions and Relevance

In this study, the discrimination of the published AKI prediction models was good, reflected by high C statistics; however, the wide variation in the clinical settings, populations, and predictive variables likely drives the highly heterogenous findings that limit clinical utility. Standardized procedures for development and validation of prediction models are urgently needed.

Recipient Survival after Orthotopic Liver Transplantation: Interpretable Machine Learning Survival Tree Algorithm for Patient-Specific Outcomes

BACKGROUND

Elucidating contributors affecting liver transplant survival is paramount. Current methods offer crude global group outcomes. To refine patient-specific mortality probability estimation and to determine covariate interaction using recipient and donor data, we generated a survival tree algorithm, Recipient Survival After Orthotopic Liver Transplantation (ReSOLT), using United Network Organ Sharing (UNOS) transplant data.

STUDY DESIGN

The UNOS database was queried for liver transplants in patients ≥18 years old between 2000 and 2021. Preoperative factors were evaluated with stepwise logistic regression; 43 significant factors were used in survival tree modeling. Graft survival of <7 days was excluded. The data were split into training and testing sets and further validated with 10-fold cross-validation. Survival tree pruning and model selection was achieved based on Akaike information criterion and log-likelihood values. Log-rank pairwise comparisons between subgroups and estimated survival probabilities were calculated.

RESULTS

A total of 122,134 liver transplant patients were included for modeling. Multivariable logistic regression (area under the curve = 0.742, F1 = 0.822) and survival tree modeling returned 8 significant recipient survival factors: recipient age, donor age, recipient primary payment, recipient hepatitis C status, recipient diabetes, recipient functional status at registration and at transplantation, and deceased donor pulmonary infection. Twenty subgroups consisting of combinations of these factors were identified with distinct Kaplan-Meier survival curves (p < 0.001 among all by log rank test) with 5- and 10-year survival probabilities.

CONCLUSIONS

Survival trees are a flexible and effective approach to understand the effects and interactions of covariates on survival. Individualized survival probability following liver transplant is possible with ReSOLT, allowing for more coherent patient and family counseling and prediction of patient outcome using both recipient and donor factors.

Prospective Evaluation of Quantitative F-18-FDG-PET/CT for Pre-Operative Thoracic Lymph Node Staging in Patients with Lung Cancer as a Target for Computer-Aided Diagnosis

Purpose: Pre-operative assessment of thoracic lymphonodal (LN) involvement in patients with lung cancer (LC) is crucial when choosing the treatment modality. Visual assessment of F-18-FDG-PET/CT (PET/CT) is well established, however, there is still a need for prospective quantitative data to differentiate benign from malignant lesions which would simplify staging and guide the further implementation of computer-aided diagnosis (CAD). Methods: In this prospective study, 37 patients with confirmed lung cancer (m/f = 24/13; age: 70 [52–83] years) were analyzed. All patients underwent PET/CT and quantitative data (standardized uptake values) were obtained. Histological results were available for 101 thoracic lymph nodes. Quantitative data were matched to determine cut-off values for delineation between benign vs. malignant lymph nodes. Furthermore, a scoring system derived from these cut-off values was established. Statistical analyses were performed through ROC analysis. Results: Quantitative analysis revealed the optimal cut-off values (p < 0.01) for the differentiation between benign and malignant thoracic lymph nodes in patients suffering from lung cancer. The respective areas under the curve (AUC) ranged from 0.86 to 0.94. The highest AUC for a ratio of lymph node to healthy lung tissue was 0.94. The resulting accuracy ranged from 78.2% to 89.1%. A dedicated scoring system led to an AUC of 0.93 with a negative predictive value of 95.4%. Conclusion: Quantitative analysis of F-18-FDG-PET/CT data provides reliable results for delineation between benign and malignant thoracic lymph nodes. Thus, quantitative parameters can improve diagnostic accuracy and reliability and can also facilitate the handling of the steadily increasing number of clinical examinations.

Machine Learning Models of Postoperative Atrial Fibrillation Prediction After Cardiac Surgery

OBJECTIVES

This study aimed to use machine learning algorithms to build an efficient forecasting model of atrial fibrillation after cardiac surgery, and to compare the predictive performance of machine learning to traditional logistic regression.

DESIGN

A retrospective study.

SETTING

Second Affiliated Hospital of Zhejiang University School of Medicine.

PARTICIPANTS

The study comprised 1,400 patients who underwent valve and/or coronary artery bypass grafting surgery with cardiopulmonary bypass from September 1, 2013 to December 31, 2018.

INTERVENTIONS

None.

MEASUREMENTS AND MAIN RESULTS

Two machine learning approaches (gradient-boosting decision tree and support-vector machine) and logistic regression were used to build predictive models. The performance was compared by the area under the curve (AUC). The clinical practicability was assessed using decision curve analysis. Postoperative atrial fibrillation occurred in 519 patients (37.1%). The AUCs of the support-vector machine, logistic regression, and gradient boosting decision tree were 0.777 (95% CI: 0.772-0.781), 0.767 (95% CI: 0.762-0.772), and 0.765 (95% CI: 0.761-0.770), respectively. As decision curve analysis manifested, these models had achieved appropriate net benefit.

CONCLUSION

In the authors' study, the support-vector machine model was the best predictor; it may be an effective tool for predicting atrial fibrillation after cardiac surgery.

Logistic regression technique is comparable to complex machine learning algorithms in predicting cognitive impairment related to post intensive care syndrome

To evaluate the performance of machine learning (ML) models and to compare it with logistic regression (LR) technique in predicting cognitive impairment related to post intensive care syndrome (PICS-CI). We conducted a prospective observational study of ICU patients at two tertiary hospitals. A cohort of 2079 patients was screened, and finally 481 patients were included. Seven different ML models were considered, decision tree (DT), random forest (RF), XGBoost, neural network (NN), naïve bayes (NB), and support vector machine (SVM), and compared with logistic regression (LR). Discriminative ability was evaluated by area under the receiver operating characteristic curve (AUC), calibration belt plots, and Hosmer-Lemeshow test was used to assess calibration. Decision curve analysis was performed to quantify clinical utility. Duration of delirium, poor Richards-Campbell sleep questionnaire (RCSQ) score, advanced age, and sepsis were the most frequent and important candidates risk factors for PICS-CI. All ML models showed good performance (AUC range: 0.822-0.906). NN model had the highest AUC (0.906 [95% CI 0.857-0.955]), which was slightly higher than, but not significantly different from that of LR (0.898 [95% CI 0.847-0.949]) (P > 0.05, Delong test). Given the overfitting and complexity of some ML models, the LR model was then used to develop a web-based risk calculator to aid decision-making ( https://model871010.shinyapps.io/dynnomapp/ ). In a low dimensional data, LR may yield as good performance as other complex ML models to predict cognitive impairment after ICU hospitalization.

Machine learning for acute kidney injury: Changing the traditional disease prediction mode

Acute kidney injury (AKI) is a serious clinical comorbidity with clear short-term and long-term prognostic implications for inpatients. The diversity of risk factors for AKI has been recognized in previous studies, and a series of predictive models have been developed using traditional statistical methods in conjunction with its preventability, but they have failed to meet the expectations in limited clinical applications, the rapid spread of electronic health records and artificial intelligence machine learning technology has brought new hope for the construction of AKI prediction models. In this article, we systematically review the definition and classification of machine learning methods, modeling ideas and evaluation methods, and the characteristics and current status of modeling studies. According to the modeling objectives, we subdivided them into critical care medical setting models, all medical environment models, special surgery models, special disease models, and special nephrotoxin exposure models. As the first review article to comprehensively summarize and analyze machine learning prediction models for AKI, we aim to objectively describe the advantages and disadvantages of machine learning approaches to modeling, and help other researchers more quickly and intuitively understand the current status of modeling research, inspire ideas and learn from experience, so as to guide and stimulate more research and more in-depth exploration in the future, which will ultimately provide greater help to improve the overall status of AKI diagnosis and treatment.

A Novel Online Calculator Predicting Acute Kidney Injury After Liver Transplantation: A Retrospective Study

Acute kidney injury (AKI) after liver transplantation (LT) is a common complication, and its development is thought to be multifactorial. We aimed to investigate potential risk factors and build a model to identify high-risk patients. A total of 199 LT patients were enrolled and each patient data was collected from the electronic medical records. Our primary outcome was postoperative AKI as diagnosed and classified by the KDIGO criteria. A least absolute shrinkage and selection operating algorithm and multivariate logistic regression were utilized to select factors and construct the model. Discrimination and calibration were used to estimate the model performance. Decision curve analysis (DCA) was applied to assess the clinical application value. Five variables were identified as independent predictors for post-LT AKI, including whole blood serum lymphocyte count, RBC count, serum sodium, insulin dosage and anhepatic phase urine volume. The nomogram model showed excellent discrimination with an AUC of 0.817 (95% CI: 0.758-0.876) in the training set. The DCA showed that at a threshold probability between 1% and 70%, using this model clinically may add more benefit. In conclusion, we developed an easy-to-use tool to calculate the risk of post-LT AKI. This model may help clinicians identify high-risk patients.

Tacrolimus in the treatment of childhood nephrotic syndrome: Machine learning detects novel biomarkers and predicts efficacy

STUDY OBJECTIVE

The pharmacokinetics and pharmacodynamics of tacrolimus (TAC) vary greatly among individuals, hindering its precise utilization. Moreover, effective models for the early prediction of TAC efficacy in patients with nephrotic syndrome (NS) are lacking. We aimed to identify key factors affecting TAC efficacy and develop efficacy prediction models for childhood NS using machine learning algorithms.

DESIGN

This was an observational cohort study of patients with pediatric refractory NS.

SETTING

Guangzhou Women and Children's Medical Center between June 2013 and December 2018.

PATIENTS

203 patients with pediatric refractory NS were used for model generation and 35 patients were used for model validation.

INTERVENTION

All patients regularly received double immunosuppressive therapy comprising TAC and low-dose prednisone or methylprednisolone. In this observational cohort study of 203 pediatric patients with refractory NS, clinical and genetic variables, including single-nucleotide polymorphism (SNPs), were identified. TAC efficacy was evaluated 3 months after administration according to two different evaluation criteria: response or non-response (Group 1) and complete remission, partial remission, or non-remission (Group 2).

MEASUREMENTS

Logistic regression, extremely random trees, gradient boosting decision trees, random forest, and extreme gradient boosting algorithms were used to develop and validate the models. Prediction models were validated among a cohort of 35 patients with NS.

MAIN RESULTS

The random forest models performed best in both groups, and the area under the receiver operating characteristics curve of these two models was 80.7% (Group 1) and 80.3% (Group 2). These prediction models included urine erythrocyte count before administration, steroid types, and eight SNPs (ITGB4 rs2290460, TRPC6 rs3824934, CTGF rs9399005, IL13 rs20541, NFKBIA rs8904, NFKBIA rs8016947, MAP3K11 rs7946115, and SMARCAL1 rs11886806).

CONCLUSIONS

Two pre-administration models with good predictive performance for TAC response of patients with NS were developed and validated using machine learning algorithms. These accurate models could assist clinicians in predicting TAC efficacy in pediatric patients with NS before utilization to avoid treatment failure or adverse effects.

Revisiting transplant immunology through the lens of single-cell technologies

Solid organ transplantation (SOT) is the standard of care for end-stage organ disease. The most frequent complication of SOT involves allograft rejection, which may occur via T cell- and/or antibody-mediated mechanisms. Diagnosis of rejection in the clinical setting requires an invasive biopsy as there are currently no reliable biomarkers to detect rejection episodes. Likewise, it is virtually impossible to identify patients who exhibit operational tolerance and may be candidates for reduced or complete withdrawal of immunosuppression. Emerging single-cell technologies, including cytometry by time-of-flight (CyTOF), imaging mass cytometry, and single-cell RNA sequencing, represent a new opportunity for deep characterization of pathogenic immune populations involved in both allograft rejection and tolerance in clinical samples. These techniques enable examination of both individual cellular phenotypes and cell-to-cell interactions, ultimately providing new insights into the complex pathophysiology of allograft rejection. However, working with these large, highly dimensional datasets requires expertise in advanced data processing and analysis using computational biology techniques. Machine learning algorithms represent an optimal strategy to analyze and create predictive models using these complex datasets and will likely be essential for future clinical application of patient level results based on single-cell data. Herein, we review the existing literature on single-cell techniques in the context of SOT.

Artificial intelligence for the prediction of acute kidney injury during the perioperative period: systematic review and Meta-analysis of diagnostic test accuracy

BACKGROUND

Acute kidney injury (AKI) is independently associated with morbidity and mortality in a wide range of surgical settings. Nowadays, with the increasing use of electronic health records (EHR), advances in patient information retrieval, and cost reduction in clinical informatics, artificial intelligence is increasingly being used to improve early recognition and management for perioperative AKI. However, there is no quantitative synthesis of the performance of these methods. We conducted this systematic review and meta-analysis to estimate the sensitivity and specificity of artificial intelligence for the prediction of acute kidney injury during the perioperative period.

METHODS

Pubmed, Embase, and Cochrane Library were searched to 2nd October 2021. Studies presenting diagnostic performance of artificial intelligence in the early detection of perioperative acute kidney injury were included. True positives, false positives, true negatives and false negatives were pooled to collate specificity and sensitivity with 95% CIs and results were portrayed in forest plots. The risk of bias of eligible studies was assessed using the PROBAST tool.

RESULTS

Nineteen studies involving 304,076 patients were included. Quantitative random-effects meta-analysis using the Rutter and Gatsonis hierarchical summary receiver operating characteristics (HSROC) model revealed pooled sensitivity, specificity, and diagnostic odds ratio of 0.77 (95% CI: 0.73 to 0.81),0.75 (95% CI: 0.71 to 0.80), and 10.7 (95% CI 8.5 to 13.5), respectively. Threshold effect was found to be the only source of heterogeneity, and there was no evidence of publication bias.

CONCLUSIONS

Our review demonstrates the promising performance of artificial intelligence for early prediction of perioperative AKI. The limitations of lacking external validation performance and being conducted only at a single center should be overcome.

TRIAL REGISTRATION

This study was not registered with PROSPERO.

Crossroads in Liver Transplantation: Is Artificial Intelligence the Key to Donor-Recipient Matching?

Liver transplantation outcomes have improved in recent years. However, with the emergence of expanded donor criteria, tools to better assist donor-recipient matching have become necessary. Most of the currently proposed scores based on conventional biostatistics are not good classifiers of a problem that is considered "unbalanced." In recent years, the implementation of artificial intelligence in medicine has experienced exponential growth. Deep learning, a branch of artificial intelligence, may be the answer to this classification problem. The ability to handle a large number of variables with speed, objectivity, and multi-objective analysis is one of its advantages. Artificial neural networks and random forests have been the most widely used deep classifiers in this field. This review aims to give a brief overview of D-R matching and its evolution in recent years and how artificial intelligence may be able to provide a solution.

Precision gynecologic oncology: circulating cell free DNA epigenomic analysis, artificial intelligence and the accurate detection of ovarian cancer

Ovarian cancer (OC) is the most lethal gynecologic cancer due primarily to its asymptomatic nature and late stage at diagnosis. The development of non-invasive markers is an urgent priority. We report the accurate detection of epithelial OC using Artificial Intelligence (AI) and genome-wide epigenetic analysis of circulating cell free tumor DNA (cfTDNA). In a prospective study, we performed genome-wide DNA methylation profiling of cytosine (CpG) markers. Both conventional logistic regression and six AI platforms were used for OC detection. Further, we performed Gene Set Enrichment Analysis (GSEA) analysis to elucidate the molecular pathogenesis of OC. A total of 179,238 CpGs were significantly differentially methylated (FDR p-value < 0.05) genome-wide in OC. High OC diagnostic accuracies were achieved. Conventional logistic regression achieved an area under the ROC curve (AUC) [95% CI] 0.99 [± 0.1] with 95% sensitivity and 100% specificity. Multiple AI platforms each achieved high diagnostic accuracies (AUC = 0.99-1.00). For example, for Deep Learning (DL)/AI AUC = 1.00, sensitivity = 100% and 88% specificity. In terms of OC pathogenesis: GSEA analysis identified 'Adipogenesis' and 'retinoblastoma gene in cancer' as the top perturbed molecular pathway in OC. This finding of epigenomic dysregulation of molecular pathways that have been previously linked to cancer adds biological plausibility to our results.

A Survey on Medical Explainable AI (XAI): Recent Progress, Explainability Approach, Human Interaction and Scoring System

The emerging field of eXplainable AI (XAI) in the medical domain is considered to be of utmost importance. Meanwhile, incorporating explanations in the medical domain with respect to legal and ethical AI is necessary to understand detailed decisions, results, and current status of the patient's conditions. Successively, we will be presenting a detailed survey for the medical XAI with the model enhancements, evaluation methods, significant overview of case studies with open box architecture, medical open datasets, and future improvements. Potential differences in AI and XAI methods are provided with the recent XAI methods stated as (i) local and global methods for preprocessing, (ii) knowledge base and distillation algorithms, and (iii) interpretable machine learning. XAI characteristics details with future healthcare explainability is included prominently, whereas the pre-requisite provides insights for the brainstorming sessions before beginning a medical XAI project. Practical case study determines the recent XAI progress leading to the advance developments within the medical field. Ultimately, this survey proposes critical ideas surrounding a user-in-the-loop approach, with an emphasis on human-machine collaboration, to better produce explainable solutions. The surrounding details of the XAI feedback system for human rating-based evaluation provides intelligible insights into a constructive method to produce human enforced explanation feedback. For a long time, XAI limitations of the ratings, scores and grading are present. Therefore, a novel XAI recommendation system and XAI scoring system are designed and approached from this work. Additionally, this paper encourages the importance of implementing explainable solutions into the high impact medical field.

An individualized medication model of sodium valproate for patients with bipolar disorder based on machine learning and deep learning techniques

Valproic acid/sodium valproate (VPA) is a widely used anticonvulsant drug for maintenance treatment of bipolar disorders. In order to balance the efficacy and adverse events of VPA treatment, an individualized dose regimen is necessary. This study aimed to establish an individualized medication model of VPA for patients with bipolar disorder based on machine learning and deep learning techniques. The sequential forward selection (SFS) algorithm was applied for selecting a feature subset, and random forest was used for interpolating missing values. Then, we compared nine models using XGBoost, LightGBM, CatBoost, random forest, GBDT, SVM, logistic regression, ANN, and TabNet, and CatBoost was chosen to establish the individualized medication model with the best performance (accuracy = 0.85, AUC = 0.91, sensitivity = 0.85, and specificity = 0.83). Three important variables that correlated with VPA daily dose included VPA TDM value, antipsychotics, and indirect bilirubin. SHapley Additive exPlanations was applied to visually interpret their impacts on VPA daily dose. Last, the confusion matrix presented that predicting a daily dose of 0.5 g VPA had a precision of 55.56% and recall rate of 83.33%, and predicting a daily dose of 1 g VPA had a precision of 95.83% and a recall rate of 85.19%. In conclusion, the individualized medication model of VPA for patients with bipolar disorder based on CatBoost had a good prediction ability, which provides guidance for clinicians to propose the optimal medication regimen.

Using machine learning models to predict HBeAg seroconversion in CHB patients receiving pegylated interferon-α monotherapy

BACKGROUND AND OBJECTIVE

Though there are many advantages of pegylated interferon-α (PegIFN-α) treatment to chronic hepatitis B (CHB) patients, the response rate of PegIFN-α is only 30 ~ 40%. Therefore, it is important to explore predictors at baseline and establish models to improve the response rate of PegIFN-α.

METHODS

We randomly divided 260 HBeAg-positive CHB patients who were not previously treated and received PegIFN-α monotherapy (180 μg/week) into a training dataset (70%) and testing dataset (30%). The intersect features were extracted from 50 routine laboratory variables using the recursive feature elimination method algorithm, Boruta algorithm, and Least Absolute Shrinkage and Selection Operator Regression algorithm in the training dataset. After that, based on the intersect features, eight machine learning models including Logistic Regression, k-Nearest Neighbors, Support Vector Machine, Decision Tree, Random Forest, Gradient Boosting, Extreme Gradient Boosting (XGBoost), and Naïve Bayes were applied to evaluate HBeAg seroconversion in HBeAg-positive CHB patients receiving PegIFN-α monotherapy in the training dataset and testing dataset.

RESULTS

XGBoost model showed the best performance, which had largest AUROC (0.900, 95% CI: 0.85-0.95 and 0.910, 95% CI: 0.84-0.98, in training dataset and testing dataset, respectively), and the best calibration curve performance to predict HBeAg seroconversion. The importance of XGBoost model indicated that treatment time contributed greatest to HBeAg seroconversion, followed by HBV DNA(log), HBeAg, HBeAb, HBcAb, ALT, triglyceride, and ALP.

CONCLUSIONS

XGBoost model based on common laboratory variables had good performance in predicting HBeAg seroconversion in HBeAg-positive CHB patients receiving PegIFN-α monotherapy.

Machine learning in predicting cardiac surgery-associated acute kidney injury: A systemic review and meta-analysis

Background

Cardiac surgery-associated acute kidney injury (CSA-AKI) is a common complication following cardiac surgery. Early prediction of CSA-AKI is of great significance for improving patients' prognoses. The aim of this study is to systematically evaluate the predictive performance of machine learning models for CSA-AKI.

Methods

Cochrane Library, PubMed, EMBASE, and Web of Science were searched from inception to 18 March 2022. Risk of bias assessment was performed using PROBAST. Rsoftware (version 4.1.1) was used to calculate the accuracy and C-index of CSA-AKI prediction. The importance of CSA-AKI prediction was defined according to the frequency of related factors in the models.

Results

There were 38 eligible studies included, with a total of 255,943 patients and 60 machine learning models. The models mainly included Logistic Regression (n = 34), Neural Net (n = 6), Support Vector Machine (n = 4), Random Forest (n = 6), Extreme Gradient Boosting (n = 3), Decision Tree (n = 3), Gradient Boosted Machine (n = 1), COX regression (n = 1), κNeural Net (n = 1), and Naïve Bayes (n = 1), of which 51 models with intact recording in the training set and 17 in the validating set. Variables with the highest predicting frequency included Logistic Regression, Neural Net, Support Vector Machine, and Random Forest. The C-index and accuracy wer 0.76 (0.740, 0.780) and 0.72 (0.70, 0.73), respectively, in the training set, and 0.79 (0.75, 0.83) and 0.73 (0.71, 0.74), respectively, in the test set.

Conclusion

The machine learning-based model is effective for the early prediction of CSA-AKI. More machine learning methods based on noninvasive or minimally invasive predictive indicators are needed to improve the predictive performance and make accurate predictions of CSA-AKI. Logistic regression remains currently the most commonly applied model in CSA-AKI prediction, although it is not the one with the best performance. There are other models that would be more effective, such as NNET and XGBoost.

Systematic review registration

https://www.crd.york.ac.uk/; review registration ID: CRD42022345259.

Preliminary prediction of semen quality based on modifiable lifestyle factors by using the XGBoost algorithm

Introduction

Semen quality has decreased gradually in recent years, and lifestyle changes are among the primary causes for this issue. Thus far, the specific lifestyle factors affecting semen quality remain to be elucidated.

Materials and methods

In this study, data on the following factors were collected from 5,109 men examined at our reproductive medicine center: 10 lifestyle factors that potentially affect semen quality (smoking status, alcohol consumption, staying up late, sleeplessness, consumption of pungent food, intensity of sports activity, sedentary lifestyle, working in hot conditions, sauna use in the last 3 months, and exposure to radioactivity); general factors including age, abstinence period, and season of semen examination; and comprehensive semen parameters [semen volume, sperm concentration, progressive and total sperm motility, sperm morphology, and DNA fragmentation index (DFI)]. Then, machine learning with the XGBoost algorithm was applied to establish a primary prediction model by using the collected data. Furthermore, the accuracy of the model was verified via multiple logistic regression following k-fold cross-validation analyses.

Results

The results indicated that for semen volume, sperm concentration, progressive and total sperm motility, and DFI, the area under the curve (AUC) values ranged from 0.648 to 0.697, while the AUC for sperm morphology was only 0.506. Among the 13 factors, smoking status was the major factor affecting semen volume, sperm concentration, and progressive and total sperm motility. Age was the most important factor affecting DFI. Logistic combined with cross-validation analysis revealed similar results. Furthermore, it showed that heavy smoking (>20 cigarettes/day) had an overall negative effect on semen volume and sperm concentration and progressive and total sperm motility (OR = 4.69, 6.97, 11.16, and 10.35, respectively), while age of >35 years was associated with increased DFI (OR = 5.47).

Conclusion

The preliminary lifestyle-based model developed for semen quality prediction by using the XGBoost algorithm showed potential for clinical application and further optimization with larger training datasets.

Performance of machine learning techniques on prediction of esophageal varices grades among patients with cirrhosis

OBJECTIVES

All patients with cirrhosis should be periodically examined for esophageal varices (EV), however, a large percentage of patients undergoing screening, do not have EV or have only mild EV and do not have high-risk characteristics. Therefore, developing a non-invasive method to predict the occurrence of EV in patients with liver cirrhosis as a non-invasive method with high accuracy seems useful. In the present research, we compared the performance of several machine learning (ML) methods to predict EV on laboratory and clinical data to choose the best model.

METHODS

Four-hundred-and-ninety data from the Liver and Gastroenterology Research Center of Shahid Beheshti University of Medical Sciences in the period 2014-2021, were analyzed applying models including random forest (RF), artificial neural network (ANN), support vector machine (SVM), and logistic regression.

RESULTS

RF and SVM had the best results in general for all grades of EV. RF showed remarkably better results and the highest area under the curve (AUC). After that, SVM and ANN had the AUC of 98%, for grade 3, the SVM algorithm had the highest AUC after RF (89%).

CONCLUSIONS

The findings may help to better predict EV with high precision and accuracy and also can help reduce the burden of frequent visits to endoscopic centers. It can also help practitioners to manage cirrhosis by predicting EV with lower costs.

Artificial Intelligence in Acute Kidney Injury Prediction

The use of artificial intelligence (AI) in nephrology and its associated clinical research is growing. Recent years have seen increased interest in utilizing AI to predict the development of hospital-based acute kidney injury (AKI). Several AI techniques have been employed to improve the ability to detect AKI across a variety of hospitalized settings. This review discusses the evolutions of AKI risk prediction discussing the static risk assessment models of yesteryear as well as the more recent trend toward AI and advanced learning techniques. We discuss the relative improvement in AKI detection as well as the relative dearth of data around the clinical implementation and patient outcomes using these models. The use of AI for AKI detection and clinical care is in its infancy, and this review describes how we arrived at our current position and hints at the promise of the future.

The promise of machine learning applications in solid organ transplantation

Solid-organ transplantation is a life-saving treatment for end-stage organ disease in highly selected patients. Alongside the tremendous progress in the last several decades, new challenges have emerged. The growing disparity between organ demand and supply requires optimal patient/donor selection and matching. Improvements in long-term graft and patient survival require data-driven diagnosis and management of post-transplant complications. The growing abundance of clinical, genetic, radiologic, and metabolic data in transplantation has led to increasing interest in applying machine-learning (ML) tools that can uncover hidden patterns in large datasets. ML algorithms have been applied in predictive modeling of waitlist mortality, donor–recipient matching, survival prediction, post-transplant complications diagnosis, and prediction, aiming to optimize immunosuppression and management. In this review, we provide insight into the various applications of ML in transplant medicine, why these were used to evaluate a specific clinical question, and the potential of ML to transform the care of transplant recipients. 36 articles were selected after a comprehensive search of the following databases: Ovid MEDLINE; Ovid MEDLINE Epub Ahead of Print and In-Process & Other Non-Indexed Citations; Ovid Embase; Cochrane Database of Systematic Reviews (Ovid); and Cochrane Central Register of Controlled Trials (Ovid). In summary, these studies showed that ML techniques hold great potential to improve the outcome of transplant recipients. Future work is required to improve the interpretability of these algorithms, ensure generalizability through larger-scale external validation, and establishment of infrastructure to permit clinical integration.

Artificial intelligence-enabled decision support in nephrology

Kidney pathophysiology is often complex, nonlinear and heterogeneous, which limits the utility of hypothetical-deductive reasoning and linear, statistical approaches to diagnosis and treatment. Emerging evidence suggests that artificial intelligence (AI)-enabled decision support systems - which use algorithms based on learned examples - may have an important role in nephrology. Contemporary AI applications can accurately predict the onset of acute kidney injury before notable biochemical changes occur; can identify modifiable risk factors for chronic kidney disease onset and progression; can match or exceed human accuracy in recognizing renal tumours on imaging studies; and may augment prognostication and decision-making following renal transplantation. Future AI applications have the potential to make real-time, continuous recommendations for discrete actions and yield the greatest probability of achieving optimal kidney health outcomes. Realizing the clinical integration of AI applications will require cooperative, multidisciplinary commitment to ensure algorithm fairness, overcome barriers to clinical implementation, and build an AI-competent workforce. AI-enabled decision support should preserve the pre-eminence of wisdom and augment rather than replace human decision-making. By anchoring intuition with objective predictions and classifications, this approach should favour clinician intuition when it is honed by experience.

Development and Validation of a Personalized Model With Transfer Learning for Acute Kidney Injury Risk Estimation Using Electronic Health Records

IMPORTANCE

Acute kidney injury (AKI) is a heterogeneous syndrome prevalent among hospitalized patients. Personalized risk estimation and risk factor identification may allow effective intervention and improved outcomes.

OBJECTIVE

To develop and validate personalized AKI risk estimation models using electronic health records (EHRs), examine whether personalized models were beneficial in comparison with global and subgroup models, and assess the heterogeneity of risk factors and their outcomes in different subpopulations.

DESIGN, SETTING, AND PARTICIPANTS

This diagnostic study analyzed EHR data from 1 tertiary care hospital and used machine learning and logistic regression to develop and validate global, subgroup, and personalized risk estimation models. Transfer learning was implemented to enhance the personalized model. Predictor outcomes across subpopulations were analyzed, and metaregression was used to explore predictor interactions. Adults who were hospitalized for 2 or more days from November 1, 2007, to December 31, 2016, were included in the analysis. Patients with moderate or severe kidney dysfunction at admission were excluded. Data were analyzed between August 28, 2019, and May 8, 2022.

EXPOSURES

Clinical and laboratory variables in the EHR.

MAIN OUTCOMES AND MEASURES

The main outcome was AKI of any severity, and AKI was defined using the Kidney Disease: Improving Global Outcomes serum creatinine criteria. Performance of the models was measured with area under the receiver operating characteristic curve (AUROC), area under the precision-recall curve, and calibration.

RESULTS

The study cohort comprised 76 957 inpatient encounters. Patients had a mean (SD) age of 55.5 (17.4) years and included 42 159 men (54.8%). The personalized model with transfer learning outperformed the global model for AKI estimation in terms of AUROC among general inpatients (0.78 [95% CI, 0.77-0.79] vs 0.76 [95% CI, 0.75-0.76]; P < .001) and across the high-risk subgroups (0.79 [95% CI, 0.78-0.80] vs 0.75 [95% CI, 0.74-0.77]; P < .001) and low-risk subgroups (0.74 [95% CI, 0.73-0.75] vs 0.71 [95% CI, 0.70-0.72]; P < .001). The AUROC improvement reached 0.13 for the high-risk subgroups, such as those undergoing liver transplant and cardiac surgery. Moreover, the personalized model with transfer learning performed better than or comparably with the best published models in well-studied AKI subgroups. Predictor outcomes varied significantly between patients, and interaction analysis uncovered modifiers of the predictor outcomes.

CONCLUSIONS AND RELEVANCE

Results of this study demonstrated that a personalized modeling with transfer learning is an improved AKI risk estimation approach that can be used across diverse patient subgroups. Risk factor heterogeneity and interactions at the individual level highlighted the need for agile, personalized care.

Predicting Lapatinib Dose Regimen Using Machine Learning and Deep Learning Techniques Based on a Real-World Study

Lapatinib is used for the treatment of metastatic HER2(+) breast cancer. We aim to establish a prediction model for lapatinib dose using machine learning and deep learning techniques based on a real-world study. There were 149 breast cancer patients enrolled from July 2016 to June 2017 at Fudan University Shanghai Cancer Center. The sequential forward selection algorithm based on random forest was applied for variable selection. Twelve machine learning and deep learning algorithms were compared in terms of their predictive abilities (logistic regression, SVM, random forest, Adaboost, XGBoost, GBDT, LightGBM, CatBoost, TabNet, ANN, Super TML, and Wide&Deep). As a result, TabNet was chosen to construct the prediction model with the best performance (accuracy = 0.82 and AUC = 0.83). Afterward, four variables that strongly correlated with lapatinib dose were ranked via importance score as follows: treatment protocols, weight, number of chemotherapy treatments, and number of metastases. Finally, the confusion matrix was used to validate the model for a dose regimen of 1,250 mg lapatinib (precision = 81% and recall = 95%), and for a dose regimen of 1,000 mg lapatinib (precision = 87% and recall = 64%). To conclude, we established a deep learning model to predict lapatinib dose based on important influencing variables selected from real-world evidence, to achieve an optimal individualized dose regimen with good predictive performance.

A Prediction Model for Tacrolimus Daily Dose in Kidney Transplant Recipients With Machine Learning and Deep Learning Techniques

Tacrolimus is a major immunosuppressor against post-transplant rejection in kidney transplant recipients. However, the narrow therapeutic index of tacrolimus and considerable variability among individuals are challenges for therapeutic outcomes. The aim of this study was to compare different machine learning and deep learning algorithms and establish individualized dose prediction models by using the best performing algorithm. Therefore, among the 10 commonly used algorithms we compared, the TabNet algorithm outperformed other algorithms with the highest R² (0.824), the lowest prediction error [mean absolute error (MAE) 0.468, mean square error (MSE) 0.558, and root mean square error (RMSE) 0.745], and good performance of overestimated (5.29%) or underestimated dose percentage (8.52%). In the final prediction model, the last tacrolimus daily dose, the last tacrolimus therapeutic drug monitoring value, time after transplantation, hematocrit, serum creatinine, aspartate aminotransferase, weight, CYP3A5, body mass index, and uric acid were the most influential variables on tacrolimus daily dose. Our study provides a reference for the application of deep learning technique in tacrolimus dose estimation, and the TabNet model with desirable predictive performance is expected to be expanded and applied in future clinical practice.

Integration of feature vectors from raw laboratory, medication and procedure names improves the precision and recall of models to predict postoperative mortality and acute kidney injury

Manuscripts that have successfully used machine learning (ML) to predict a variety of perioperative outcomes often use only a limited number of features selected by a clinician. We hypothesized that techniques leveraging a broad set of features for patient laboratory results, medications, and the surgical procedure name would improve performance as compared to a more limited set of features chosen by clinicians. Feature vectors for laboratory results included 702 features total derived from 39 laboratory tests, medications consisted of a binary flag for 126 commonly used medications, procedure name used the Word2Vec package for create a vector of length 100. Nine models were trained: baseline features, one for each of the three types of data Baseline + Each data type, (all features, and then all features with feature reduction algorithm. Across both outcomes the models that contained all features (model 8) (Mortality ROC-AUC 94.32 ± 1.01, PR-AUC 36.80 ± 5.10 AKI ROC-AUC 92.45 ± 0.64, PR-AUC 76.22 ± 1.95) was superior to models with only subsets of features. Featurization techniques leveraging a broad away of clinical data can improve performance of perioperative prediction models.

Application of machine learning in liver transplantation: a review

BACKGROUND

Machine learning (ML) has been increasingly applied in the health-care and liver transplant setting. The demand for liver transplantation continues to expand on an international scale, and with advanced aging and complex comorbidities, many challenges throughout the transplantation decision-making process must be better addressed. There exist massive datasets with hidden, non-linear relationships between demographic, clinical, laboratory, genetic, and imaging parameters that conventional methods fail to capitalize on when reviewing their predictive potential. Pre-transplant challenges include addressing efficacies of liver segmentation, hepatic steatosis assessment, and graft allocation. Post-transplant applications include predicting patient survival, graft rejection and failure, and post-operative morbidity risk.

AIM

In this review, we describe a comprehensive summary of ML applications in liver transplantation including the clinical context and how to overcome challenges for clinical implementation.

METHODS

Twenty-nine articles were identified from Ovid MEDLINE, MEDLINE Epub Ahead of Print and In-Process and Other Non-Indexed Citations, Embase, Cochrane Database of Systematic Reviews, and Cochrane Central Register of Controlled Trials.

CONCLUSION

ML is vastly interrogated in liver transplantation with promising applications in pre- and post-transplant settings. Although challenges exist including site-specific training requirements, the demand for more multi-center studies, and optimization hurdles for clinical interpretability, the powerful potential of ML merits further exploration to enhance patient care.

Machine learning-based system for prediction of ascites grades in patients with liver cirrhosis using laboratory and clinical data: design and implementation study

OBJECTIVES

The aim of the study was to implement a non-invasive model to predict ascites grades among patients with cirrhosis.

METHODS

In the present study, we used modern machine learning (ML) methods to develop a scoring system solely based on routine laboratory and clinical data to help physicians accurately diagnose and predict different degrees of ascites. We used ANACONDA3-5.2.0 64 bit, free and open-source platform distribution of Python programming language with numerous modules, packages, and rich libraries that provide various methods for classification problems. Through the 10-fold cross-validation, we employed three common learning models on our dataset, k-nearest neighbors (KNN), support vector machine (SVM), and neural network classification algorithms.

RESULTS

According to the data received from the research institute, three types of data analysis have been performed. The algorithms used to predict ascites were KNN, cross-validation (CV), and multilayer perceptron neural networks (MLPNN), which achieved an average accuracy of 94, 91, and 90%, respectively. Also, in the average accuracy of the algorithms, KNN had the highest accuracy of 94%.

CONCLUSIONS

We applied well-known ML approaches to predict ascites. The findings showed a strong performance compared to the classical statistical approaches. This ML-based approach can help to avoid unnecessary risks and costs for patients with acute stages of the disease.

Machine Learning-Based Evaluation on Craniodentofacial Morphological Harmony of Patients After Orthodontic Treatment

Objectives: Machine learning is increasingly being used in the medical field. Based on machine learning models, the present study aims to improve the prediction performance of craniodentofacial morphological harmony judgment after orthodontic treatment and to determine the most significant factors.

Methods: A dataset of 180 subjects was randomly selected from a large sample of 3,706 finished orthodontic cases from six top orthodontic treatment centers around China. Thirteen algorithms were used to predict the value of the cephalometric morphological harmony score of each subject and to search for the optimal model. Based on the feature importance ranking and by removing features, the regression models of machine learning (including the Adaboost, ExtraTree, XGBoost, and linear regression models) were used to predict and compare the score of harmony for each subject from the dataset with cross validations. By analyzing the prediction values, the most optimal model and the most significant cephalometric characteristics were determined.

Results: When nine features were included, the performance of the XGBoost regression model was MAE = 0.267, RMSE = 0.341, and Pearson correlation coefficient = 0.683, which indicated that the XGBoost regression model exhibited the best fitting and predicting performance for craniodentofacial morphological harmony judgment. Nine cephalometric features including L1/NB (inclination of the lower central incisors), ANB (sagittal position between the maxilla and mandible), LL-EP (distance from the point of the prominence of the lower lip to the aesthetic plane), SN/OP (inclination of the occlusal plane), SNB (sagittal position of the mandible in relation to the cranial base), U1/SN (inclination of the upper incisors to the cranial base), L1-NB (protrusion of the lower central incisors), Ns-Prn-Pos (nasal protrusion), and U1/L1 (relationship between the protrusions of the upper and lower central incisors) were revealed to significantly influence the judgment.

Conclusion: The application of the XGBoost regression model enhanced the predictive ability regarding the craniodentofacial morphological harmony evaluation by experts after orthodontic treatment. Teeth position, teeth alignment, jaw position, and soft tissue morphology would be the most significant factors influencing the judgment. The methodology also provided guidance for the application of machine learning models to resolve medical problems characterized by limited sample size.

Machine learning-based modeling of acute respiratory failure following emergency general surgery operations

Background

Emergency general surgery (EGS) operations are associated with substantial risk of morbidity including postoperative respiratory failure (PRF). While existing risk models are not widely utilized and rely on traditional statistical methods, application of machine learning (ML) in prediction of PRF following EGS remains unexplored.

Objective

The present study aimed to develop ML-based prediction models for respiratory failure following EGS and compare their performance to traditional regression models using a nationally-representative cohort.

Methods

Non-elective hospitalizations for EGS (appendectomy, cholecystectomy, repair of perforated ulcer, large or small bowel resection, lysis of adhesions) were identified in the 2016–18 Nationwide Readmissions Database. Factors associated with PRF were identified using ML techniques and logistic regression. The performance of XGBoost and logistic regression was evaluated using the receiver operating characteristic curve and coefficient of determination (R²). The impact of PRF on mortality, length of stay (LOS) and hospitalization costs was secondarily assessed using generalized linear models.

Results

Of 1,003,703 hospitalizations, 8.8% developed PRF. The XGBoost model exhibited slightly superior discrimination compared to logistic regression (0.900, 95% CI 0.899–0.901 vs 0.894, 95% CI 0.862–0.896). Compared to logistic regression, XGBoost demonstrated excellent calibration across all risk levels (R²: 0.998 vs 0.962). Congestive heart failure, neurologic disorders, and coagulopathy were significantly associated with increased risk of PRF. After risk-adjustment, PRF was associated with 10-fold greater odds (95% confidence interval (CI) 9.8–11.1) of mortality and incremental increases in LOS by 3.1 days (95% CI 3.0–3.2) and $11,900 (95% CI 11,600–12,300) in costs.

Conclusions

Logistic regression and XGBoost perform similarly in overall classification of PRF risk. However, due to superior calibration at extremes of risk, ML-based models may prove more useful in the clinical setting, where probabilities rather than classifications are desired.

Flap failure prediction in microvascular tissue reconstruction using machine learning algorithms

BACKGROUND

Microvascular tissue reconstruction is a well-established, commonly used technique for a wide variety of the tissue defects. However, flap failure is associated with an additional hospital stay, medical cost burden, and mental stress. Therefore, understanding of the risk factors associated with this event is of utmost importance.

AIM

To develop machine learning-based predictive models for flap failure to identify the potential factors and screen out high-risk patients.

METHODS

Using the data set of 946 consecutive patients, who underwent microvascular tissue reconstruction of free flap reconstruction for head and neck, breast, back, and extremity, we established three machine learning models including random forest classifier, support vector machine, and gradient boosting. Model performances were evaluated by the indicators such as area under the curve of receiver operating characteristic curve, accuracy, precision, recall, and F1 score. A multivariable regression analysis was performed for the most critical variables in the random forest model.

RESULTS

Post-surgery, the flap failure event occurred in 34 patients (3.6%). The machine learning models based on various preoperative and intraoperative variables were successfully developed. Among them, the random forest classifier reached the best performance in receiver operating characteristic curve, with an area under the curve score of 0.770 in the test set. The top 10 variables in the random forest were age, body mass index, ischemia time, smoking, diabetes, experience, prior chemotherapy, hypertension, insulin, and obesity. Interestingly, only age, body mass index, and ischemic time were statistically associated with the outcomes.

CONCLUSION

Machine learning-based algorithms, especially the random forest classifier, were very important in categorizing patients at high risk of flap failure. The occurrence of flap failure was a multifactor-driven event and was identified with numerous factors that warrant further investigation. Importantly, the successful application of machine learning models may help the clinician in decision-making, understanding the underlying pathologic mechanisms of the disease, and improving the long-term outcome of patients.

Artificial intelligence in perioperative medicine - a narrative review

Recent advancements in artificial intelligence (AI) techniques have enabled the development of accurate prediction models using clinical big data. AI models for perioperative risk stratification, intraoperative event prediction, biosignal analyses, and intensive care medicine have been developed in the field of perioperative medicine. Some of these models have been validated using external datasets and randomized controlled trials. Once these models are implemented in electronic health record systems or software medical devices, they could help anesthesiologists improve clinical outcomes by accurately predicting complications and suggesting optimal treatment strategies in real-time. This review provides an overview of the AI techniques used in perioperative medicine and a summary of the studies that have been published using these techniques. Understanding these techniques will aid in their appropriate application in clinical practice.

Risk factors and prediction of acute kidney injury after liver transplantation: Logistic regression and artificial neural network approaches

BACKGROUND

Acute kidney injury (AKI) has serious consequences on the prognosis of patients undergoing liver transplantation. Recently, artificial neural network (ANN) was reported to have better predictive ability than the classical logistic regression (LR) for this postoperative outcome.

AIM

To identify the risk factors of AKI after deceased-donor liver transplantation (DDLT) and compare the prediction performance of ANN with that of LR for this complication.

METHODS

Adult patients with no evidence of end-stage kidney dysfunction (KD) who underwent the first DDLT according to model for end-stage liver disease (MELD) score allocation system was evaluated. AKI was defined according to the International Club of Ascites criteria, and potential predictors of postoperative AKI were identified by LR. The prediction performance of both ANN and LR was tested.

RESULTS

The incidence of AKI was 60.6% (n = 88/145) and the following predictors were identified by LR: MELD score > 25 (odds ratio [OR] = 1.999), preoperative kidney dysfunction (OR = 1.279), extended criteria donors (OR = 1.191), intraoperative arterial hypotension (OR = 1.935), intraoperative massive blood transfusion (MBT) (OR = 1.830), and postoperative serum lactate (SL) (OR = 2.001). The area under the receiver-operating characteristic curve was best for ANN (0.81, 95% confidence interval [CI]: 0.75-0.83) than for LR (0.71, 95%CI: 0.67-0.76). The root-mean-square error and mean absolute error in the ANN model were 0.47 and 0.38, respectively.

CONCLUSION

The severity of liver disease, pre-existing kidney dysfunction, marginal grafts, hemodynamic instability, MBT, and SL are predictors of postoperative AKI, and ANN has better prediction performance than LR in this scenario.