Machine learning for predicting long-term kidney allograft survival: a scoping review

Predicting kidney graft function and failure among kidney transplant recipients

BACKGROUND

Graft loss is a major health concern for kidney transplant (KTx) recipients. It is of clinical interest to develop a prognostic model for both graft function, quantified by estimated glomerular filtration rate (eGFR), and the risk of graft failure. Additionally, the model should be dynamic in the sense that it adapts to accumulating longitudinal information, including time-varying at-risk population, predictor-outcome association, and clinical history. Finally, the model should also properly account for the competing risk by death with a functioning graft. A model with the features above is not yet available in the literature and is the focus of this research.

METHODS

We built and internally validated a prediction model on 3,893 patients from the Wisconsin Allograft Recipient Database (WisARD) who had a functioning graft 6 months after kidney transplantation. The landmark analysis approach was used to build a proof-of-concept dynamic prediction model to address the aforementioned methodological issues: the prediction of graft failure, accounted for competing risk of death, as well as the future eGFR value, are updated at each post-transplant time. We used 21 predictors including recipient characteristics, donor characteristics, transplant-related and post-transplant factors, longitudinal eGFR, hospitalization, and rejection history. A sensitivity analysis explored a less conservative variable selection rule that resulted in a more parsimonious model with reduced predictors.

RESULTS

For prediction up to the next 1 to 5 years, the model achieved high accuracy in predicting graft failure, with the AUC between 0.80 and 0.95, and moderately high accuracy in predicting eGFR, with the root mean squared error between 10 and 18 mL/min/1.73m2 and 70%-90% of predicted eGFR falling within 30% of the observed eGFR. The model demonstrated substantial accuracy improvement compared to a conventional prediction model that used only baseline predictors.

CONCLUSION

The model outperformed conventional prediction model that used only baseline predictors. It is a useful tool for patient counseling and clinical management of KTx and is currently available as a web app.

Establishing a differential diagnosis model between primary membranous nephropathy and non-primary membranous nephropathy by machine learning algorithms

CONTEXT

Four algorithms with relatively balanced complexity and accuracy in deep learning classification algorithm were selected for differential diagnosis of primary membranous nephropathy (PMN).

OBJECTIVE

This study explored the most suitable classification algorithm for PMN identification, and to provide data reference for PMN diagnosis research.

METHODS

A total of 500 patients were referred to Luo-he Central Hospital from 2019 to 2021. All patients were diagnosed with primary glomerular disease confirmed by renal biopsy, contained 322 cases of PMN, the 178 cases of non-PMN. Using the decision tree, random forest, support vector machine, and extreme gradient boosting (Xgboost) to establish a differential diagnosis model for PMN and non-PMN. Based on the true positive rate, true negative rate, false-positive rate, false-negative rate, accuracy, feature work area under the curve (AUC) of subjects, the best performance of the model was chosen.

RESULTS

The efficiency of the Xgboost model based on the above evaluation indicators was the highest, which the diagnosis of PMN of the sensitivity and specificity, respectively 92% and 96%.

CONCLUSIONS

The differential diagnosis model for PMN was established successfully and the efficiency performance of the Xgboost model was the best. It could be used for the clinical diagnosis of PMN.

Table 2 Fallacy in Descriptive Epidemiology: Bringing Machine Learning to the Table

There is a lack of rigorous methodological development for descriptive epidemiology, where the goal is to describe and identify the most important associations with an outcome given a large set of potential predictors. This has often led to the Table 2 fallacy, where one presents the coefficient estimates for all covariates from a single multivariable regression model, which are often uninterpretable in a descriptive analysis. We argue that machine learning (ML) is a potential solution to this problem. We illustrate the power of ML with an example analysis identifying the most important predictors of alcohol abuse among sexual minority youth. The framework we propose for this analysis is as follows: (1) Identify a few ML methods for the analysis, (2) optimize the parameters using the whole data with a nested cross-validation approach, (3) rank the variables using variable importance scores, (4) present partial dependence plots (PDP) to illustrate the association between the important variables and the outcome, (5) and identify the strength of the interaction terms using the PDPs. We discuss the potential strengths and weaknesses of using ML methods for descriptive analysis and future directions for research. R codes to reproduce these analyses are provided, which we invite other researchers to use.

A Machine Learning Approach Reveals Distinct Predictors of Vaping Dependence for Adolescent Daily and Non-Daily Vapers in the COVID-19 Era

Since 2016, there has been a substantial rise in e-cigarette (vaping) dependence among young people. In this prospective cohort study, we aimed to identify the different predictors of vaping dependence over 3 months among adolescents who were baseline daily and non-daily vapers. We recruited ever-vaping Canadian residents aged 16-25 years on social media platforms and asked them to complete a baseline survey in November 2020. A validated vaping dependence score (0-23) summing up their responses to nine questions was calculated at the 3-month follow-up survey. Separate lasso regression models were developed to identify predictors of higher 3-month vaping dependence score among baseline daily and non-daily vapers. Of the 1172 participants, 643 (54.9%) were daily vapers with a mean age of 19.6 ± 2.6 years and 76.4% (n = 895) of them being female. The two models achieved adequate predictive performance. Place of last vape purchase, number of days a pod lasts, and the frequency of nicotine-containing vaping were the most important predictors for dependence among daily vapers, while race, sexual orientation and reporting treatment for heart disease were the most important predictors in non-daily vapers. These findings have implications for vaping control policies that target adolescents at different stages of vape use.

Machine learning does not outperform traditional statistical modelling for kidney allograft failure prediction

Machine learning (ML) models have recently shown potential for predicting kidney allograft outcomes. However, their ability to outperform traditional approaches remains poorly investigated. Therefore, using large cohorts of kidney transplant recipients from 14 centers worldwide, we developed ML-based prediction models for kidney allograft survival and compared their prediction performances to those achieved by a validated Cox-Based Prognostication System (CBPS). In a French derivation cohort of 4000 patients, candidate determinants of allograft failure including donor, recipient and transplant-related parameters were used as predictors to develop tree-based models (RSF, RSF-ERT, CIF), Support Vector Machine models (LK-SVM, AK-SVM) and a gradient boosting model (XGBoost). Models were externally validated with cohorts of 2214 patients from Europe, 1537 from North America, and 671 from South America. Among these 8422 kidney transplant recipients, 1081 (12.84%) lost their grafts after a median post-transplant follow-up time of 6.25 years (Inter Quartile Range 4.33-8.73). At seven years post-risk evaluation, the ML models achieved a C-index of 0.788 (95% bootstrap percentile confidence interval 0.736-0.833), 0.779 (0.724-0.825), 0.786 (0.735-0.832), 0.527 (0.456-0.602), 0.704 (0.648-0.759) and 0.767 (0.711-0.815) for RSF, RSF-ERT, CIF, LK-SVM, AK-SVM and XGBoost respectively, compared with 0.808 (0.792-0.829) for the CBPS. In validation cohorts, ML models' discrimination performances were in a similar range of those of the CBPS. Calibrations of the ML models were similar or less accurate than those of the CBPS. Thus, when using a transparent methodological pipeline in validated international cohorts, ML models, despite overall good performances, do not outperform a traditional CBPS in predicting kidney allograft failure. Hence, our current study supports the continued use of traditional statistical approaches for kidney graft prognostication.

Machine learning applications in tobacco research: a scoping review

OBJECTIVE

Identify and review the body of tobacco research literature that self-identified as using machine learning (ML) in the analysis.

DATA SOURCES

MEDLINE, EMABSE, PubMed, CINAHL Plus, APA PsycINFO and IEEE Xplore databases were searched up to September 2020. Studies were restricted to peer-reviewed, English-language journal articles, dissertations and conference papers comprising an empirical analysis where ML was identified to be the method used to examine human experience of tobacco. Studies of genomics and diagnostic imaging were excluded.

STUDY SELECTION

Two reviewers independently screened the titles and abstracts. The reference list of articles was also searched. In an iterative process, eligible studies were classified into domains based on their objectives and types of data used in the analysis.

DATA EXTRACTION

Using data charting forms, two reviewers independently extracted data from all studies. A narrative synthesis method was used to describe findings from each domain such as study design, objective, ML classes/algorithms, knowledge users and the presence of a data sharing statement. Trends of publication were visually depicted.

DATA SYNTHESIS

74 studies were grouped into four domains: ML-powered technology to assist smoking cessation (n=22); content analysis of tobacco on social media (n=32); smoker status classification from narrative clinical texts (n=6) and tobacco-related outcome prediction using administrative, survey or clinical trial data (n=14). Implications of these studies and future directions for ML researchers in tobacco control were discussed.

CONCLUSIONS

ML represents a powerful tool that could advance the research and policy decision-making of tobacco control. Further opportunities should be explored.

Toward generalizing the use of artificial intelligence in nephrology and kidney transplantation

With its robust ability to integrate and learn from large sets of clinical data, artificial intelligence (AI) can now play a role in diagnosis, clinical decision making, and personalized medicine. It is probably the natural progression of traditional statistical techniques. Currently, there are many unmet needs in nephrology and, more particularly, in the kidney transplantation (KT) field. The complexity and increase in the amount of data, and the multitude of nephrology registries worldwide have enabled the explosive use of AI within the field. Nephrologists in many countries are already at the center of experiments and advances in this cutting-edge technology and our aim is to generalize the use of AI among nephrologists worldwide. In this paper, we provide an overview of AI from a medical perspective. We cover the core concepts of AI relevant to the practicing nephrologist in a consistent and simple way to help them get started, and we discuss the technical challenges. Finally, we focus on the KT field: the unmet needs and the potential role that AI can play to fill these gaps, then we summarize the published KT-related studies, including predictive factors used in each study, which will allow researchers to quickly focus on the most relevant issues.

Explainable machine learning framework for predicting long-term cardiovascular disease risk among adolescents

Although cardiovascular disease (CVD) is the leading cause of death worldwide, over 80% of it is preventable through early intervention and lifestyle changes. Most cases of CVD are detected in adulthood, but the risk factors leading to CVD begin at a younger age. This research is the first to develop an explainable machine learning (ML)-based framework for long-term CVD risk prediction (low vs. high) among adolescents. This study uses longitudinal data from a nationally representative sample of individuals who participated in the Add Health study. A total of 14,083 participants who completed relevant survey questionnaires and health tests from adolescence to young adulthood were chosen. Four ML classifiers [decision tree (DT), random forest (RF), extreme gradient boosting (XGBoost), and deep neural networks (DNN)] and 36 adolescent predictors are used to predict adulthood CVD risk. While all ML models demonstrated good prediction capability, XGBoost achieved the best performance (AUC-ROC: 84.5% and AUC-PR: 96.9% on testing data). Besides, critical predictors of long-term CVD risk and its impact on risk prediction are obtained using an explainable technique for interpreting ML predictions. The results suggest that ML can be employed to detect adulthood CVD very early in life, and such an approach may facilitate primordial prevention and personalized intervention.

Machine learning for optimized individual survival prediction in resectable upper gastrointestinal cancer

PURPOSE

Surgical oncologists are frequently confronted with the question of expected long-term prognosis. The aim of this study was to apply machine learning algorithms to optimize survival prediction after oncological resection of gastroesophageal cancers.

METHODS

Eligible patients underwent oncological resection of gastric or distal esophageal cancer between 2001 and 2020 at Heidelberg University Hospital, Department of General Surgery. Machine learning methods such as multi-task logistic regression and survival forests were compared with usual algorithms to establish an individual estimation.

RESULTS

The study included 117 variables with a total of 1360 patients. The overall missingness was 1.3%. Out of eight machine learning algorithms, the random survival forest (RSF) performed best with a concordance index of 0.736 and an integrated Brier score of 0.166. The RSF demonstrated a mean area under the curve (AUC) of 0.814 over a time period of 10 years after diagnosis. The most important long-term outcome predictor was lymph node ratio with a mean AUC of 0.730. A numeric risk score was calculated by the RSF for each patient and three risk groups were defined accordingly. Median survival time was 18.8 months in the high-risk group, 44.6 months in the medium-risk group and above 10 years in the low-risk group.

CONCLUSION

The results of this study suggest that RSF is most appropriate to accurately answer the question of long-term prognosis. Furthermore, we could establish a compact risk score model with 20 input parameters and thus provide a clinical tool to improve prediction of oncological outcome after upper gastrointestinal surgery.

Augmenting the Transplant Team With Artificial Intelligence: Toward Meaningful AI Use in Solid Organ Transplant

Advances in systems immunology, such as new biomarkers, offer the potential for highly personalized immunosuppression regimens that could improve patient outcomes. In the future, integrating all of this information with other patient history data will likely have to rely on artificial intelligence (AI). AI agents can help augment transplant decision making by discovering patterns and making predictions for specific patients that are not covered in the literature or in ways that are impossible for humans to anticipate by integrating vast amounts of data (e.g. trending across numerous biomarkers). Similar to other clinical decision support systems, AI may help overcome human biases or judgment errors. However, AI is not widely utilized in transplant to date. In this rapid review, we survey the methods employed in recent research in transplant-related AI applications and identify concerns related to implementing these tools. We identify three key challenges (bias/accuracy, clinical decision process/AI explainability, AI acceptability criteria) holding back AI in transplant. We also identify steps that can be taken in the near term to help advance meaningful use of AI in transplant (forming a Transplant AI Team at each center, establishing clinical and ethical acceptability criteria, and incorporating AI into the Shared Decision Making Model).

A machine learning approach to identify correlates of current e-cigarette use in Canada

Aim: Popularity of electronic cigarettes (i.e. e-cigarettes) is soaring in Canada. Understanding person-level correlates of current e-cigarette use (vaping) is crucial to guide tobacco policy, but prior studies have not fully identified these correlates due to model overfitting caused by multicollinearity. This study addressed this issue by using classification tree, a machine learning algorithm. Methods: This population-based cross-sectional study used the Canadian Tobacco, Alcohol, and Drugs Survey (CTADS) from 2017 that targeted residents aged 15 or older. Forty-six person-level characteristics were first screened in a logistic mixed-effects regression procedure for their strength in predicting vaper type (current vs. former vaper) among people who reported to have ever vaped. A 9:1 ratio was used to randomly split the data into a training set and a validation set. A classification tree model was developed using the cross-validation method on the training set using the selected predictors and assessed on the validation set using sensitivity, specificity and accuracy. Results: Of the 3,059 people with an experience of vaping, the average age was 24.4 years (standard deviation = 11.0), with 41.9% of them being female and 8.5% of them being aboriginal. There were 556 (18.2%) current vapers. The classification tree model performed relatively well and suggested attraction to e-cigarette flavors was the most important correlate of current vaping, followed by young age (< 18) and believing vaping to be less harmful to oneself than cigarette smoking. Conclusions: People who vape due to flavors are associated with very high risk of becoming current vapers. The findings of this study provide evidence that supports the ongoing ban on flavored vaping products in the US and suggests a similar regulatory intervention may be effective in Canada.