Use of disease embedding technique to predict the risk of progression to end-stage renal disease

Artificial Intelligence to Predict Chronic Kidney Disease Progression to Kidney Failure: A Narrative Review

Chronic kidney disease is characterised by the progressive loss of kidney function. However, predicting who will progress to kidney failure is difficult. Artificial Intelligence, including Machine Learning, shows promise in this area. This narrative review highlights the most common and important variables used in machine learning models to predict progressive chronic kidney disease. Ovid Medline and EMBASE were searched in August 2023 with keywords relating to 'chronic kidney disease', 'machine learning', and 'end-stage renal disease'. Studies were assessed against inclusion and exclusion criteria and excluded if variables inputted into machine learning models were not discussed. Data extraction focused on specific variables inputted into the machine learning models. After screening of 595 articles, 16 were included in the review. The most utilised machine learning models were random forest, support vector machines and XGBoost. The most commonly occurring variables were age, gender, measures of renal function, measures of proteinuria, and full blood examination. Only half of all studies included clinical variables in their models. The most important variables overall were measures of renal function, measures of proteinuria, age, full blood examination and serum albumin. Machine learning was consistently superior or non-inferior when compared to the Kidney Failure Risk Equation. This review identified key variables used in machine learning models to predict chronic kidney disease progression to kidney failure. These findings lay the foundations for the development of future machine learning models capable of rivalling the Kidney Failure Risk Equation in the provision of accurate kidney failure prediction.

Representation of multimorbidity and frailty in the development and validation of kidney failure prognostic prediction models: a systematic review

BACKGROUND

Prognostic models that identify individuals with chronic kidney disease (CKD) at greatest risk of developing kidney failure help clinicians to make decisions and deliver precision medicine. It is recognised that people with CKD usually have multiple long-term health conditions (multimorbidity) and often experience frailty. We undertook a systematic review to evaluate the representation and consideration of multimorbidity and frailty within CKD cohorts used to develop and/or validate prognostic models assessing the risk of kidney failure.

METHODS

We identified studies that described derivation, validation or update of kidney failure prognostic models in MEDLINE, CINAHL Plus and the Cochrane Library-CENTRAL. The primary outcome was representation of multimorbidity or frailty. The secondary outcome was predictive accuracy of identified models in relation to presence of multimorbidity or frailty.

RESULTS

Ninety-seven studies reporting 121 different kidney failure prognostic models were identified. Two studies reported prevalence of multimorbidity and a single study reported prevalence of frailty. The rates of specific comorbidities were reported in a greater proportion of studies: 67.0% reported baseline data on diabetes, 54.6% reported hypertension and 39.2% reported cardiovascular disease. No studies included frailty in model development, and only one study considered multimorbidity as a predictor variable. No studies assessed model performance in populations in relation to multimorbidity. A single study assessed associations between frailty and the risks of kidney failure and death.

CONCLUSIONS

There is a paucity of kidney failure risk prediction models that consider the impact of multimorbidity and/or frailty, resulting in a lack of clear evidence-based practice for multimorbid or frail individuals. These knowledge gaps should be explored to help clinicians know whether these models can be used for CKD patients who experience multimorbidity and/or frailty.

SYSTEMATIC REVIEW REGISTRATION

This review has been registered on PROSPERO (CRD42022347295).

Causal knowledge graph construction and evaluation for clinical decision support of diabetic nephropathy

BACKGROUND

Many important clinical decisions require causal knowledge (CK) to take action. Although many causal knowledge bases for medicine have been constructed, a comprehensive evaluation based on real-world data and methods for handling potential knowledge noise are still lacking.

OBJECTIVE

The objectives of our study are threefold: (1) propose a framework for the construction of a large-scale and high-quality causal knowledge graph (CKG); (2) design the methods for knowledge noise reduction to improve the quality of the CKG; (3) evaluate the knowledge completeness and accuracy of the CKG using real-world data.

MATERIAL AND METHODS

We extracted causal triples from three knowledge sources (SemMedDB, UpToDate and Churchill's Pocketbook of Differential Diagnosis) based on rule methods and language models, performed ontological encoding, and then designed semantic modeling between electronic health record (EHR) data and the CKG to complete knowledge instantiation. We proposed two graph pruning strategies (co-occurrence ratio and causality ratio) to reduce the potential noise introduced by SemMedDB. Finally, the evaluation was carried out by taking the diagnostic decision support (DDS) of diabetic nephropathy (DN) as a real-world case. The data originated from a Chinese hospital EHR system from October 2010 to October 2020. The knowledge completeness and accuracy of the CKG were evaluated based on three state-of-the-art embedding methods (R-GCN, MHGRN and MedPath), the annotated clinical text and the expert review, respectively.

RESULTS

This graph included 153,289 concepts and 1,719,968 causal triples. A total of 1427 inpatient data were used for evaluation. Better results were achieved by combining three knowledge sources than using only SemMedDB (three models: area under the receiver operating characteristic curve (AUC): p < 0.01, F1: p < 0.01), and the graph covered 93.9 % of the causal relations between diseases and diagnostic evidence recorded in clinical text. Causal relations played a vital role in all relations related to disease progression for DDS of DN (three models: AUC: p > 0.05, F1: p > 0.05), and after pruning, the knowledge accuracy of the CKG was significantly improved (three models: AUC: p < 0.01, F1: p < 0.01; expert review: average accuracy: + 5.5 %).

CONCLUSIONS

The results demonstrated that our proposed CKG could completely and accurately capture the abstract CK under the concrete EHR data, and the pruning strategies could improve the knowledge accuracy of our CKG. The CKG has the potential to be applied to the DDS of diseases.

Machine learning approaches for electronic health records phenotyping: a methodical review

OBJECTIVE

Accurate and rapid phenotyping is a prerequisite to leveraging electronic health records for biomedical research. While early phenotyping relied on rule-based algorithms curated by experts, machine learning (ML) approaches have emerged as an alternative to improve scalability across phenotypes and healthcare settings. This study evaluates ML-based phenotyping with respect to (1) the data sources used, (2) the phenotypes considered, (3) the methods applied, and (4) the reporting and evaluation methods used.

MATERIALS AND METHODS

We searched PubMed and Web of Science for articles published between 2018 and 2022. After screening 850 articles, we recorded 37 variables on 100 studies.

RESULTS

Most studies utilized data from a single institution and included information in clinical notes. Although chronic conditions were most commonly considered, ML also enabled the characterization of nuanced phenotypes such as social determinants of health. Supervised deep learning was the most popular ML paradigm, while semi-supervised and weakly supervised learning were applied to expedite algorithm development and unsupervised learning to facilitate phenotype discovery. ML approaches did not uniformly outperform rule-based algorithms, but deep learning offered a marginal improvement over traditional ML for many conditions.

DISCUSSION

Despite the progress in ML-based phenotyping, most articles focused on binary phenotypes and few articles evaluated external validity or used multi-institution data. Study settings were infrequently reported and analytic code was rarely released.

CONCLUSION

Continued research in ML-based phenotyping is warranted, with emphasis on characterizing nuanced phenotypes, establishing reporting and evaluation standards, and developing methods to accommodate misclassified phenotypes due to algorithm errors in downstream applications.

Machine learning algorithms' accuracy in predicting kidney disease progression: a systematic review and meta-analysis

BACKGROUND

Kidney disease progression rates vary among patients. Rapid and accurate prediction of kidney disease outcomes is crucial for disease management. In recent years, various prediction models using Machine Learning (ML) algorithms have been established in nephrology. However, their accuracy have been inconsistent. Therefore, we conducted a systematic review and meta-analysis to investigate the diagnostic accuracy of ML algorithms for kidney disease progression.

METHODS

We searched PubMed, EMBASE, Cochrane Central Register of Controlled Trials, the Chinese Biomedicine Literature Database, Chinese National Knowledge Infrastructure, Wanfang Database, and the VIP Database for diagnostic studies on ML algorithms' accuracy in predicting kidney disease prognosis, from the establishment of these databases until October 2020. Two investigators independently evaluate study quality by QUADAS-2 tool and extracted data from single ML algorithm for data synthesis using the bivariate model and the hierarchical summary receiver operating characteristic (HSROC) model.

RESULTS

Fifteen studies were left after screening, only 6 studies were eligible for data synthesis. The sample size of these 6 studies was 12,534, and the kidney disease types could be divided into chronic kidney disease (CKD) and Immunoglobulin A Nephropathy, with 5 articles using end-stage renal diseases occurrence as the primary outcome. The main results indicated that the area under curve (AUC) of the HSROC was 0.87 (0.84-0.90) and ML algorithm exhibited a strong specificity, 95% confidence interval and heterogeneity (I2) of (0.87, 0.84-0.90, [I2 99.0%]) and a weak sensitivity of (0.68, 0.58-0.77, [I2 99.7%]) in predicting kidney disease deterioration. And the the results of subgroup analysis indicated that ML algorithm's AUC for predicting CKD prognosis was 0.82 (0.79-0.85), with the pool sensitivity of (0.64, 0.49-0.77, [I2 99.20%]) and pool specificity of (0.84, 0.74-0.91, [I2 99.84%]). The ML algorithm's AUC for predicting IgA nephropathy prognosis was 0.78 (0.74-0.81), with the pool sensitivity of (0.74, 0.71-0.77, [I2 7.10%]) and pool specificity of (0.93, 0.91-0.95, [I2 83.92%]).

CONCLUSION

Taking advantage of big data, ML algorithm-based prediction models have high accuracy in predicting kidney disease progression, we recommend ML algorithms as an auxiliary tool for clinicians to determine proper treatment and disease management strategies.

Prediction models used in the progression of chronic kidney disease: A scoping review

OBJECTIVE

To provide a review of prediction models that have been used to measure clinical or pathological progression of chronic kidney disease (CKD).

DESIGN

Scoping review.

DATA SOURCES

Medline, EMBASE, CINAHL and Scopus from the year 2011 to 17th February 2022.

STUDY SELECTION

All English written studies that are published in peer-reviewed journals in any country, that developed at least a statistical or computational model that predicted the risk of CKD progression.

DATA EXTRACTION

Eligible studies for full text review were assessed on the methods that were used to predict the progression of CKD. The type of information extracted included: the author(s), title of article, year of publication, study dates, study location, number of participants, study design, predicted outcomes, type of prediction model, prediction variables used, validation assessment, limitations and implications.

RESULTS

From 516 studies, 33 were included for full-text review. A qualitative analysis of the articles was compared following the extracted information. The study populations across the studies were heterogenous and data acquired by the studies were sourced from different levels and locations of healthcare systems. 31 studies implemented supervised models, and 2 studies included unsupervised models. Regardless of the model used, the predicted outcome included measurement of risk of progression towards end-stage kidney disease (ESKD) of related definitions, over given time intervals. However, there is a lack of reporting consistency on details of the development of their prediction models.

CONCLUSIONS

Researchers are working towards producing an effective model to provide key insights into the progression of CKD. This review found that cox regression modelling was predominantly used among the small number of studies in the review. This made it difficult to perform a comparison between ML algorithms, more so when different validation methods were used in different cohort types. There needs to be increased investment in a more consistent and reproducible approach for future studies looking to develop risk prediction models for CKD progression.