Dataset Information

An interpretable boosting model to predict side effects of analgesics for osteoarthritis.

ABSTRACT: BACKGROUND:Osteoarthritis (OA) is the most common disease of arthritis. Analgesics are widely used in the treat of arthritis, which may increase the risk of cardiovascular diseases by 20% to 50% overall.There are few studies on the side effects of OA medication, especially the risk prediction models on side effects of analgesics. In addition, most prediction models do not provide clinically useful interpretable rules to explain the reasoning process behind their predictions. In order to assist OA patients, we use the eXtreme Gradient Boosting (XGBoost) method to balance the accuracy and interpretability of the prediction model. RESULTS:In this study we used the XGBoost model as a classifier, which is a supervised machine learning method and can predict side effects of analgesics for OA patients and identify high-risk features (RFs) of cardiovascular diseases caused by analgesics. The Electronic Medical Records (EMRs), which were derived from public knee OA studies, were used to train the model. The performance of the XGBoost model is superior to four well-known machine learning algorithms and identifies the risk features from the biomedical literature. In addition the model can provide decision support for using analgesics in OA patients. CONCLUSION:Compared with other machine learning methods, we used XGBoost method to predict side effects of analgesics for OA patients from EMRs, and selected the individual informative RFs. The model has good predictability and interpretability, this is valuable for both medical researchers and patients.

SUBMITTER: Liu L

PROVIDER: S-EPMC6249730 | biostudies-other | 2018 Nov

REPOSITORIES: biostudies-other

ACCESS DATA

Publications

An interpretable boosting model to predict side effects of analgesics for osteoarthritis.

Liu Liangliang L Yu Ying Y Fei Zhihui Z Li Min M Wu Fang-Xiang FX Li Hong-Dong HD Pan Yi Y Wang Jianxin J

BMC systems biology 20181122 Suppl 6

<h4>Background</h4>Osteoarthritis (OA) is the most common disease of arthritis. Analgesics are widely used in the treat of arthritis, which may increase the risk of cardiovascular diseases by 20% to 50% overall.There are few studies on the side effects of OA medication, especially the risk prediction models on side effects of analgesics. In addition, most prediction models do not provide clinically useful interpretable rules to explain the reasoning process behind their predictions. In order to ...[more]

PMID: 30463545

Similar Datasets

Project description:BackgroundIntensive care unit (ICU) readmissions are associated with mortality and poor outcomes. To improve discharge decisions, machine learning (ML) could help to identify patients at risk of ICU readmission. However, as many models are black boxes, dangerous properties may remain unnoticed. Widely used post hoc explanation methods also have inherent limitations. Few studies are evaluating inherently interpretable ML models for health care and involve clinicians in inspecting the trained model.MethodsAn inherently interpretable model for the prediction of 3 day ICU readmission was developed. We used explainable boosting machines that learn modular risk functions and which have already been shown to be suitable for the health care domain. We created a retrospective cohort of 15,589 ICU stays and 169 variables collected between 2006 and 2019 from the University Hospital Münster. A team of physicians inspected the model, checked the plausibility of each risk function, and removed problematic ones. We collected qualitative feedback during this process and analyzed the reasons for removing risk functions. The performance of the final explainable boosting machine was compared with a validated clinical score and three commonly used ML models. External validation was performed on the widely used Medical Information Mart for Intensive Care version IV database.ResultsThe developed explainable boosting machine used 67 features and showed an area under the precision-recall curve of 0.119 ± 0.020 and an area under the receiver operating characteristic curve of 0.680 ± 0.025. It performed on par with state-of-the-art gradient boosting machines (0.123 ± 0.016, 0.665 ± 0.036) and outperformed the Simplified Acute Physiology Score II (0.084 ± 0.025, 0.607 ± 0.019), logistic regression (0.092 ± 0.026, 0.587 ± 0.016), and recurrent neural networks (0.095 ± 0.008, 0.594 ± 0.027). External validation confirmed that explainable boosting machines (0.221 ± 0.023, 0.760 ± 0.010) performed similarly to gradient boosting machines (0.232 ± 0.029, 0.772 ± 0.018). Evaluation of the model inspection showed that explainable boosting machines can be useful to detect and remove problematic risk functions.ConclusionsWe developed an inherently interpretable ML model for 3 day ICU readmission prediction that reached the state-of-the-art performance of black box models. Our results suggest that for low- to medium-dimensional datasets that are common in health care, it is feasible to develop ML models that allow a high level of human control without sacrificing performance.

Project description:BACKGROUND:Excessive or prolonged usage of dexamethasone can cause serious side effects, but few studies reveal the related mechanism. Dexamethasone work differently in blood tumors and solid tumors, and the cause is still obscure. The aims of this study was to identify potential biomarkers associated with the side effects of dexamethasone in different tumors. METHODS:Gene Expression Omnibus database (GEO) datasets of blood tumors and solid tumors were retrieval to selected microarray data. The differentially expressed genes (DEGs) were identified. Gene ontology (GO) and pathway enrichment analyses, and protein-protein interaction (PPI) network analysis were performed. RESULTS:One hundred and eighty dexamethasone-specific DEGs (92 up and 88 downregulated) were obtained in lymphoma cell samples (named as DEGs-lymph), including APOD, TP53INP1, CLIC3, SERPINA9, and C3orf52. One hundred and four specific DEGs (100 up and 4 downregulated) were identified in prostate cancer cell samples (named as DEGs-prostate), including COL6A2, OSBPL5, OLAH, OGFRL1, and SLC39A14. The significantly enriched GO terms of DEGs-lymph contained cellular amino acid metabolic process and cell cycle. The most significantly enriched pathway of DEGs-lymph was cytosolic tRNA aminoacylation. The DEGs-prostate was enriched in 39 GO terms and two pathways, and the pathways were PPARA activates gene expression Homo sapiens, and insulin resistance. The PPI network of DEGs-lymph gathered into two major clusters, WARS1 and CDC25A were representatives for them, respectively. One cluster was mainly involved in cytosolic tRNA aminoacylation, aminoacyl-tRNA biosynthesis and the function of amino acid metabolism; another was associated with cell cycle and cell apoptosis. As for the PPI network of DEGs-prostate, HELZ2 was the top nodes involved in the most protein-protein pairs, which was related to the pathway of "PPARA activates gene expression Homo sapiens." CONCLUSIONS:WARS1 and CDC25A might be potential biomarkers for side effects of dexamethasone in lymphoma, and HELZ2 in prostate cancer.

Dataset Information

An interpretable boosting model to predict side effects of analgesics for osteoarthritis.

Publications

An interpretable boosting model to predict side effects of analgesics for osteoarthritis.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets