Figure - available from: BMC Medical Informatics and Decision Making
This content is subject to copyright. Terms and conditions apply.
Source publication
Background
The misestimation of surgical risk is a serious threat to the lives of patients when implementing surgical risk calculator. Improving the accuracy of postoperative risk prediction has received much attention and many methods have been proposed to cope with this problem in the past decades. However, those linear approaches are inable to c...
Similar publications
This paper proposes a novel framework for a Knowledge Based Intelligent Clinical Decision Support System for the prediction of prostate cancer which is one of the most deadly illnesses that has a deleterious effect on people afflicted with it and has for long remained a perennial health problem affecting a significant number of people the world ove...
Background
Recommendations for the diagnosis of pulmonary embolism are available for healthcare providers. Yet, real practice data show existing gaps in the translation of evidence-based recommendations. This is a study to assess the effect of a computerised decision support system (CDSS) with an enhanced design based on best practices in content a...
Background:
Artificial intelligence (AI) has developed rapidly, and its application extends to clinical decision support system (CDSS) for improving healthcare quality. However, the interpretability of AI-driven CDSS poses significant challenges to widespread application.
Objective:
This study is a review of the knowledge-based and data-based CD...
Building machine learning algorithms for real-time clinical decision support systems has become a current research hotspot. The success of these algorithms depends on their ability to handle data stream characteristics. For example, we cite as characteristics the large amounts of data, the high speed and rate of incoming data, and the change in dat...
Citations
Background
Studies have revealed that acute myeloid leukemia (AML) patients are prone to combined cardiac injury. We aimed to identify hematological risk factors associated with cardiac injury in newly diagnosed AML patients before chemotherapy and develop a personalized predictive model.
Methods
The population baseline, blood test, electrocardiogram, echocardiograph, and genetic and cytogenetic data were collected from newly diagnosed AML patients. The data were subdivided into training and validation cohorts. The independent risk factors were explored by univariate and multivariate logistic regression analysis respectively, and data dimension reduction and variable selection were performed using the least absolute shrinkage and selection operator (LASSO) regression models. The nomogram was generated and the reliability and generalizability were verified by receiver operating characteristic (ROC) curves, the area under the curve (AUC) and calibration curves in an external validation cohort.
Results
Finally, 499 AML patients were included. After univariate logistic regression, LASSO regression and multivariate logistic regression analysis, abnormal NT-proBNP, NPM1 mutation, WBC, and RBC were independent risk factors for cardiac injury in AML patients (all P < 0.05). The nomogram was constructed based on the above four variables with high accuracy. The area under the curve was 0.742, 0.750, and 0.706 in the training, internal validation, and external validation cohort, respectively. The calibration curve indicated that the model has good testing capability. The Kaplan-Meier curve showed that the higher the risk of combined cardiac injury in AML patients, the lower their probability of survival.
Conclusions
This prediction nomogram identifies hematological risk factors associated with cardiac injury in newly diagnosed AML patients and can help hematologists identify the risk and provide precise treatment options.
