No full-text available
To read the full-text of this research,
you can request a copy directly from the authors.
Development of an artificial intelligence model to predict survival at specific time intervals for lung cancer patients.
Abstract
6556
Background: Survival prediction models for lung cancer patients could help guide their care and therapy decisions. The objectives of this study were to predict probability of survival beyond 90, 180 and 360 days from any point in a lung cancer patient’s journey. Methods: We developed a Gradient Boosting model (XGBoost) using data from 55k lung cancer patients in the ASCO CancerLinQ database that used 3958 unique variables including Dx and Rx codes, biomarkers, surgeries and lab tests from ≤1 year prior to the prediction point, which was chosen at random for each patient. We used 40% data for training, 25% for hyper-parameter tuning, 20% for testing and 15% for holdout validation. Death date available in the Electronic Health Record was cross checked by linkage to death registries. Results: The model was validated on the holdout set of 8,468 patients. The Area Under the Curve (AUC) for the model was 0.79. The precision and recall for predicting survival beyond the three time points were between 0.7-0.8 and 0.8-0.9 respectively (see table). This compares favourably to other lung cancer survival models created using different machine learning techniques (Jochems 2017, Dekker 2009). A Cox-PH model created using the top 20 variables also had a significantly lower performance (see table). Analysis of input variables yielded distinctive patterns for patient subgroups and time points. Tumor status, medications, lab values and functional status were found to be significant in patient sub cohorts. Conclusions: An AI model to predict survival of lung cancer patients built using a large real world dataset yielded high accuracy. This general model can further be used to predict survival of sub cohorts stratified by variables such as stage or various treatment effects. Such a model could be useful for assessing patient risk and treatment options, evaluating cost and quality of care or determining clinical trial eligibility. [Table: see text]
... Novel analytic techniques can bring together diverse data types to expand novel insights gained from RWE. Enrichments of high-quality data coupled with machine learning can help find areas of therapeutic need, enhance clinical trial interpretation, and even identify novel targets. For example, artificial intelligence (AI) applied to >50 000 lung cancer cases from the American Society of Clinical Oncology (ASCO) CancerLinQ database was used to predict survival through 360 days of follow up [11]. Molecular medicine is a critical component in advancing cancer patient care. ...
Resourcing real-world evidence (RWE) is becoming an increasingly important asset in developing novel therapies for cancer. In this article, an overview of the benefits and challenges of using these data is provided. Through several case examples we highlight future applications and potential.
... Informatics 2020, 7, 25 2 of 18 and colleagues [19], this "prediction technology" is core to the anticipated applications of artificial intelligence (AI) for improving health care. ...
Predictive analytics using electronic health record (EHR) data have rapidly advanced over the last decade. While model performance metrics have improved considerably, best practices for implementing predictive models into clinical settings for point-of-care risk stratification are still evolving. Here, we conducted a systematic review of articles describing predictive models integrated into EHR systems and implemented in clinical practice. We conducted an exhaustive database search and extracted data encompassing multiple facets of implementation. We assessed study quality and level of evidence. We obtained an initial 3393 articles for screening, from which a final set of 44 articles was included for data extraction and analysis. The most common clinical domains of implemented predictive models were related to thrombotic disorders/anticoagulation (25%) and sepsis (16%). The majority of studies were conducted in inpatient academic settings. Implementation challenges included alert fatigue, lack of training, and increased work burden on the care team. Of 32 studies that reported effects on clinical outcomes, 22 (69%) demonstrated improvement after model implementation. Overall, EHR-based predictive models offer promising results for improving clinical outcomes, although several gaps in the literature remain, and most study designs were observational. Future studies using randomized controlled trials may help improve the generalizability of findings.
ResearchGate has not been able to resolve any references for this publication.