- Award ID(s):
- 1741340
- NSF-PAR ID:
- 10373935
- Editor(s):
- Li-Jessen, Nicole Yee-Key
- Date Published:
- Journal Name:
- PLOS Digital Health
- Volume:
- 1
- Issue:
- 8
- ISSN:
- 2767-3170
- Page Range / eLocation ID:
- e0000076
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
null (Ed.)Background Conventional diagnosis of COVID-19 with reverse transcription polymerase chain reaction (RT-PCR) testing (hereafter, PCR) is associated with prolonged time to diagnosis and significant costs to run the test. The SARS-CoV-2 virus might lead to characteristic patterns in the results of widely available, routine blood tests that could be identified with machine learning methodologies. Machine learning modalities integrating findings from these common laboratory test results might accelerate ruling out COVID-19 in emergency department patients. Objective We sought to develop (ie, train and internally validate with cross-validation techniques) and externally validate a machine learning model to rule out COVID 19 using only routine blood tests among adults in emergency departments. Methods Using clinical data from emergency departments (EDs) from 66 US hospitals before the pandemic (before the end of December 2019) or during the pandemic (March-July 2020), we included patients aged ≥20 years in the study time frame. We excluded those with missing laboratory results. Model training used 2183 PCR-confirmed cases from 43 hospitals during the pandemic; negative controls were 10,000 prepandemic patients from the same hospitals. External validation used 23 hospitals with 1020 PCR-confirmed cases and 171,734 prepandemic negative controls. The main outcome was COVID 19 status predicted using same-day routine laboratory results. Model performance was assessed with area under the receiver operating characteristic (AUROC) curve as well as sensitivity, specificity, and negative predictive value (NPV). Results Of 192,779 patients included in the training, external validation, and sensitivity data sets (median age decile 50 [IQR 30-60] years, 40.5% male [78,249/192,779]), AUROC for training and external validation was 0.91 (95% CI 0.90-0.92). Using a risk score cutoff of 1.0 (out of 100) in the external validation data set, the model achieved sensitivity of 95.9% and specificity of 41.7%; with a cutoff of 2.0, sensitivity was 92.6% and specificity was 59.9%. At the cutoff of 2.0, the NPVs at a prevalence of 1%, 10%, and 20% were 99.9%, 98.6%, and 97%, respectively. Conclusions A machine learning model developed with multicenter clinical data integrating commonly collected ED laboratory data demonstrated high rule-out accuracy for COVID-19 status, and might inform selective use of PCR-based testing.more » « less
-
Background Risk-based screening for lung cancer is currently being considered in several countries; however, the optimal approach to determine eligibility remains unclear. Ensemble machine learning could support the development of highly parsimonious prediction models that maintain the performance of more complex models while maximising simplicity and generalisability, supporting the widespread adoption of personalised screening. In this work, we aimed to develop and validate ensemble machine learning models to determine eligibility for risk-based lung cancer screening.
Methods and findings For model development, we used data from 216,714 ever-smokers recruited between 2006 and 2010 to the UK Biobank prospective cohort and 26,616 high-risk ever-smokers recruited between 2002 and 2004 to the control arm of the US National Lung Screening (NLST) randomised controlled trial. The NLST trial randomised high-risk smokers from 33 US centres with at least a 30 pack-year smoking history and fewer than 15 quit-years to annual CT or chest radiography screening for lung cancer. We externally validated our models among 49,593 participants in the chest radiography arm and all 80,659 ever-smoking participants in the US Prostate, Lung, Colorectal and Ovarian (PLCO) Screening Trial. The PLCO trial, recruiting from 1993 to 2001, analysed the impact of chest radiography or no chest radiography for lung cancer screening. We primarily validated in the PLCO chest radiography arm such that we could benchmark against comparator models developed within the PLCO control arm. Models were developed to predict the risk of 2 outcomes within 5 years from baseline: diagnosis of lung cancer and death from lung cancer. We assessed model discrimination (area under the receiver operating curve, AUC), calibration (calibration curves and expected/observed ratio), overall performance (Brier scores), and net benefit with decision curve analysis.
Models predicting lung cancer death (UCL-D) and incidence (UCL-I) using 3 variables—age, smoking duration, and pack-years—achieved or exceeded parity in discrimination, overall performance, and net benefit with comparators currently in use, despite requiring only one-quarter of the predictors. In external validation in the PLCO trial, UCL-D had an AUC of 0.803 (95% CI: 0.783, 0.824) and was well calibrated with an expected/observed (E/O) ratio of 1.05 (95% CI: 0.95, 1.19). UCL-I had an AUC of 0.787 (95% CI: 0.771, 0.802), an E/O ratio of 1.0 (95% CI: 0.92, 1.07). The sensitivity of UCL-D was 85.5% and UCL-I was 83.9%, at 5-year risk thresholds of 0.68% and 1.17%, respectively, 7.9% and 6.2% higher than the USPSTF-2021 criteria at the same specificity. The main limitation of this study is that the models have not been validated outside of UK and US cohorts.
Conclusions We present parsimonious ensemble machine learning models to predict the risk of lung cancer in ever-smokers, demonstrating a novel approach that could simplify the implementation of risk-based lung cancer screening in multiple settings.
-
Abstract STUDY QUESTION Can we derive adequate models to predict the probability of conception among couples actively trying to conceive?
SUMMARY ANSWER Leveraging data collected from female participants in a North American preconception cohort study, we developed models to predict pregnancy with performance of ∼70% in the area under the receiver operating characteristic curve (AUC).
WHAT IS KNOWN ALREADY Earlier work has focused primarily on identifying individual risk factors for infertility. Several predictive models have been developed in subfertile populations, with relatively low discrimination (AUC: 59–64%).
STUDY DESIGN, SIZE, DURATION Study participants were female, aged 21–45 years, residents of the USA or Canada, not using fertility treatment, and actively trying to conceive at enrollment (2013–2019). Participants completed a baseline questionnaire at enrollment and follow-up questionnaires every 2 months for up to 12 months or until conception. We used data from 4133 participants with no more than one menstrual cycle of pregnancy attempt at study entry.
PARTICIPANTS/MATERIALS, SETTING, METHODS On the baseline questionnaire, participants reported data on sociodemographic factors, lifestyle and behavioral factors, diet quality, medical history and selected male partner characteristics. A total of 163 predictors were considered in this study. We implemented regularized logistic regression, support vector machines, neural networks and gradient boosted decision trees to derive models predicting the probability of pregnancy: (i) within fewer than 12 menstrual cycles of pregnancy attempt time (Model I), and (ii) within 6 menstrual cycles of pregnancy attempt time (Model II). Cox models were used to predict the probability of pregnancy within each menstrual cycle for up to 12 cycles of follow-up (Model III). We assessed model performance using the AUC and the weighted-F1 score for Models I and II, and the concordance index for Model III.
MAIN RESULTS AND THE ROLE OF CHANCE Model I and II AUCs were 70% and 66%, respectively, in parsimonious models, and the concordance index for Model III was 63%. The predictors that were positively associated with pregnancy in all models were: having previously breastfed an infant and using multivitamins or folic acid supplements. The predictors that were inversely associated with pregnancy in all models were: female age, female BMI and history of infertility. Among nulligravid women with no history of infertility, the most important predictors were: female age, female BMI, male BMI, use of a fertility app, attempt time at study entry and perceived stress.
LIMITATIONS, REASONS FOR CAUTION Reliance on self-reported predictor data could have introduced misclassification, which would likely be non-differential with respect to the pregnancy outcome given the prospective design. In addition, we cannot be certain that all relevant predictor variables were considered. Finally, though we validated the models using split-sample replication techniques, we did not conduct an external validation study.
WIDER IMPLICATIONS OF THE FINDINGS Given a wide range of predictor data, machine learning algorithms can be leveraged to analyze epidemiologic data and predict the probability of conception with discrimination that exceeds earlier work.
STUDY FUNDING/COMPETING INTEREST(S) The research was partially supported by the U.S. National Science Foundation (under grants DMS-1664644, CNS-1645681 and IIS-1914792) and the National Institutes for Health (under grants R01 GM135930 and UL54 TR004130). In the last 3 years, L.A.W. has received in-kind donations for primary data collection in PRESTO from FertilityFriend.com, Kindara.com, Sandstone Diagnostics and Swiss Precision Diagnostics. L.A.W. also serves as a fibroid consultant to AbbVie, Inc. The other authors declare no competing interests.
TRIAL REGISTRATION NUMBER N/A.
-
Abstract The COVID-19 pandemic has challenged front-line clinical decision-making, leading to numerous published prognostic tools. However, few models have been prospectively validated and none report implementation in practice. Here, we use 3345 retrospective and 474 prospective hospitalizations to develop and validate a parsimonious model to identify patients with favorable outcomes within 96 h of a prediction, based on real-time lab values, vital signs, and oxygen support variables. In retrospective and prospective validation, the model achieves high average precision (88.6% 95% CI: [88.4–88.7] and 90.8% [90.8–90.8]) and discrimination (95.1% [95.1–95.2] and 86.8% [86.8–86.9]) respectively. We implemented and integrated the model into the EHR, achieving a positive predictive value of 93.3% with 41% sensitivity. Preliminary results suggest clinicians are adopting these scores into their clinical workflows.more » « less
-
null (Ed.)With the recent explosion in the size of libraries available for screening, virtual screening is positioned to assume a more prominent role in early drug discovery’s search for active chemical matter. In typical virtual screens, however, only about 12% of the top-scoring compounds actually show activity when tested in biochemical assays. We argue that most scoring functions used for this task have been developed with insufficient thoughtfulness into the datasets on which they are trained and tested, leading to overly simplistic models and/or overtraining. These problems are compounded in the literature because studies reporting new scoring methods have not validated their models prospectively within the same study. Here, we report a strategy for building a training dataset (D-COID) that aims to generate highly compelling decoy complexes that are individually matched to available active complexes. Using this dataset, we train a general-purpose classifier for virtual screening (vScreenML) that is built on the XGBoost framework. In retrospective benchmarks, our classifier shows outstanding performance relative to other scoring functions. In a prospective context, nearly all candidate inhibitors from a screen against acetylcholinesterase show detectable activity; beyond this, 10 of 23 compounds have IC 50 better than 50 μM. Without any medicinal chemistry optimization, the most potent hit has IC 50 280 nM, corresponding to K i of 173 nM. These results support using the D-COID strategy for training classifiers in other computational biology tasks, and for vScreenML in virtual screening campaigns against other protein targets. Both D-COID and vScreenML are freely distributed to facilitate such efforts.more » « less