Local and Distributed Machine Learning for Inter-hospital Data Utilization: An Application for TAVI Outcome Prediction.
Ontology highlight
ABSTRACT:
SUBMITTER: Lopes RR
PROVIDER: S-EPMC8632813 | biostudies-literature |
REPOSITORIES: biostudies-literature
Similar Datasets
Project description:BACKGROUND:Prognostication is an essential tool for risk adjustment and decision making in the intensive care unit (ICU). Research into prognostication in ICU has so far been limited to data from admission or the first 24 hours. Most ICU admissions last longer than this, decisions are made throughout an admission, and some admissions are explicitly intended as time-limited prognostic trials. Despite this, temporal changes in prognostic ability during ICU admission has received little attention to date. Current predictive models, in the form of prognostic clinical tools, are typically derived from linear models and do not explicitly handle incremental information from trends. Machine learning (ML) allows predictive models to be developed which use non-linear predictors and complex interactions between variables, thus allowing incorporation of trends in measured variables over time; this has made it possible to investigate prognosis throughout an admission. METHODS AND FINDINGS:This study uses ML to assess the predictability of ICU mortality as a function of time. Logistic regression against physiological data alone outperformed APACHE-II and demonstrated several important interactions including between lactate & noradrenaline dose, between lactate & MAP, and between age & MAP consistent with the current sepsis definitions. ML models consistently outperformed logistic regression with Deep Learning giving the best results. Predictive power was maximal on the second day and was further improved by incorporating trend data. Using a limited range of physiological and demographic variables, the best machine learning model on the first day showed an area under the receiver-operator characteristic curve (AUC) of 0.883 (σ = 0.008), compared to 0.846 (σ = 0.010) for a logistic regression from the same predictors and 0.836 (σ = 0.007) for a logistic regression based on the APACHE-II score. Adding information gathered on the second day of admission improved the maximum AUC to 0.895 (σ = 0.008). Beyond the second day, predictive ability declined. CONCLUSION:This has implications for decision making in intensive care and provides a justification for time-limited trials of ICU therapy; the assessment of prognosis over more than one day may be a valuable strategy as new information on the second day helps to differentiate outcomes. New ML models based on trend data beyond the first day could greatly improve upon current risk stratification tools.
| S-EPMC6241126 | biostudies-other
Project description:AimsTo assess treatment decision and outcome in patients referred for transcatheter aortic valve implantation (TAVI) in addition to predictive factors of mortality after TAVI.MethodsThree-centre prospective observational study including 358 patients. Endpoints were defined according to the Valve Academic Research Consortium.ResultsOf the 358 patients referred for TAVI, TAVI was performed in 235 patients (65%), surgical aortic valve replacement (AVR) in 24 (7%) and medical therapy (MT) in 99 (28%). Reasons to decline TAVI in favour of AVR/MT were patient preference (29%), peripheral vascular disease (15%) and non-severe aortic stenosis (11%). The logistic EuroSCORE was significantly higher in patients who underwent TAVI and MT in comparison with those undergoing AVR (19 vs. 10%, p?=?0.007). At 30 days, all-cause mortality and the combined safety endpoint were 9 and 24% after TAVI and 8 and 25% after AVR, respectively. All-cause mortality was significantly lower in the TAVI group compared with the MT group at 6 months, 1 year and 2 years (12% vs. 22%, 21% vs. 33% and 31% vs. 55%, respectively, p?<?0.001). Multivariable analysis revealed that blood transfusion (HR: 1.19; 95% CI: 1.05-1.33), pre-existing renal failure (HR: 1.18; 95% CI: 1.06-1.33) and STS score (HR: 1.06; 95% CI: 1.02-1.10) were independent predictors of mortality at a median of 10 (IQR: 3-23) months after TAVI.ConclusionsApproximately two-thirds of the patients referred for TAVI receive this treatment with gratifying short- and long-term survival. Another 7% underwent AVR. Prognosis is poor in patients who do not receive valve replacement therapy.
| S-EPMC3247629 | biostudies-literature
Project description:ObjectivesTo evaluate the impact of community level information on the predictability of out-of-hospital cardiac arrest (OHCA) survival.MethodsWe used the Cardiac Arrest Registry to Enhance Survival (CARES) to geocode 9,595 Chicago incidents from 2014 to 2019 into community areas. Community variables including crime, healthcare, and economic factors from public data were merged with CARES. The merged data were used to develop ML models for OHCA survival. Models were evaluated using Area Under the Receiver Operating Characteristic curve (AUROC) and features were analyzed using SHapley Additive exPansion (SHAP) values.ResultsBaseline results using CARES data achieved an AUROC of 84%. The final model utilizing community variables increased the AUROC to 88%. A SHAP analysis between high and low performing community area clusters showed the high performing cluster is positively impacted by good health related features and good community safety features positively impact the low performing cluster.ConclusionUtilizing community variables helps predict neurologic outcomes with better performance than only CARES data. Future studies will use this model to perform simulations to identify interventions to improve OHCA survival.
| S-EPMC9728593 | biostudies-literature
Project description:BACKGROUND:Transcatheter aortic valve implantation (TAVI) has become a commonly applied procedure for high-risk aortic valve stenosis patients. However, for some patients, this procedure does not result in the expected benefits. Previous studies indicated that it is difficult to predict the beneficial effects for specific patients. We aim to study the accuracy of various traditional machine learning (ML) algorithms in the prediction of TAVI outcomes. METHODS AND RESULTS:Clinical and laboratory data from 1,478 TAVI patients from a single centre were collected. The outcome measures were improvement of dyspnoea and mortality. Three experiments were performed using (1) screening data, (2) laboratory data, and (3) the combination of both. Five well-established ML techniques were implemented, and the models were evaluated based on the area under the curve (AUC). Random forest classifier achieved the highest AUC (0.70) for predicting mortality. Logistic regression had the highest AUC (0.56) in predicting improvement of dyspnoea. CONCLUSIONS:In our single-centre TAVI population, the tree-based models were slightly more accurate than others in predicting mortality. However, ML models performed poorly in predicting improvement of dyspnoea.
| S-EPMC6712116 | biostudies-literature
Project description:ObjectivesPredictive analytics in emergency care has mostly been limited to the use of clinical decision rules (CDRs) in the form of simple heuristics and scoring systems. In the development of CDRs, limitations in analytic methods and concerns with usability have generally constrained models to a preselected small set of variables judged to be clinically relevant and to rules that are easily calculated. Furthermore, CDRs frequently suffer from questions of generalizability, take years to develop, and lack the ability to be updated as new information becomes available. Newer analytic and machine learning techniques capable of harnessing the large number of variables that are already available through electronic health records (EHRs) may better predict patient outcomes and facilitate automation and deployment within clinical decision support systems. In this proof-of-concept study, a local, big data-driven, machine learning approach is compared to existing CDRs and traditional analytic methods using the prediction of sepsis in-hospital mortality as the use case.MethodsThis was a retrospective study of adult ED visits admitted to the hospital meeting criteria for sepsis from October 2013 to October 2014. Sepsis was defined as meeting criteria for systemic inflammatory response syndrome with an infectious admitting diagnosis in the ED. ED visits were randomly partitioned into an 80%/20% split for training and validation. A random forest model (machine learning approach) was constructed using over 500 clinical variables from data available within the EHRs of four hospitals to predict in-hospital mortality. The machine learning prediction model was then compared to a classification and regression tree (CART) model, logistic regression model, and previously developed prediction tools on the validation data set using area under the receiver operating characteristic curve (AUC) and chi-square statistics.ResultsThere were 5,278 visits among 4,676 unique patients who met criteria for sepsis. Of the 4,222 patients in the training group, 210 (5.0%) died during hospitalization, and of the 1,056 patients in the validation group, 50 (4.7%) died during hospitalization. The AUCs with 95% confidence intervals (CIs) for the different models were as follows: random forest model, 0.86 (95% CI = 0.82 to 0.90); CART model, 0.69 (95% CI = 0.62 to 0.77); logistic regression model, 0.76 (95% CI = 0.69 to 0.82); CURB-65, 0.73 (95% CI = 0.67 to 0.80); MEDS, 0.71 (95% CI = 0.63 to 0.77); and mREMS, 0.72 (95% CI = 0.65 to 0.79). The random forest model AUC was statistically different from all other models (p ≤ 0.003 for all comparisons).ConclusionsIn this proof-of-concept study, a local big data-driven, machine learning approach outperformed existing CDRs as well as traditional analytic techniques for predicting in-hospital mortality of ED patients with sepsis. Future research should prospectively evaluate the effectiveness of this approach and whether it translates into improved clinical outcomes for high-risk sepsis patients. The methods developed serve as an example of a new model for predictive analytics in emergency care that can be automated, applied to other clinical outcomes of interest, and deployed in EHRs to enable locally relevant clinical predictions.
| S-EPMC5884101 | biostudies-literature
Project description:To save time during transport, where resuscitation quality can degrade in a moving ambulance, it would be prudent to continue the resuscitation on scene if there is a high likelihood of ROSC occurring at the scene. We developed the pre-hospital real-time cardiac arrest outcome prediction (PReCAP) model to predict ROSC at the scene using prehospital input variables with time-adaptive cohort. The patient survival at discharge from the emergency department (ED), the 30-day survival rate, and the final Cerebral Performance Category (CPC) were secondary prediction outcomes in this study. The Pan-Asian Resuscitation Outcome Study (PAROS) database, which includes out-of-hospital cardiac arrest (OHCA) patients transferred by emergency medical service in Asia between 2009 and 2018, was utilized for this study. From the variables available in the PAROS database, we selected relevant variables to predict OHCA outcomes. Light gradient-boosting machine (LightGBM) was used to build the PReCAP model. Between 2009 and 2018, 157,654 patients in the PAROS database were enrolled in our study. In terms of prediction of ROSC on scene, the PReCAP had an AUROC score between 0.85 and 0.87. The PReCAP had an AUROC score between 0.91 and 0.93 for predicting survived to discharge from ED, and an AUROC score between 0.80 and 0.86 for predicting the 30-day survival. The PReCAP predicted CPC with an AUROC score ranging from 0.84 to 0.91. The feature importance differed with time in the PReCAP model prediction of ROSC on scene. Using the PAROS database, PReCAP predicted ROSC on scene, survival to discharge from ED, 30-day survival, and CPC for each minute with an AUROC score ranging from 0.8 to 0.93. As this model used a multi-national database, it might be applicable for a variety of environments and populations.
| S-EPMC10663550 | biostudies-literature
Project description:This article is motivated by the increasing need to model risk for large hospital and health care systems that provide services to diverse and complex patients. Often, heterogeneity across a population is determined by a set of factors such as chronic conditions. When these stratifying factors result in overlapping subpopulations, it is likely that the covariate effects for the overlapping groups have some similarity. We exploit this similarity by imposing structural constraints on the importance of variables in predicting outcomes such as hospital admission. Our basic assumption is that if a variable is important for a subpopulation with one of the chronic conditions, then it should be important for the subpopulation with both conditions. However, a variable can be important for the subpopulation with two particular chronic conditions but not for the subpopulations of people with just one of those two conditions. This assumption and its generalization to more conditions are reasonable and aid greatly in borrowing strength across the subpopulations. We prove an oracle property for our estimation method and show that even when the structural assumptions are misspecified, our method will still include all of the truly nonzero variables in large samples. We demonstrate impressive performance of our method in extensive numerical studies and on an application in hospital admission prediction and validation for the Medicare population of a large health care provider.
| S-EPMC6076875 | biostudies-literature
Project description:BackgroundTelemonitoring of symptoms and physiological signs has been suggested as a means of early detection of chronic obstructive pulmonary disease (COPD) exacerbations, with a view to instituting timely treatment. However, algorithms to identify exacerbations result in frequent false-positive results and increased workload. Machine learning, when applied to predictive modelling, can determine patterns of risk factors useful for improving prediction quality.ObjectiveOur objectives were to (1) establish whether machine learning techniques applied to telemonitoring datasets improve prediction of hospital admissions and decisions to start corticosteroids, and (2) determine whether the addition of weather data further improves such predictions.MethodsWe used daily symptoms, physiological measures, and medication data, with baseline demography, COPD severity, quality of life, and hospital admissions from a pilot and large randomized controlled trial of telemonitoring in COPD. We linked weather data from the United Kingdom meteorological service. We used feature selection and extraction techniques for time series to construct up to 153 predictive patterns (features) from symptom, medication, and physiological measurements. We used the resulting variables to construct predictive models fitted to training sets of patients and compared them with common symptom-counting algorithms.ResultsWe had a mean 363 days of telemonitoring data from 135 patients. The two most practical traditional score-counting algorithms, restricted to cases with complete data, resulted in area under the receiver operating characteristic curve (AUC) estimates of 0.60 (95% CI 0.51-0.69) and 0.58 (95% CI 0.50-0.67) for predicting admissions based on a single day's readings. However, in a real-world scenario allowing for missing data, with greater numbers of patient daily data and hospitalizations (N=57,150, N+=55, respectively), the performance of all the traditional algorithms fell, including those based on 2 days' data. One of the most frequently used algorithms performed no better than chance. All considered machine learning models demonstrated significant improvements; the best machine learning algorithm based on 57,150 episodes resulted in an aggregated AUC of 0.74 (95% CI 0.67-0.80). Adding weather data measurements did not improve the predictive performance of the best model (AUC 0.74, 95% CI 0.69-0.79). To achieve an 80% true-positive rate (sensitivity), the traditional algorithms were associated with an 80% false-positive rate: our algorithm halved this rate to approximately 40% (specificity approximately 60%). The machine learning algorithm was moderately superior to the best symptom-counting algorithm (AUC 0.77, 95% CI 0.74-0.79 vs AUC 0.66, 95% CI 0.63-0.68) at predicting the need for corticosteroids.ConclusionsEarly detection and management of COPD remains an important goal given its huge personal and economic costs. Machine learning approaches, which can be tailored to an individual's baseline profile and can learn from experience of the individual patient, are superior to existing predictive algorithms and show promise in achieving this goal.Trial registrationInternational Standard Randomized Controlled Trial Number ISRCTN96634935; http://www.isrctn.com/ISRCTN96634935 (Archived by WebCite at http://www.webcitation.org/722YkuhAz).
| S-EPMC6231768 | biostudies-literature
Project description:The application of machine learning has rapidly evolved in medicine over the past decade. In stroke, commercially available machine learning algorithms have already been incorporated into clinical application for rapid diagnosis. The creation and advancement of deep learning techniques have greatly improved clinical utilization of machine learning tools and new algorithms continue to emerge with improved accuracy in stroke diagnosis and outcome prediction. Although imaging-based feature recognition and segmentation have significantly facilitated rapid stroke diagnosis and triaging, stroke prognostication is dependent on a multitude of patient specific as well as clinical factors and hence accurate outcome prediction remains challenging. Despite its vital role in stroke diagnosis and prognostication, it is important to recognize that machine learning output is only as good as the input data and the appropriateness of algorithm applied to any specific data set. Additionally, many studies on machine learning tend to be limited by small sample size and hence concerted efforts to collate data could improve evaluation of future machine learning tools in stroke. In the present state, machine learning technology serves as a helpful and efficient tool for rapid clinical decision making while oversight from clinical experts is still required to address specific aspects not accounted for in an automated algorithm. This article provides an overview of machine learning technology and a tabulated review of pertinent machine learning studies related to stroke diagnosis and outcome prediction.
| S-EPMC8685212 | biostudies-literature
Project description:Functional outcomes after acute ischemic stroke are of great concern to patients and their families, as well as physicians and surgeons who make the clinical decisions. We developed machine learning (ML)-based functional outcome prediction models in acute ischemic stroke. This retrospective study used a prospective cohort database. A total of 1066 patients with acute ischemic stroke between January 2019 and March 2021 were included. Variables such as demographic factors, stroke-related factors, laboratory findings, and comorbidities were utilized at the time of admission. Five ML algorithms were applied to predict a favorable functional outcome (modified Rankin Scale 0 or 1) at 3 months after stroke onset. Regularized logistic regression showed the best performance with an area under the receiver operating characteristic curve (AUC) of 0.86. Support vector machines represented the second-highest AUC of 0.85 with the highest F1-score of 0.86, and finally, all ML models applied achieved an AUC > 0.8. The National Institute of Health Stroke Scale at admission and age were consistently the top two important variables for generalized logistic regression, random forest, and extreme gradient boosting models. ML-based functional outcome prediction models for acute ischemic stroke were validated and proven to be readily applicable and useful.
| S-EPMC8534707 | biostudies-literature