Predictive Analytics with Strategically Missing Data.
Ontology highlight
ABSTRACT:
SUBMITTER: Zhang J
PROVIDER: S-EPMC8459828 | biostudies-literature |
REPOSITORIES: biostudies-literature
Similar Datasets
Project description:The UK Biobank is a rich national health resource that provides enormous opportunities for international researchers to examine, model, and analyze census-like multisource healthcare data. The archive presents several challenges related to aggregation and harmonization of complex data elements, feature heterogeneity and salience, and health analytics. Using 7,614 imaging, clinical, and phenotypic features of 9,914 subjects we performed deep computed phenotyping using unsupervised clustering and derived two distinct sub-cohorts. Using parametric and nonparametric tests, we determined the top 20 most salient features contributing to the cluster separation. Our approach generated decision rules to predict the presence and progression of depression or other mental illnesses by jointly representing and modeling the significant clinical and demographic variables along with the derived salient neuroimaging features. We reported consistency and reliability measures of the derived computed phenotypes and the top salient imaging biomarkers that contributed to the unsupervised clustering. This clinical decision support system identified and utilized holistically the most critical biomarkers for predicting mental health, e.g., depression. External validation of this technique on different populations may lead to reducing healthcare expenses and improving the processes of diagnosis, forecasting, and tracking of normal and pathological aging.
| S-EPMC6461626 | biostudies-literature
Project description:Nowadays, big data are everywhere. Examples of big data include weather data, web-search data, disease reports, as well as epidemic data and statistics. These big data can be easily generated and collected from a wide variety of data sources. A data science framework—such as predictive analytics framework—helps mining data from various big data sources to find useful information and discover knowledge, which can then be transformed into wisdom for appropriate actions. In this paper, we present an innovative big data predictive analytics framework over hybrid big data sources. To demonstrate the effectiveness and practicality of our framework, we conduct several case studies, including one on applying the framework to disease analytics. More specifically, we integrate, incorporate and analyze weather data and web-search data to predict and forecast dengue cases based on a hybrid of three kernels in support vector machine (SVM) ensemble. Results show how our predictive analytics framework benefits health agencies in disease control and prevention.
| S-EPMC7123615 | biostudies-literature
Project description:Multimodality datasets are becoming increasingly common in various domains to provide complementary information for predictive analytics. One significant challenge in fusing multimodality data is that the multiple modalities are not universally available for all samples due to cost and accessibility constraints. This results in a unique data structure called Incomplete Multimodality Dataset (IMD). We propose a novel Incomplete-Multimodality Transfer Learning (IMTL) model that builds a predictive model for each sub-cohort of samples with the same missing modality pattern, and meanwhile couples the model estimation processes for different sub-cohorts to allow for transfer learning. We develop an Expectation-Maximization (EM) algorithm to estimate the parameters of IMTL and further extend it to a collaborative learning paradigm that is specifically valuable for patient privacy preservation in health care applications. We prove two advantageous properties of IMTL: the ability for out-of-sample prediction and a theoretical guarantee for a larger Fisher information compared with models without transfer learning. IMTL is applied to diagnosis and prognosis of the Alzheimer's Disease (AD) at an early stage called Mild Cognitive Impairment (MCI) using incomplete multimodality imaging data. IMTL achieves higher accuracy than competing methods without transfer learning. Supplementary materials are available for this article on the publisher's website.
| S-EPMC10312385 | biostudies-literature
Project description:BackgroundAcute kidney injury (AKI) is a common complication after surgery that is associated with increased morbidity and mortality. The majority of existing perioperative AKI risk prediction models are limited in their generalizability and do not fully utilize intraoperative physiological time-series data. Thus, there is a need for intelligent, accurate, and robust systems to leverage new information as it becomes available to predict the risk of developing postoperative AKI.MethodsA retrospective single-center cohort of 2,911 adults who underwent surgery at the University of Florida Health between 2000 and 2010 was utilized for this study. Machine learning and statistical analysis techniques were used to develop perioperative models to predict the risk of developing AKI during the first three days after surgery, first seven days after surgery, and overall (after surgery during the index hospitalization). The improvement in risk prediction was examined by incorporating intraoperative physiological time-series variables. Our proposed model enriched a preoperative model that produced a probabilistic AKI risk score by integrating intraoperative statistical features through a machine learning stacking approach inside a random forest classifier. Model performance was evaluated using the area under the receiver operating characteristic curve (AUC), accuracy, and Net Reclassification Improvement (NRI).ResultsThe predictive performance of the proposed model is better than the preoperative data only model. The proposed model had an AUC of 0.86 (accuracy of 0.78) for the seven-day AKI outcome, while the preoperative model had an AUC of 0.84 (accuracy of 0.76). Furthermore, by integrating intraoperative features, the algorithm was able to reclassify 40% of the false negative patients from the preoperative model. The NRI for each outcome was AKI at three days (8%), seven days (7%), and overall (4%).ConclusionsPostoperative AKI prediction was improved with high sensitivity and specificity through a machine learning approach that dynamically incorporated intraoperative data.
| S-EPMC6448850 | biostudies-literature
Project description:PurposeTo (1) use All of Us (AoU) data to validate a previously published single-center model predicting the need for surgery among individuals with glaucoma, (2) train new models using AoU data, and (3) share insights regarding this novel data source for ophthalmic research.DesignDevelopment and evaluation of machine learning models.MethodsElectronic health record data were extracted from AoU for 1,231 adults diagnosed with primary open-angle glaucoma. The single-center model was applied to AoU data for external validation. AoU data were then used to train new models for predicting the need for glaucoma surgery using multivariable logistic regression, artificial neural networks, and random forests. Five-fold cross-validation was performed. Model performance was evaluated based on area under the receiver operating characteristic curve (AUC), accuracy, precision, and recall.ResultsThe mean (standard deviation) age of the AoU cohort was 69.1 (10.5) years, with 57.3% women and 33.5% black, significantly exceeding representation in the single-center cohort (P = .04 and P < .001, respectively). Of 1,231 participants, 286 (23.2%) needed glaucoma surgery. When applying the single-center model to AoU data, accuracy was 0.69 and AUC was only 0.49. Using AoU data to train new models resulted in superior performance: AUCs ranged from 0.80 (logistic regression) to 0.99 (random forests).ConclusionsModels trained with national AoU data achieved superior performance compared with using single-center data. Although AoU does not currently include ophthalmic imaging, it offers several strengths over similar big-data sources such as claims data. AoU is a promising new data source for ophthalmic research.
| S-EPMC8184631 | biostudies-literature
Project description:Artificial intelligence (AI) and machine learning (ML) have been increasingly used in materials science to build predictive models and accelerate discovery. For selected properties, availability of large databases has also facilitated application of deep learning (DL) and transfer learning (TL). However, unavailability of large datasets for a majority of properties prohibits widespread application of DL/TL. We present a cross-property deep-transfer-learning framework that leverages models trained on large datasets to build models on small datasets of different properties. We test the proposed framework on 39 computational and two experimental datasets and find that the TL models with only elemental fractions as input outperform ML/DL models trained from scratch even when they are allowed to use physical attributes as input, for 27/39 (≈ 69%) computational and both the experimental datasets. We believe that the proposed framework can be widely useful to tackle the small data challenge in applying AI/ML in materials science.
| S-EPMC8594437 | biostudies-literature
Project description:Effective capacity management of operation rooms is key to avoid surgery cancellations and prevent long waiting lists that negatively affect clinical and financial outcomes as well as patient and staff satisfaction. This requires optimal surgery scheduling, leveraging essential parameters like surgery duration, post-operative bed type and hospital length-of-stay. Common clinical practice is to use the surgeon's average procedure time of the last N patients as a planned surgery duration for the next patient. A discrepancy between the actual and planned surgery duration may lead to suboptimal surgery schedule. We used deidentified data from 2294 cardio-thoracic surgeries to first calculate the discrepancy of the current model and second to develop new predictive models based on linear regression, random forest, and extreme gradient boosting. The new ensamble models reduced the RMSE for elective and acute surgeries by 19% (0.99 vs 0.80, p = 0.002) and 52% (1.87 vs 0.89, p < 0.001), respectively. Also, the elective and acute surgeries "behind schedule" were reduced by 28% (60% vs. 32%, p < 0.001) and 9% (37% vs. 28%, p = 0.003), respectively. These improvements were fueled by the patient and surgery features added to the models. Surgery planners can benefit from these predictive models as a patient flow AI decision support tool to optimize OR utilization.
| S-EPMC10630382 | biostudies-literature
Project description:BackgroundThe assessment of calibration performance of risk prediction models based on regression or more flexible machine learning algorithms receives little attention.Main textHerein, we argue that this needs to change immediately because poorly calibrated algorithms can be misleading and potentially harmful for clinical decision-making. We summarize how to avoid poor calibration at algorithm development and how to assess calibration at algorithm validation, emphasizing balance between model complexity and the available sample size. At external validation, calibration curves require sufficiently large samples. Algorithm updating should be considered for appropriate support of clinical practice.ConclusionEfforts are required to avoid poor calibration when developing prediction models, to evaluate calibration when validating models, and to update models when indicated. The ultimate aim is to optimize the utility of predictive analytics for shared decision-making and patient counseling.
| S-EPMC6912996 | biostudies-literature
Project description:For decades, self-report measures based on questionnaires have been widely used in educational research to study implicit and complex constructs such as motivation, emotion, cognitive and metacognitive learning strategies. However, the existence of potential biases in such self-report instruments might cast doubts on the validity of the measured constructs. The emergence of trace data from digital learning environments has sparked a controversial debate on how we measure learning. On the one hand, trace data might be perceived as "objective" measures that are independent of any biases. On the other hand, there is mixed evidence of how trace data are compatible with existing learning constructs, which have traditionally been measured with self-reports. This study investigates the strengths and weaknesses of different types of data when designing predictive models of academic performance based on computer-generated trace data and survey data. We investigate two types of bias in self-report surveys: response styles (i.e., a tendency to use the rating scale in a certain systematic way that is unrelated to the content of the items) and overconfidence (i.e., the differences in predicted performance based on surveys' responses and a prior knowledge test). We found that the response style bias accounts for a modest to a substantial amount of variation in the outcomes of the several self-report instruments, as well as in the course performance data. It is only the trace data, notably that of process type, that stand out in being independent of these response style patterns. The effect of overconfidence bias is limited. Given that empirical models in education typically aim to explain the outcomes of learning processes or the relationships between antecedents of these learning outcomes, our analyses suggest that the bias present in surveys adds predictive power in the explanation of performance data and other questionnaire data.
| S-EPMC7292385 | biostudies-literature
Project description:ObjectiveThe development of predictive models for clinical application requires the availability of electronic health record (EHR) data, which is complicated by patient privacy concerns. We showcase the "Model to Data" (MTD) approach as a new mechanism to make private clinical data available for the development of predictive models. Under this framework, we eliminate researchers' direct interaction with patient data by delivering containerized models to the EHR data.Materials and methodsWe operationalize the MTD framework using the Synapse collaboration platform and an on-premises secure computing environment at the University of Washington hosting EHR data. Containerized mortality prediction models developed by a model developer, were delivered to the University of Washington via Synapse, where the models were trained and evaluated. Model performance metrics were returned to the model developer.ResultsThe model developer was able to develop 3 mortality prediction models under the MTD framework using simple demographic features (area under the receiver-operating characteristic curve [AUROC], 0.693), demographics and 5 common chronic diseases (AUROC, 0.861), and the 1000 most common features from the EHR's condition/procedure/drug domains (AUROC, 0.921).DiscussionWe demonstrate the feasibility of the MTD framework to facilitate the development of predictive models on private EHR data, enabled by common data models and containerization software. We identify challenges that both the model developer and the health system information technology group encountered and propose future efforts to improve implementation.ConclusionsThe MTD framework lowers the barrier of access to EHR data and can accelerate the development and evaluation of clinical prediction models.
| S-EPMC7526463 | biostudies-literature