Forecasting new diseases in low-data settings using transfer learning.
Ontology highlight
ABSTRACT:
SUBMITTER: Roster K
PROVIDER: S-EPMC9222348 | biostudies-literature |
REPOSITORIES: biostudies-literature
Similar Datasets
Project description:This article contains the data related to the research article "Long-term forecast of energy commodities price using machine learning" (Herrera et al., 2019). The datasets contain monthly prices of six main energy commodities covering a large period of nearly four decades. Four methods are applied, i.e. a hybridization of traditional econometric models, artificial neural networks, random forests, and the no-change method. Data is divided into 80-20% ratio for training and test respectively and RMSE, MAPE, and M-DM test used for performance evaluation. Other methods can be applied to the dataset and used as a benchmark.
| S-EPMC6610706 | biostudies-literature
Project description:Hundreds of millions of surgical procedures take place annually across the world, which generate a prevalent type of electronic health record (EHR) data comprising time series physiological signals. Here, we present a transferable embedding method (i.e., a method to transform time series signals into input features for predictive machine learning models) named PHASE (PHysiologicAl Signal Embeddings) that enables us to more accurately forecast adverse surgical outcomes based on physiological signals. We evaluate PHASE on minute-by-minute EHR data of more than 50,000 surgeries from two operating room (OR) datasets and patient stays in an intensive care unit (ICU) dataset. PHASE outperforms other state-of-the-art approaches, such as long-short term memory networks trained on raw data and gradient boosted trees trained on handcrafted features, in predicting six distinct outcomes: hypoxemia, hypocapnia, hypotension, hypertension, phenylephrine, and epinephrine. In a transfer learning setting where we train embedding models in one dataset then embed signals and predict adverse events in unseen data, PHASE achieves significantly higher prediction accuracy at lower computational cost compared to conventional approaches. Finally, given the importance of understanding models in clinical applications we demonstrate that PHASE is explainable and validate our predictive models using local feature attribution methods.
| S-EPMC8654960 | biostudies-literature
Project description:Producing timely, well-informed and reliable forecasts for an ongoing epidemic of an emerging infectious disease is a huge challenge. Epidemiologists and policy makers have to deal with poor data quality, limited understanding of the disease dynamics, rapidly changing social environment and the uncertainty on effects of various interventions in place. Under this setting, detailed computational models provide a comprehensive framework for integrating diverse data sources into a well-defined model of disease dynamics and social behavior, potentially leading to better understanding and actions. In this paper, we describe one such agent-based model framework developed for forecasting the 2014-2015 Ebola epidemic in Liberia, and subsequently used during the Ebola forecasting challenge. We describe the various components of the model, the calibration process and summarize the forecast performance across scenarios of the challenge. We conclude by highlighting how such a data-driven approach can be refined and adapted for future epidemics, and share the lessons learned over the course of the challenge.
| S-EPMC5568513 | biostudies-literature
Project description:The necessary requirement of a traumatic event preceding the development of Posttraumatic Stress Disorder, theoretically allows for administering preventive and early interventions in the early aftermath of such events. Machine learning models including biomedical data to forecast PTSD outcome after trauma are highly promising for detection of individuals most in need of such interventions. In the current study, machine learning was applied on biomedical data collected within 48 h post-trauma to forecast individual risk for long-term PTSD, using a multinominal approach including the full spectrum of common PTSD symptom courses within one prognostic model for the first time. N = 417 patients (37.2% females; mean age 46.09 ± 15.88) admitted with (suspected) serious injury to two urban Academic Level-1 Trauma Centers were included. Routinely collected biomedical information (endocrine measures, vital signs, pharmacotherapy, demographics, injury and trauma characteristics) upon ED admission and subsequent 48 h was used. Cross-validated multi-nominal classification of longitudinal self-reported symptom severity (IES-R) over 12 months and bimodal classification of clinician-rated PTSD diagnosis (CAPS-IV) at 12 months post-trauma was performed using extreme Gradient Boosting and evaluated on hold-out sets. SHapley Additive exPlanations (SHAP) values were used to explain the derived models in human-interpretable form. Good prediction of longitudinal PTSD symptom trajectories (multiclass AUC = 0.89) and clinician-rated PTSD at 12 months (AUC = 0.89) was achieved. Most relevant prognostic variables to forecast both multinominal and dichotomous PTSD outcomes included acute endocrine and psychophysiological measures and hospital-prescribed pharmacotherapy. Thus, individual risk for long-term PTSD was accurately forecasted from biomedical information routinely collected within 48 h post-trauma. These results facilitate future targeted preventive interventions by enabling future early risk detection and provide further insights into the complex etiology of PTSD.
| S-EPMC7843920 | biostudies-literature
Project description:There is a growing demand for the use of machine learning (ML) to derive fast-to-evaluate surrogate models of materials properties. In recent years, a broad array of materials property databases have emerged as part of a digital transformation of materials science. However, recent technological advances in ML are not fully exploited because of the insufficient volume and diversity of materials data. An ML framework called "transfer learning" has considerable potential to overcome the problem of limited amounts of materials data. Transfer learning relies on the concept that various property types, such as physical, chemical, electronic, thermodynamic, and mechanical properties, are physically interrelated. For a given target property to be predicted from a limited supply of training data, models of related proxy properties are pretrained using sufficient data; these models capture common features relevant to the target task. Repurposing of such machine-acquired features on the target task yields outstanding prediction performance even with exceedingly small data sets, as if highly experienced human experts can make rational inferences even for considerably less experienced tasks. In this study, to facilitate widespread use of transfer learning, we develop a pretrained model library called XenonPy.MDL. In this first release, the library comprises more than 140?000 pretrained models for various properties of small molecules, polymers, and inorganic crystalline materials. Along with these pretrained models, we describe some outstanding successes of transfer learning in different scenarios such as building models with only dozens of materials data, increasing the ability of extrapolative prediction through a strategic model transfer, and so on. Remarkably, transfer learning has autonomously identified rather nontrivial transferability across different properties transcending the different disciplines of materials science; for example, our analysis has revealed underlying bridges between small molecules and polymers and between organic and inorganic chemistry.
| S-EPMC6813555 | biostudies-literature
Project description:PurposeTo determine if deep learning networks could be trained to forecast future 24-2 Humphrey Visual Fields (HVFs).MethodsAll data points from consecutive 24-2 HVFs from 1998 to 2018 were extracted from a university database. Ten-fold cross validation with a held out test set was used to develop the three main phases of model development: model architecture selection, dataset combination selection, and time-interval model training with transfer learning, to train a deep learning artificial neural network capable of generating a point-wise visual field prediction. The point-wise mean absolute error (PMAE) and difference in Mean Deviation (MD) between predicted and actual future HVF were calculated.ResultsMore than 1.7 million perimetry points were extracted to the hundredth decibel from 32,443 24-2 HVFs. The best performing model with 20 million trainable parameters, CascadeNet-5, was selected. The overall point-wise PMAE for the test set was 2.47 dB (95% CI: 2.45 dB to 2.48 dB), and deep learning showed a statistically significant improvement over linear models. The 100 fully trained models successfully predicted future HVFs in glaucomatous eyes up to 5.5 years in the future with a correlation of 0.92 between the MD of predicted and actual future HVF and an average difference of 0.41 dB.ConclusionsUsing unfiltered real-world datasets, deep learning networks show the ability to not only learn spatio-temporal HVF changes but also to generate predictions for future HVFs up to 5.5 years, given only a single HVF.
| S-EPMC6450620 | biostudies-literature
Project description:PurposeWe aimed to evaluate the performance of deep learning-based generalization of ultra-low-count amyloid PET/MRI enhancement when applied to studies acquired with different scanning hardware and protocols.MethodsEighty simultaneous [18F]florbetaben PET/MRI studies were acquired, split equally between two sites (site 1: Signa PET/MRI, GE Healthcare, 39 participants, 67 ± 8 years, 23 females; site 2: mMR, Siemens Healthineers, 64 ± 11 years, 23 females) with different MRI protocols. Twenty minutes of list-mode PET data (90-110 min post-injection) were reconstructed as ground-truth. Ultra-low-count data obtained from undersampling by a factor of 100 (site 1) or the first minute of PET acquisition (site 2) were reconstructed for ultra-low-dose/ultra-short-time (1% dose and 5% time, respectively) PET images. A deep convolution neural network was pre-trained with site 1 data and either (A) directly applied or (B) trained further on site 2 data using transfer learning. Networks were also trained from scratch based on (C) site 2 data or (D) all data. Certified physicians determined amyloid uptake (+/-) status for accuracy and scored the image quality. The peak signal-to-noise ratio, structural similarity, and root-mean-squared error were calculated between images and their ground-truth counterparts. Mean regional standardized uptake value ratios (SUVR, reference region: cerebellar cortex) from 37 successful site 2 FreeSurfer segmentations were analyzed.ResultsAll network-synthesized images had reduced noise than their ultra-low-count reconstructions. Quantitatively, image metrics improved the most using method B, where SUVRs had the least variability from the ground-truth and the highest effect size to differentiate between positive and negative images. Method A images had lower accuracy and image quality than other methods; images synthesized from methods B-D scored similarly or better than the ground-truth images.ConclusionsDeep learning can successfully produce diagnostic amyloid PET images from short frame reconstructions. Data bias should be considered when applying pre-trained deep ultra-low-count amyloid PET/MRI networks for generalization.
| S-EPMC7680289 | biostudies-literature
Project description:ObjectiveThere is a wide range of risk factors predisposing to the onset of neonatal encephalopathy (NE), including maternal antepartum/intrapartum comorbidities or events. However, few studies have investigated the difference in the impact of acute and chronic diseases on forecasting NE, which could assist clinicians in choosing the best course of action to prevent NE or reduce its severity and complications. In this study, we aimed to engineer features based on acute and chronic diseases and assess the differences of the impact of acute and chronic diseases on NE prediction using machine learning models.Materials and methodsWe used ten years of electronic health records of mothers from a large academic medical center to develop three types of features: chronic disease, recurrence of an acute disease, and temporal relationships between acute diseases. Two types of NE prediction models, based on acute and chronic diseases, respectively, were trained with feature selection. We further compared the prediction performance of the models with two state-of-the-art NE forecasting models. The machine learning models ranked the three types of engineered features based on their contributions to the NE prediction.ResultsThe NE model trained on acute disease features showed significantly higher AUC than the model relying on chronic disease features (AUC difference: 0.161, p-value < 0.001). The NE model trained on both acute and chronic disease features achieved the highest average AUC (0.889), with a significant improvement over the best existing model (0.854) with p = 0.0129. Recurrence of "known or suspected fetal abnormality affecting management of mother (655)" was assigned the highest weights in predicting NE.ConclusionsMachine learning models based on the three types of engineered features significantly improve NE prediction. Our results specifically suggest that acute disease-associated features play a more important role in predicting NE.
| S-EPMC8551018 | biostudies-literature
Project description:The cell cycle is a highly conserved, continuous process which controls faithful replication and division of cells. Single-cell technologies have enabled increasingly precise measurements of the cell cycle as both as a biological process of interest and as a possible confounding factor. Despite its importance and conservation, there is no universally applicable approach to infer position in the cell cycle with high-resolution from single-cell RNA-seq data. Here, we present tricycle, an R/Bioconductor package,to address this challenge by leveraging key features of the biology of the cell cycle, the mathematical properties of principal component analysis of periodic functions, and the ubiquitous applicability of transfer learning. We show that tricycle can predict any cell’s position in the cell cycle regardless of the cell type, species of origin, and even sequencing assay. The accuracy of tricycle compares favorably to gold-standard experimental assays which generally require specialized measurements in specifically constructed in vitro systems. Unlike gold-standard assays, tricycle is applicable to any single-cell RNA-seq dataset. Tricycle is highly scalable, universally accurate, and eminently pertinent for atlas-level data.
2021-04-07 | GSE171636 | GEO
Project description:Building accurate predictive models of clinical multivariate time series is crucial for understanding of the patient condition, the dynamics of a disease, and clinical decision making. A challenging aspect of this process is that the model should be flexible and adaptive to reflect well patient-specific temporal behaviors and this also in the case when the available patient-specific data are sparse and short span. To address this problem we propose and develop an adaptive two-stage forecasting approach for modeling multivariate, irregularly sampled clinical time series of varying lengths. The proposed model (1) learns the population trend from a collection of time series for past patients; (2) captures individual-specific short-term multivariate variability; and (3) adapts by automatically adjusting its predictions based on new observations. The proposed forecasting model is evaluated on a real-world clinical time series dataset. The results demonstrate the benefits of our approach on the prediction tasks for multivariate, irregularly sampled clinical time series, and show that it can outperform both the population based and patient-specific time series prediction models in terms of prediction accuracy.
| S-EPMC4980099 | biostudies-literature