Deep-Learning Approach to Predict Survival Outcomes Using Wearable Actigraphy Device Among End-Stage Cancer Patients.
Ontology highlight
ABSTRACT:
SUBMITTER: Yang TY
PROVIDER: S-EPMC8695752 | biostudies-literature |
REPOSITORIES: biostudies-literature
Similar Datasets
Project description:Unobtrusive home sleep monitoring using wrist-worn wearable photoplethysmography (PPG) could open the way for better sleep disorder screening and health monitoring. However, PPG is rarely included in large sleep studies with gold-standard sleep annotation from polysomnography. Therefore, training data-intensive state-of-the-art deep neural networks is challenging. In this work a deep recurrent neural network is first trained using a large sleep data set with electrocardiogram (ECG) data (292 participants, 584 recordings) to perform 4-class sleep stage classification (wake, rapid-eye-movement, N1/N2, and N3). A small part of its weights is adapted to a smaller, newer PPG data set (60 healthy participants, 101 recordings) through three variations of transfer learning. Best results (Cohen's kappa of 0.65 ± 0.11, accuracy of 76.36 ± 7.57%) were achieved with the domain and decision combined transfer learning strategy, significantly outperforming the PPG-trained and ECG-trained baselines. This performance for PPG-based 4-class sleep stage classification is unprecedented in literature, bringing home sleep stage monitoring closer to clinical use. The work demonstrates the merit of transfer learning in developing reliable methods for new sensor technologies by reusing similar, older non-wearable data sets. Further study should evaluate our approach in patients with sleep disorders such as insomnia and sleep apnoea.
| S-EPMC8443610 | biostudies-literature
Project description:BACKGROUND:Data collected by an actigraphy device worn on the wrist or waist can provide objective measurements for studies related to physical activity; however, some data may contain intervals where values are missing. In previous studies, statistical methods have been applied to impute missing values on the basis of statistical assumptions. Deep learning algorithms, however, can learn features from the data without any such assumptions and may outperform previous approaches in imputation tasks. OBJECTIVE:The aim of this study was to impute missing values in data using a deep learning approach. METHODS:To develop an imputation model for missing values in accelerometer-based actigraphy data, a denoising convolutional autoencoder was adopted. We trained and tested our deep learning-based imputation model with the National Health and Nutrition Examination Survey data set and validated it with the external Korea National Health and Nutrition Examination Survey and the Korean Chronic Cerebrovascular Disease Oriented Biobank data sets which consist of daily records measuring activity counts. The partial root mean square error and partial mean absolute error of the imputed intervals (partial RMSE and partial MAE, respectively) were calculated using our deep learning-based imputation model (zero-inflated denoising convolutional autoencoder) as well as using other approaches (mean imputation, zero-inflated Poisson regression, and Bayesian regression). RESULTS:The zero-inflated denoising convolutional autoencoder exhibited a partial RMSE of 839.3 counts and partial MAE of 431.1 counts, whereas mean imputation achieved a partial RMSE of 1053.2 counts and partial MAE of 545.4 counts, the zero-inflated Poisson regression model achieved a partial RMSE of 1255.6 counts and partial MAE of 508.6 counts, and Bayesian regression achieved a partial RMSE of 924.5 counts and partial MAE of 605.8 counts. CONCLUSIONS:Our deep learning-based imputation model performed better than the other methods when imputing missing values in actigraphy data.
| S-EPMC7413283 | biostudies-literature
Project description:Recent advances of wearable computing technology have allowed continuous health monitoring in large observational studies and clinical trials. Examples of data collected by wearable devices include minute-by-minute physical activity proxies measured by accelerometers or heart rate. The analysis of data generated by wearable devices has so far been quite limited to crude summaries, for example, the mean activity count over the day. To better utilize the full data and account for the dynamics of activity level in the time domain, we introduce a two-stage regression model for the minute-by-minute physical activity proxy data. The model allows for both time-varying parameters and time-invariant parameters, which helps capture both the transition dynamics between active/inactive periods (Stage 1) and the activity intensity dynamics during active periods (Stage 2). The approach extends methods developed for zero-inflated Poisson data to account for the high-dimensionality and time-dependence of the high density data generated by wearable devices. Methods are motivated by and applied to the Baltimore Longitudinal Study of Aging.
| S-EPMC5893449 | biostudies-literature
Project description:BackgroundProfound heterogeneity in prognosis has been observed in colorectal cancer (CRC) patients with intermediate levels of disease (stage II-III), advocating the identification of valuable biomarkers that could improve the prognostic stratification. This study aims to develop a deep learning-based pipeline for fully automatic quantification of immune infiltration within the stroma region on immunohistochemical (IHC) whole-slide images (WSIs) and further analyze its prognostic value in CRC.MethodsPatients from two independent cohorts were divided into three groups: the development group (N = 200), the internal (N = 134), and the external validation group (N = 90). We trained a convolutional neural network for tissue classification of CD3 and CD8 stained WSIs. A scoring system, named stroma-immune score, was established by quantifying the density of CD3+ and CD8+ T-cells infiltration in the stroma region.ResultsPatients with higher stroma-immune scores had much longer survival. In the development group, 5-year survival rates of the low and high scores were 55.7% and 80.8% (hazard ratio [HR] for high vs. low 0.39, 95% confidence interval [CI] 0.24-0.63, P < 0.001). These results were confirmed in the internal and external validation groups with 5-year survival rates of low and high scores were 57.1% and 78.8%, 63.9% and 88.9%, respectively (internal: HR for high vs. low 0.49, 95% CI 0.28-0.88, P = 0.017; external: HR for high vs. low 0.35, 95% CI 0.15-0.83, P = 0.018). The combination of stroma-immune score and tumor-node-metastasis (TNM) stage showed better discrimination ability for survival prediction than using the TNM stage alone.ConclusionsWe proposed a stroma-immune score via a deep learning-based pipeline to quantify CD3+ and CD8+ T-cells densities within the stroma region on WSIs of CRC and further predict survival.
| S-EPMC8557607 | biostudies-literature
Project description:The purpose of this study was to assess the feasibility of machine learning (ML) in predicting the risk of end-stage kidney disease (ESKD) from patients with chronic kidney disease (CKD). Data were obtained from a longitudinal CKD cohort. Predictor variables included patients' baseline characteristics and routine blood test results. The outcome of interest was the presence or absence of ESKD by the end of 5 years. Missing data were imputed using multiple imputation. Five ML algorithms, including logistic regression, naïve Bayes, random forest, decision tree, and K-nearest neighbors were trained and tested using fivefold cross-validation. The performance of each model was compared to that of the Kidney Failure Risk Equation (KFRE). The dataset contained 748 CKD patients recruited between April 2006 and March 2008, with the follow-up time of 6.3 ± 2.3 years. ESKD was observed in 70 patients (9.4%). Three ML models, including the logistic regression, naïve Bayes and random forest, showed equivalent predictability and greater sensitivity compared to the KFRE. The KFRE had the highest accuracy, specificity, and precision. This study showed the feasibility of ML in evaluating the prognosis of CKD based on easily accessible features. Three ML models with adequate performance and sensitivity scores suggest a potential use for patient screenings. Future studies include external validation and improving the models with additional predictor variables.
| S-EPMC9120106 | biostudies-literature
Project description:The blood-brain barrier plays a crucial role in regulating the passage of 98% of the compounds that enter the central nervous system (CNS). Compounds with high permeability must be identified to enable the synthesis of brain medications for the treatment of various brain diseases, such as Parkinson's, Alzheimer's, and brain tumors. Throughout the years, several models have been developed to solve this problem and have achieved acceptable accuracy scores in predicting compounds that penetrate the blood-brain barrier. However, predicting compounds with "low" permeability has been a challenging task. In this study, we present a deep learning (DL) classification model to predict blood-brain barrier permeability. The proposed model addresses the fundamental issues presented in former models: high dimensionality, class imbalances, and low specificity scores. We address these issues to enhance the high-dimensional, imbalanced dataset before developing the classification model: the imbalanced dataset is addressed using oversampling techniques and the high dimensionality using a non-linear dimensionality reduction technique known as kernel principal component analysis (KPCA). This technique transforms the high-dimensional dataset into a low-dimensional Euclidean space while retaining invaluable information. For the classification task, we developed an enhanced feed-forward deep learning model and a convolutional neural network model. In terms of specificity scores (i.e., predicting compounds with low permeability), the results obtained by the enhanced feed-forward deep learning model outperformed those obtained by other models in the literature that were developed using the same technique. In addition, the proposed convolutional neural network model surpassed models used in other studies in multiple accuracy measures, including overall accuracy and specificity. The proposed approach solves the problem inevitably faced with obtaining low specificity resulting in high false positive rate.
| S-EPMC8205267 | biostudies-literature
Project description:Study objectivesTo compare the quality and consistency in sleep measurement of a consumer wearable device and a research-grade actigraph with polysomnography (PSG) in adolescents.MethodsFifty-eight healthy adolescents (aged 15-19 years; 30 males) underwent overnight PSG while wearing both a Fitbit Alta HR and a Philips Respironics Actiwatch 2 (AW2) for 5 nights, with either 5 hours or 6.5 hours time in bed (TIB) and for 4 nights with 9 hours TIB. AW2 data were evaluated using two different wake and immobility thresholds. Discrepancies in estimated total sleep time (TST) and wake after sleep onset (WASO) between devices and PSG, as well as epoch-by-epoch agreements in sleep/wake classification, were assessed. Fitbit-generated sleep staging was compared to PSG.ResultsFitbit and AW2 under default settings similarly underestimated TST and overestimated WASO (TST: medium setting (M10) ≤ 38 minutes, Fitbit ≤ 47 minutes; WASO: M10 ≤ 38 minutes; Fitbit ≤ 42 minutes). AW2 at the high motion threshold setting provided readings closest to PSG (TST: ≤ 12 minutes; WASO: ≤ 18 minutes). Sensitivity for detecting sleep was ≥ 90% for both wearable devices and further improved to 95% by using the high threshold (H5) setting for the AW2 (0.95). Wake detection specificity was highest in Fitbit (≥ 0.88), followed by the AW2 at M10 (≥ 0.80) and H5 thresholds (≤ 0.73). In addition, Fitbit inconsistently estimated stage N1 + N2 sleep depending on TIB, underestimated stage N3 sleep (21-46 min), but was comparable to PSG for rapid eye movement sleep. Fitbit sensitivity values for the detection of N1 + N2, N3 and rapid eye movement sleep were ≥ 0.68, ≥ 0.50, and ≥ 0.72, respectively.ConclusionsA consumer-grade wearable device can measure sleep duration as well as a research actigraph. However, sleep staging would benefit from further refinement before these methods can be reliably used for adolescents.Clinical trial registrationRegistry: ClinicalTrials.gov; Title: The Cognitive and Metabolic Effects of Sleep Restriction in Adolescents; Identifier: NCT03333512; URL: https://clinicaltrials.gov/ct2/show/NCT03333512.CitationLee XK, Chee NIYN, Ong JL, Teo TB, van Rijn E, Lo JC, Chee MWL. Validation of a consumer sleep wearable device with actigraphy and polysomnography in adolescents across sleep opportunity manipulations. J Clin Sleep Med. 2019;15(9):1337-1346.
| S-EPMC6760396 | biostudies-literature
Project description:Phosphorylation, which is mediated by protein kinases and opposed by protein phosphatases, is an important post-translational modification that regulates many cellular processes, including cellular metabolism, cell migration, and cell division. Due to its essential role in cellular physiology, a great deal of attention has been devoted to identifying sites of phosphorylation on cellular proteins and understanding how modification of these sites affects their cellular functions. This has led to the development of several computational methods designed to predict sites of phosphorylation based on a protein's primary amino acid sequence. In contrast, much less attention has been paid to dephosphorylation and its role in regulating the phosphorylation status of proteins inside cells. Indeed, to date, dephosphorylation site prediction tools have been restricted to a few tyrosine phosphatases. To fill this knowledge gap, we have employed a transfer learning strategy to develop a deep learning-based model to predict sites that are likely to be dephosphorylated. Based on independent test results, our model, which we termed DTL-DephosSite, achieved efficiency scores for phosphoserine/phosphothreonine residues of 84%, 84% and 0.68 with respect to sensitivity (SN), specificity (SP) and Matthew's correlation coefficient (MCC). Similarly, DTL-DephosSite exhibited efficiency scores of 75%, 88% and 0.64 for phosphotyrosine residues with respect to SN, SP, and MCC.
| S-EPMC8264445 | biostudies-literature
Project description:Protein-ligand binding prediction has extensive biological significance. Binding affinity helps in understanding the degree of protein-ligand interactions and is a useful measure in drug design. Protein-ligand docking using virtual screening and molecular dynamic simulations are required to predict the binding affinity of a ligand to its cognate receptor. Performing such analyses to cover the entire chemical space of small molecules requires intense computational power. Recent developments using deep learning have enabled us to make sense of massive amounts of complex data sets where the ability of the model to "learn" intrinsic patterns in a complex plane of data is the strength of the approach. Here, we have incorporated convolutional neural networks to find spatial relationships among data to help us predict affinity of binding of proteins in whole superfamilies toward a diverse set of ligands without the need of a docked pose or complex as user input. The models were trained and validated using a stringent methodology for feature extraction. Our model performs better in comparison to some existing methods used widely and is suitable for predictions on high-resolution protein crystal (⩽2.5 Å) and nonpeptide ligand as individual inputs. Our approach to network construction and training on protein-ligand data set prepared in-house has yielded significant insights. We have also tested DEELIG on few COVID-19 main protease-inhibitor complexes relevant to the current public health scenario. DEELIG-based predictions can be incorporated in existing databases including RSCB PDB, PDBMoad, and PDBbind in filling missing binding affinity data for protein-ligand complexes.
| S-EPMC8274096 | biostudies-literature
Project description:Early diagnosis of pathological markers can significantly shorten the rate of viral transmission, reduce the probability of infection, and improve the cure rate of diseases. Therefore, analytical techniques for identifying pathological markers and environmental toxicants have received considerable attention from researchers worldwide. However, the most popular techniques used in clinical settings involve expensive precision instruments and complex detection processes. Thus, a simpler, more efficient, rapid, and intelligent means of analysis must be urgently developed. Electrochemical biosensors have the advantages of simple processing, low cost, low sample preparation requirements, rapid analysis, easy miniaturization, and integration. Thus, they have become popular in extensive research. Machine learning is widely used in material-assisted synthesis, sensor design, and other fields owing to its powerful data analysis and simulation learning capabilities. In this study, a machine learning-assisted carbon black-graphene oxide conjugate polymer (CB-GO/CP) electrode, in conjunction with a flexible wearable device, is proposed for the smart portable detection of tyrosine (Tyr). Input feature value data are obtained for the artificial neural network (ANN) and support vector machines (SVM) model learning via multiple data collections in artificial urine and by recording the pH and temperature values. The results reveal that a machine-learning model that integrates multiple external factors is more accurate for the prediction of Tyr concentration.
| S-EPMC10407620 | biostudies-literature