scholarly journals Development and validation of risk scores for all-cause mortality for the purposes of a smartphone-based ‘general health score’ application: a prospective cohort study using the UK Biobank (Preprint)

2020 ◽  
Author(s):  
Ashley K. Clift ◽  
Erwann Le Lannou ◽  
Arsi Hyvärinen ◽  
Sachin S. Shah ◽  
Devin D. Dunn ◽  
...  
Keyword(s):  
Machine Learning ◽  
Cohort Study ◽  
Cox Model ◽  
Statistical Modelling ◽  
Learning Approaches ◽  
Uk Biobank ◽  
Learning Models ◽  
C Statistic ◽  
All Cause Mortality ◽  
Machine Learning Models

BACKGROUND Even though established links exist between individuals behaviours and potentially adverse health outcomes, to date either univariate, simpler models or multivariate, yet difficult to employ ones, have been developed. Such models are unlikely to be successful at capturing the wider determinants of health in the broader population. Hence, there is a need for a multidimensional, yet widely employable and accessible, way to obtain a comprehensive health metric. OBJECTIVE To develop and validate a novel, easily interpretable points-based health score ("C-Score") derived from metrics measurable using smartphone components, and iterations thereof that utilise statistical modelling and machine learning approaches. METHODS Comprehensive literature review to identify suitable predictor variables for inclusion in a first iteration points-based model. This was followed by a prospective cohort study in a UK Biobank population for the purposes of validating the C-Score, and developing and comparatively validating variations of the score using statistical/machine learning models to assess the balance between expediency and ease of interpretability versus model complexity. Primary and secondary outcome measures: Discrimination of a points-based score for all-cause mortality within 10 years (Harrell’s c-statistic). Discrimination and calibration of Cox proportional hazards models and machine learning models that incorporate C-Score values (or raw data inputs) and other predictors to predict risk of all-cause mortality within 10 years. RESULTS The cohort comprised 420,560 individuals. During a cohort follow-up of 4,526,452 person-years, there were 16,188 deaths from any cause (3.85%). The points-based model had good discrimination (c-statistic = 0.66). There was a 31% relative reduction in risk of all-cause mortality per decile of increasing C-Score (hazard ratio: 0.69, 95% CI: 0.663 to 0.675). A Cox model integrating age and C-Score had improved discrimination (8% percentage points, c-statistic = 0.74) and good calibration. Machine learning approaches did not offer improved discrimination over statistical modelling. CONCLUSIONS The novel health metric (‘C-Score’) has good predictive capabilities for all-cause mortality within 10 years. Embedding C-Score within a smartphone application may represent a useful tool for democratised, individualised health risk prediction. A simple Cox model using C-Score and age optimally balances parsimony and accuracy of risk predictions and could be used to produce absolute risk estimations for application users.

scholarly journals Development and validation of risk scores for all-cause mortality for the purposes of a smartphone-based ‘general health score’ application: a prospective cohort study using the UK Biobank

2020 ◽  
Author(s):  
Ashley K. Clift ◽  
Erwann Le Lannou ◽  
Christian P. Tighe ◽  
Sachin S. Shah ◽  
Matthew Beatty ◽  
...  
Keyword(s):  
Machine Learning ◽  
Cohort Study ◽  
Cox Model ◽  
Statistical Modelling ◽  
Learning Approaches ◽  
Uk Biobank ◽  
Learning Models ◽  
C Statistic ◽  
All Cause Mortality ◽  
Machine Learning Models

AbstractBackgroundEven though established links exist between individuals behaviours and potentially adverse health outcomes, to date either univariate, simpler models or multivariate, yet difficult to employ ones, have been developed. Such models are unlikely to be successful at capturing the wider determinants of health in the broader population. Hence, there is a need for a multidimensional, yet widely employable and accessible, way to obtain a comprehensive health metric.ObjectiveTo develop and validate a novel, easily interpretable points-based health score (“C-Score”) derived from metrics measurable using smartphone components, and iterations thereof that utilise statistical modelling and machine learning approaches.MethodsComprehensive literature review to identify suitable predictor variables for inclusion in a first iteration points-based model. This was followed by a prospective cohort study in a UK Biobank population for the purposes of validating the C-Score, and developing and comparatively validating variations of the score using statistical/machine learning models to assess the balance between expediency and ease of interpretability versus model complexity. Primary and secondary outcome measures: Discrimination of a points-based score for all-cause mortality within 10 years (Harrell’s c-statistic). Discrimination and calibration of Cox proportional hazards models and machine learning models that incorporate C-Score values (or raw data inputs) and other predictors to predict risk of all-cause mortality within 10 years.ResultsThe cohort comprised 420,560 individuals. During a cohort follow-up of 4,526,452 person-years, there were 16,188 deaths from any cause (3.85%). The points-based model had good discrimination (c-statistic = 0.66). There was a 31% relative reduction in risk of all-cause mortality per decile of increasing C-Score (hazard ratio: 0.69, 95% CI: 0.663 to 0.675). A Cox model integrating age and C-Score had improved discrimination (8% percentage points, c-statistic = 0.74) and good calibration. Machine learning approaches did not offer improved discrimination over statistical modelling.ConclusionsThe novel health metric (‘C-Score’) has good predictive capabilities for all-cause mortality within 10 years. Embedding C-Score within a smartphone application may represent a useful tool for democratised, individualised health risk prediction. A simple Cox model using C-Score and age optimally balances parsimony and accuracy of risk predictions and could be used to produce absolute risk estimations for application users.

Machine learning approaches for predicting difficult airway and first-pass success in the emergency department: A multiple prospective observational study (Preprint)

2021 ◽  
Author(s):  
Syunsuke Yamanaka ◽  
Tadahiro Goto ◽  
Koji Morikawa ◽  
Hiroko Watase ◽  
Hiroshi Okamoto ◽  
...  
Keyword(s):  
Machine Learning ◽  
Random Forest ◽  
Difficult Airway ◽  
Nearest Neighbor ◽  
Learning Approaches ◽  
Learning Models ◽  
Discrimination Ability ◽  
C Statistic ◽  
First Pass ◽  
Machine Learning Models

BACKGROUND There is still room for improvement in the modified LEMON criteria for difficult airway prediction and no prediction tool for first-pass success in the ED. OBJECTIVE We applied modern machine learning approaches to predict difficult airway and first-pass success. METHODS In a multicenter prospective study that enrolled consecutive patients who underwent tracheal intubation in the 13 EDs, we developed seven machine learning models (e.g., random forest model) using routinely collected data (e.g., demographics, initial airway assessment). The outcomes were difficult airway and first-pass success. Model performance was evaluated by c-statistics, calibration slope, and association measures (e.g., sensitivity) in the test set (randomly-selected 20% of data). Their performance was compared with the modified LEMON criteria for the difficult airway and with a logistic regression model for the first-pass success. RESULTS Of 10,741 patients who underwent intubation, 543 patients (5%) had a difficult airway, and 7,690 patients (71%) had first-pass success. In predicting the difficult airway, machine learning models—except for k-point nearest neighbor and multilayer perceptron—had a higher discrimination ability compared with the modified LEMON criteria (P<0.01). For example, the ensemble method had the highest c-statistic (0.74 vs 0.62 in the modified LEMON criteria; P <0.01). For the first-pass success, machine learning models—except for k-point nearest neighbor and random forest models—had a higher discrimination ability. In particular, the ensemble model had the highest c-statistic (0.81 vs 0.76 in the reference regression; P <0.01). CONCLUSIONS Machine learning models demonstrated a greater ability in predicting difficult airway and first-pass success in the ED.

scholarly journals Development and Validation of Risk Scores for All-Cause Mortality for a Smartphone-Based “General Health Score” App: Prospective Cohort Study Using the UK Biobank

10.2196/25655 ◽  
2021 ◽  
Vol 9 (2) ◽  
pp. e25655
Author(s):  
Ashley K Clift ◽  
Erwann Le Lannou ◽  
Christian P Tighe ◽  
Sachin S Shah ◽  
Matthew Beatty ◽  
...  
Keyword(s):  
Cohort Study ◽  
Statistical Modeling ◽  
Prospective Cohort Study ◽  
Prospective Cohort ◽  
General Health ◽  
Cox Model ◽  
Uk Biobank ◽  
Health Score ◽  
C Statistic ◽  
All Cause Mortality

Background Given the established links between an individual’s behaviors and lifestyle factors and potentially adverse health outcomes, univariate or simple multivariate health metrics and scores have been developed to quantify general health at a given point in time and estimate risk of negative future outcomes. However, these health metrics may be challenging for widespread use and are unlikely to be successful at capturing the broader determinants of health in the general population. Hence, there is a need for a multidimensional yet widely employable and accessible way to obtain a comprehensive health metric. Objective The objective of the study was to develop and validate a novel, easily interpretable, points-based health score (“C-Score”) derived from metrics measurable using smartphone components and iterations thereof that utilize statistical modeling and machine learning (ML) approaches. Methods A literature review was conducted to identify relevant predictor variables for inclusion in the first iteration of a points-based model. This was followed by a prospective cohort study in a UK Biobank population for the purposes of validating the C-Score and developing and comparatively validating variations of the score using statistical and ML models to assess the balance between expediency and ease of interpretability and model complexity. Primary and secondary outcome measures were discrimination of a points-based score for all-cause mortality within 10 years (Harrell c-statistic) and discrimination and calibration of Cox proportional hazards models and ML models that incorporate C-Score values (or raw data inputs) and other predictors to predict the risk of all-cause mortality within 10 years. Results The study cohort comprised 420,560 individuals. During a cohort follow-up of 4,526,452 person-years, there were 16,188 deaths from any cause (3.85%). The points-based model had good discrimination (c-statistic=0.66). There was a 31% relative reduction in risk of all-cause mortality per decile of increasing C-Score (hazard ratio of 0.69, 95% CI 0.663-0.675). A Cox model integrating age and C-Score had improved discrimination (8 percentage points; c-statistic=0.74) and good calibration. ML approaches did not offer improved discrimination over statistical modeling. Conclusions The novel health metric (“C-Score”) has good predictive capabilities for all-cause mortality within 10 years. Embedding the C-Score within a smartphone app may represent a useful tool for democratized, individualized health risk prediction. A simple Cox model using C-Score and age balances parsimony and accuracy of risk predictions and could be used to produce absolute risk estimations for app users.

Machine learning approaches to understand and predict rate constants for organic processes in mixtures containing ionic liquids

2021 ◽  
Vol 23 (4) ◽  
pp. 2742-2752
Author(s):  
Tamar L. Greaves ◽  
Karin S. Schaffarczyk McHale ◽  
Raphael F. Burkart-Radke ◽  
Jason B. Harper ◽  
Tu C. Le
Keyword(s):  
Machine Learning ◽  
Ionic Liquids ◽  
Rate Constants ◽  
Learning Approaches ◽  
Learning Models ◽  
Organic Reaction ◽  
Machine Learning Models ◽  
Selection Of

Machine learning models were developed for an organic reaction in ionic liquids and validated on a selection of ionic liquids.

EVALUATING INTONATIONAL FEATURES FOR EMOTION RECOGNITION FROM SPEECH

2007 ◽  
Vol 16 (06) ◽  
pp. 1001-1014 ◽  
Author(s):  
PANAGIOTIS ZERVAS ◽  
IOSIF MPORAS ◽  
NIKOS FAKOTAKIS ◽  
GEORGE KOKKINAKIS
Keyword(s):  
Machine Learning ◽  
Decision Tree ◽  
Emotion Recognition ◽  
Bayesian Learning ◽  
Experimental Results ◽  
Speech Signals ◽  
Learning Approaches ◽  
Learning Models ◽  
C4.5 Decision Tree ◽  
Machine Learning Models

This paper presents and discusses the problem of emotion recognition from speech signals with the utilization of features bearing intonational information. In particular parameters extracted from Fujisaki's model of intonation are presented and evaluated. Machine learning models were build with the utilization of C4.5 decision tree inducer, instance based learner and Bayesian learning. The datasets utilized for the purpose of training machine learning models were extracted from two emotional databases of acted speech. Experimental results showed the effectiveness of Fujisaki's model attributes since they enhanced the recognition process for most of the emotion categories and learning approaches helping to the segregation of emotion categories.

scholarly journals Sentiment Analysis and Topic Modeling on Tweets about Online Education during COVID-19

2021 ◽  
Vol 11 (18) ◽  
pp. 8438
Author(s):  
Muhammad Mujahid ◽  
Ernesto Lee ◽  
Furqan Rustam ◽  
Patrick Bernard Washington ◽  
Saleem Ullah ◽  
...  
Keyword(s):  
Machine Learning ◽  
Deep Learning ◽  
Online Education ◽  
Sentiment Analysis ◽  
Topic Modeling ◽  
Support Vector ◽  
Learning Approaches ◽  
Learning Models ◽  
E Learning ◽  
Machine Learning Models

Amid the worldwide COVID-19 pandemic lockdowns, the closure of educational institutes leads to an unprecedented rise in online learning. For limiting the impact of COVID-19 and obstructing its widespread, educational institutions closed their campuses immediately and academic activities are moved to e-learning platforms. The effectiveness of e-learning is a critical concern for both students and parents, specifically in terms of its suitability to students and teachers and its technical feasibility with respect to different social scenarios. Such concerns must be reviewed from several aspects before e-learning can be adopted at such a larger scale. This study endeavors to investigate the effectiveness of e-learning by analyzing the sentiments of people about e-learning. Due to the rise of social media as an important mode of communication recently, people’s views can be found on platforms such as Twitter, Instagram, Facebook, etc. This study uses a Twitter dataset containing 17,155 tweets about e-learning. Machine learning and deep learning approaches have shown their suitability, capability, and potential for image processing, object detection, and natural language processing tasks and text analysis is no exception. Machine learning approaches have been largely used both for annotation and text and sentiment analysis. Keeping in view the adequacy and efficacy of machine learning models, this study adopts TextBlob, VADER (Valence Aware Dictionary for Sentiment Reasoning), and SentiWordNet to analyze the polarity and subjectivity score of tweets’ text. Furthermore, bearing in mind the fact that machine learning models display high classification accuracy, various machine learning models have been used for sentiment classification. Two feature extraction techniques, TF-IDF (Term Frequency-Inverse Document Frequency) and BoW (Bag of Words) have been used to effectively build and evaluate the models. All the models have been evaluated in terms of various important performance metrics such as accuracy, precision, recall, and F1 score. The results reveal that the random forest and support vector machine classifier achieve the highest accuracy of 0.95 when used with Bow features. Performance comparison is carried out for results of TextBlob, VADER, and SentiWordNet, as well as classification results of machine learning models and deep learning models such as CNN (Convolutional Neural Network), LSTM (Long Short Term Memory), CNN-LSTM, and Bi-LSTM (Bidirectional-LSTM). Additionally, topic modeling is performed to find the problems associated with e-learning which indicates that uncertainty of campus opening date, children’s disabilities to grasp online education, and lagging efficient networks for online education are the top three problems.

scholarly journals Machine Learning and Prediction of All-Cause Mortality among Chinese Older Adults

2021 ◽  
Author(s):  
Xurui Jin ◽  
Yiyang Sun ◽  
Tinglong Zhu ◽  
Yu Leng ◽  
Shuyi Guan ◽  
...  
Keyword(s):  
Machine Learning ◽  
Prediction Model ◽  
Regression Model ◽  
Predictive Value ◽  
Cox Regression ◽  
Brier Score ◽  
Baseline Survey ◽  
Learning Models ◽  
All Cause Mortality ◽  
Machine Learning Models

AbstractBackground and aimMortality risk stratification was vital for targeted intervention. This study aimed at building the prediction model of all-cause mortality among Chinese dwelling elderly with different methods including regression models and machine learning models and to compare the performance of machine learning models with regression model on predicting mortality. Additionally, this study also aimed at ranking the predictors of mortality within different models and comparing the predictive value of different groups of predictors using the model with best performance.MethodI used data from the sub-study of Chinese Longitudinal Healthy Longevity Survey (CLHLS) - Healthy Ageing and Biomarkers Cohort Study (HABCS). The baseline survey of HABCS was conducted in 2008 and covered similar domains that CLHLS has investigated and shared the sampling strategy. The follow-up of HABCS was conducted every 2-3 years till 2018.The analysis sample included 2,448 participants from HABCS. I used totally 117 predictors to build the prediction model for survival using the HABCS cohort, including 61 questionnaire, 41 biomarker and 15 genetics predictors. Four models were built (XG-Boost, random survival forest [RSF], Cox regression with all variables and Cox-backward). We used C-index and integrated Brier score (Brier score for the two years’ mortality prediction model) to evaluate the performance of those models.ResultsThe XG-Boost model and RSF model shows slightly better predictive performance than Cox models and Cox-backward models based on the C-index and integrated Brier score in predicting surviving. Age. Activity of daily living and Mini-Mental State Examination score were identified as the top 3 predictors in the XG-Boost and RSF models. Biomarker and questionnaire predictors have a similar predictive value, while genetic predictors have no addictive predictive value when combined with questionnaire or biomarker predictors.ConclusionIn this work, it is shown that machine learning techniques can be a useful tool for both prediction and its performance sightly outperformed the regression model in predicting survival.

scholarly journals Significance Of Multilayer Perceptron Model For Early Detection Of Diabetes Over Ml Methods

2021 ◽  
Vol 23 (08) ◽  
pp. 148-160
Author(s):  
Dr. V.Vasudha Rani ◽  
◽  
Dr. G. Vasavi ◽  
Dr. K.R.N Kiran Kumar ◽  
◽  
...  
Keyword(s):  
Machine Learning ◽  
Multilayer Perceptron ◽  
Predictive Analytics ◽  
Early Stage ◽  
Feature Selection Method ◽  
Health Condition ◽  
Performance Comparison ◽  
Learning Approaches ◽  
Learning Models ◽  
Machine Learning Models

Diabetes is one of the chronicdiseases in the world. Millions of people are suffering with several other health issues caused by diabetes, every year. Diabetes has got three stages such as type2, type1 and insulin. Curing of diabetes disease at later stages is practically difficult. Here in this paper, we proposed a DNN model and its performance comparison with some of the machine learning models to predict the disease at an earlystage based on the current health condition of the patient. An artificial neural network (ANN) is a predictive model designed to work the same way a human brain does and works better with larger datasets. Having the concept of hidden layers, neural networks work better at predictive analytics and can make predictions with more accuracy. Novelty of this work lies in integration of feature selection method used to optimize the Multilayer Perceptron (MLP) to reduce the number of required input attributes. The results achieved using this method and several conventional machines learning approaches such as Logistic Regression, Random Forest Classifier (RFC) are compared. The proposed DNN method is proved to show better accuracy than Machine learning models for early stage detection of diabetes. This paper work is applicable to clinical support as a tool for making predecisions by the doctors and physicians.

scholarly journals FedSpeech: Federated Text-to-Speech with Continual Learning

2021 ◽  
Author(s):  
Ziyue Jiang ◽  
Yi Ren ◽  
Ming Lei ◽  
Zhou Zhao
Keyword(s):  
Machine Learning ◽  
Global Model ◽  
Learning Approaches ◽  
Learning Models ◽  
Text To Speech ◽  
Training Samples ◽  
Task Training ◽  
Collaborative Training ◽  
Machine Learning Models ◽  
Continual Learning

Federated learning enables collaborative training of machine learning models under strict privacy restrictions and federated text-to-speech aims to synthesize natural speech of multiple users with a few audio training samples stored in their devices locally. However, federated text-to-speech faces several challenges: very few training samples from each speaker are available, training samples are all stored in local device of each user, and global model is vulnerable to various attacks. In this paper, we propose a novel federated learning architecture based on continual learning approaches to overcome the difficulties above. Specifically, 1) we use gradual pruning masks to isolate parameters for preserving speakers' tones; 2) we apply selective masks for effectively reusing knowledge from tasks; 3) a private speaker embedding is introduced to keep users' privacy. Experiments on a reduced VCTK dataset demonstrate the effectiveness of FedSpeech: it nearly matches multi-task training in terms of multi-speaker speech quality; moreover, it sufficiently retains the speakers' tones and even outperforms the multi-task training in the speaker similarity experiment.

scholarly journals Consistency of variety of machine learning and statistical models in predicting clinical risks of individual patients: longitudinal cohort study using cardiovascular disease as exemplar

BMJ ◽  
2020 ◽  
pp. m3919
Author(s):  
Yan Li ◽  
Matthew Sperrin ◽  
Darren M Ashcroft ◽  
Tjeerd Pieter van Staa
Keyword(s):  
Neural Network ◽  
Machine Learning ◽  
Cardiovascular Disease ◽  
Cohort Study ◽  
Statistical Models ◽  
Model Performance ◽  
Population Level ◽  
Survival Models ◽  
Learning Models ◽  
Machine Learning Models

AbstractObjectiveTo assess the consistency of machine learning and statistical techniques in predicting individual level and population level risks of cardiovascular disease and the effects of censoring on risk predictions.DesignLongitudinal cohort study from 1 January 1998 to 31 December 2018.Setting and participants3.6 million patients from the Clinical Practice Research Datalink registered at 391 general practices in England with linked hospital admission and mortality records.Main outcome measuresModel performance including discrimination, calibration, and consistency of individual risk prediction for the same patients among models with comparable model performance. 19 different prediction techniques were applied, including 12 families of machine learning models (grid searched for best models), three Cox proportional hazards models (local fitted, QRISK3, and Framingham), three parametric survival models, and one logistic model.ResultsThe various models had similar population level performance (C statistics of about 0.87 and similar calibration). However, the predictions for individual risks of cardiovascular disease varied widely between and within different types of machine learning and statistical models, especially in patients with higher risks. A patient with a risk of 9.5-10.5% predicted by QRISK3 had a risk of 2.9-9.2% in a random forest and 2.4-7.2% in a neural network. The differences in predicted risks between QRISK3 and a neural network ranged between –23.2% and 0.1% (95% range). Models that ignored censoring (that is, assumed censored patients to be event free) substantially underestimated risk of cardiovascular disease. Of the 223 815 patients with a cardiovascular disease risk above 7.5% with QRISK3, 57.8% would be reclassified below 7.5% when using another model.ConclusionsA variety of models predicted risks for the same patients very differently despite similar model performances. The logistic models and commonly used machine learning models should not be directly applied to the prediction of long term risks without considering censoring. Survival models that consider censoring and that are explainable, such as QRISK3, are preferable. The level of consistency within and between models should be routinely assessed before they are used for clinical decision making.

Sign in / Sign up

Export Citation Format

Share Document