Work-related Musculoskeletal disorders (MSDs) account for 60% of sickness-related absences and even permanent inability to work in the Europe.Long term impacts of MSDs include "Pain chronification" which is the transition of temporary pain into persistent pain.Preventive pain management can lower the risk of chronic pain.It is therefore important to appropriately assess pain in advance, which can assist a person in improving their fear of returning to work.In this study, we analysed pain data acquired over time by a smartphone application from a number of participants.We attempt to forecast a person's future pain levels based on his or her prior pain data.Due to the self-reported nature of the data, modelling daily pain is challenging due to the large number of missing values.For pain prediction modelling of a test subject, we employ a subset selection strategy that dynamically selects a closest subset of individuals from the training data.The similarity between the test subject and the training subjects is determined via dynamic time warping-based dissimilarity measure based on the time limited historical data until a given point in time.The pain trends of these selected subset subjects is more similar to that of the individual of interest.Then, we employ a Gaussian processes regression model for modelling the pain.We empirically test our model using a leave-one-subject-out cross validation to attain 20% improvement over state-of-the-art results in early prediction of pain.

Advances in Internet of Things (IoT) devices and in Machine Learning (ML) applications can provide valuable insights and predictions on personal health by optimizing data generation and processing. Nevertheless, the flow of data about the health status of a patient brings a variety of technical, legal and economic challenges that need to be addressed through an interdisciplinary approach.In this context, based on the action research methodology, the paper introduces an exemplary health-related activity recognition platform based on IoT, developed as a part of European-funded project Horizon 2020 in collaboration with academia and industry.The platform proposes innovative solutions on how personal healthcare data can be processed and analysed, protecting users' privacy. The main strength of the platform is the interdisciplinary approach used within a triple-helix model, involving a variety of institutions, companies and researchers from different academic fields. In this perspective, the paper shows the potential that the integration of IoT and ML models have to offer and the main challenges that still need to be addressed.

Modelling real-world time series can be challenging in the absence of sufficient data. Limited data in healthcare, can arise for several reasons, namely when the number of subjects is insufficient or the observed time series is irregularly sampled at a very low sampling frequency. This is especially true when attempting to develop personalised models, as there are typically few data points available for training from an individual subject. Furthermore, the need for early prediction (as is often the case in healthcare applications) amplifies the problem of limited availability of data. This article proposes a novel personalised technique that can be learned in the absence of sufficient data for early prediction in time series. Our novelty lies in the development of a subset selection approach to select time series that share temporal similarities with the time series of interest, commonly known as the test time series. Then, a Gaussian processes-based model is learned using the existing test data and the chosen subset to produce personalised predictions for the test subject. We will conduct experiments with univariate and multivariate data from real-world healthcare applications to show that our strategy outperforms the state-of-the-art by around 20%.

Pre-pregnancy body mass index and weight gain management are associated with pregnancy outcomes in expecting women. Poor gestational weight gain (GWG) management could increase the risk of adverse complications. These risks can be alleviated by lifestyle-based interventions if an undesired GWG trend is detected early on in the pregnancy. Current literature lacks analysis of gestational weight gain data and tracking the pregnancy over time. In this work, we collected longitudinal gestational weight gain data from women during their pregnancy and model their weight measurements to predict the end-of-pregnancy weight gain and classify it in accordance with the medically recommended guidelines. The measurement frequency of the weights is often very variable such that segments of data can be missing and the need to predict early utilising few data points complicates data modelling. We propose a Bayesian approach to forecast weight gain while effectively dealing with the limited data availability for early prediction. We validate on diverse populations from Europe and China. We show that utilising individual's data only up to mid-way through the pregnancy, our approach produces mean absolute errors of 2.45 kgs and 2.82 kgs in forecasting end-of-pregnancy weight gain on these populations respectively, whereas the best of state-of-the-art yields 8.17 and 6.60 kgs on respective populations. The proposed method can serve as a tool to keep track of an individual's pregnancy and achieve GWG goals, thus supporting the prevention of excessive or insufficient weight gain during pregnancy.

Gestational weight gain prediction in expecting women is associated with multiple risks. Manageable interventions can be devised if the weight gain can be predicted as early as possible. However, training the model to predict such weight gain requires access to centrally stored privacy sensitive weight data. Federated learning can help mitigate this problem by sending local copies of trained models instead of raw data and aggregate them at the central server. In this paper, we present a privacy preserving federated learning approach where the participating users collaboratively learn and update the global model. Furthermore, we show that this model updation can be done incrementally without having the need to store the local updates eternally. Our proposed model achieves a mean absolute error of 4.455 kgs whilst preserving privacy against 2.572 kgs achieved in a centralised approach utilising individual training data until day 140. Clinical relevance— Privacy preserving training of machine learning algorithm for early gestational weight gain prediction with minor tradeoff to performance.

Datasets in healthcare are plagued with incomplete information. Imputation is a common method to deal with missing data where the basic idea is to substitute some reasonable guess for each missing value and then continue with the analysis as if there were no missing data. However unbiased predictions based on imputed datasets can only be guaranteed when the missing mechanism is completely independent of the observed or missing data. Often, this promise is broken in healthcare dataset acquisition due to unintentional errors or response bias of the interviewees. We highlight this issue by studying extensively on an annual health survey dataset on infant mortality prediction and provide a systematic testing for such assumption. We identify such biased features using an empirical approach and show the impact of wrongful inclusion of these features on the predictive performance.Clinical relevance- We show that blind analysis along with plug and play imputation of healthcare data is a potential pitfall that clinicians and researchers want to avoid in finding important markers of disease.

Objective: Atrial fibrillation (AF) and other types of abnormal heart rhythm are related to multiple fatal cardiovascular diseases that affect the quality of human life. Hence the development of an automated robust method that can reliably detect AF, in addition to other non-sinus and sinus rhythms, would be a valuable addition to medicine. The present study focuses on developing an algorithm for the classification of short, single-lead electrocardiogram (ECG) recordings into normal, AF, other abnormal rhythms and noisy classes. Approach: The proposed classification framework presents a two-layer, three-node architecture comprising binary classifiers. PQRST markers are detected on each ECG recording, followed by noise removal using a spectrogram power based novel adaptive thresholding scheme. Next, a feature pool comprising time, frequency, morphological and statistical domain ECG features is extracted for the classification task. At each node of the classification framework, suitable feature subsets, identified through feature ranking and dimension reduction, are selected for use. Adaptive boosting is selected as the classifier for the present case. The training data comprises 8528 ECG recordings provided under the PhysioNet 2017 Challenge. F1 scores averaged across the three non-noisy classes are taken as the performance metric. Main result: The final five-fold cross-validation score achieved by the proposed framework on the training data has high accuracy with low variance (0.8254 +/- 0.0043). Significance: Further, the proposed algorithm has achieved joint first place in the PhysioNet/Computing in Cardiology Challenge 2017 with a score of 0.83 computed on a hidden test dataset.

Excessive or inadequate Gestational Weight Gain (GWG) is considered to not only put the mothers, but also the infants at increased risks with a number of adverse outcomes. In this paper, we use self-reported weight measurements from the early days of pregnancy to predict and classify the end-of-pregnancy weight gain into an underweight, normal or obese category in accordance with the Institute of Medicine recommended guidelines. Self-reported weight measurements suffer from issues such as lack of enough data and non-uniformity. We propose and compare two novel parametric and non-parametric approaches that utilise self-training data along with population data to tackle limited data availability. We, dynamically find the subset of closest time series from the population weight-gain data to a given subject. Then, a non-parametric Gaussian Process (GP) regression model, learnt on the selected subset is used to forecast the self-reported weight measurements of given subject. Our novel approach produces mean absolute error (MAE) of 2.572 kgs in forecasting end-of-pregnancy weight gain and achieves weight-category-classification accuracy of 63.75% mid-way through the pregnancy, whereas a state-of-the-art approach is only 53.75% accurate and produces high MAE of 16.22 kgs. Our method ensures reliable prediction of the end-of-pregnancy weight gain using few data points and can assist in early intervention that can prevent gaining or losing excessive weight during pregnancy.

Early gestational weight gain prediction can help expecting women overcome several associated risks. However, training the model requires access to centrally stored privacy sensitive weight and other meta-data. In this demo, we present a privacy preserving federated learning approach where we train a global weight gain prediction model by aggregating client models trained locally on their personal data. We showcase a software data-exploration tool that exhibits local model generation, sharing and updating across users and server for proposed collaborative learning. Our proposed model predicts the final weight category with 61.3% accuracy on day 140, with a 8.8% compromise on the centralized training accuracy.

Computational analysis on physiological signals would provide immense impact for enabling automated clinical analytics. However, the class imbalance issue where negative or minority class instances are rare in number impairs the robustness of the practical solution. The key idea of our approach is intelligent augmentation of minority class examples to construct smooth, unbiased decision boundary for robust semi-supervised learning. This solves the practical class imbalance problem in anomaly detection task for computational clinical analytics using physiological signals. We choose two critical cardiac marker physiological signals: Heart sound or Phonocardiogram (PCG) and Electrocardiogram (ECG) to validate our claim of robust anomaly detection of clinical events under augmented class learning, where intelligent synthesis of minority class instances attempt to balance the class distribution. We perform extensive experiments on publicly available expert-labelled MIT-Physionet PCG and ECG datasets that establish high performance merit of the proposed scheme, and our scheme fittingly performs better than the state-of-the-art algorithms.

In this paper, we present completely automated cardiac anomaly detection for remote screening of cardio-vascular abnormality using Phonocardiogram (PCG) or heart sound signal. Even though PCG contains significant and vital cardiac health information and cardiac abnormality signature, the presence of substantial noise does not guarantee highly effective analysis of cardiac condition. Our proposed method intelligently identifies and eliminates noisy PCG signal and consequently detects pathological abnormality condition. We further present a unified model of hybrid feature selection method. Our feature selection model is diversity optimized and cost-sensitive over conditional likelihood of the training and validation examples that maximizes classification model performance. We employ multi-stage hybrid feature selection process involving first level filter method and second level wrapper method. We achieve 85% detection accuracy by using publicly available MIT-Physionet challenge 2016 datasets consisting of more than 3000 annotated PCG signals.

Feature subset selection and identification of appropriate classification method plays an important role to optimize the predictive performance of supervised machine learning system. Current literature makes isolated attempts to optimize the feature selection and classifier identification. However, feature set has an intrinsic relationship with classification technique and together they form a `model' for classification task. In this paper, we propose AutoModeling that finds optimal learning model and jointly optimize the feature and hypothesis space to maximize performance measure objective function. It is an automated framework of selecting the ensemble model {selected feature subset, selected classifier} from a given superset of features and classifiers learned from given training dataset in a computational efficient manner. We introduce novel relax-greedy search with our proposed patience function as a wrapper feature selection that maximizes the predictive performance and eliminates the classical nesting effect. We perform extensive experimentations on different types of publicly available datasets and AutoModeling demonstrates superior performance over relevant state-of-the-art methods, expert-driven manual methods and deep neural networks.

We present a system to analyze patterns inside pulsatile signals and discover repetitions inside signals. We measure dominance of the repetitions using morphology and discrete nature of the signals by exploiting machine learning and information theoretic concepts. Patterns are represented as combinations of the basic features and derived features. Consistency of discovered patterns identifies state of physiological stability which varies from one individual to another. Hence it has immense impact on deriving the accurate physiological parameters for personalized health analytics. Proposed mechanism discovers the regular and irregular patterns by performing extensive analysis on several real life cardiac data sets. We have achieved more than 90% accuracy in identifying irregular patterns using our proposed method.

In this paper, we present CardioFit, a completely noninvasive cardiac condition monitoring system that enhances the clinical utility of health care analytics like lowering false detection of cardiac arrhythmia condition, higher accuracy in heart rate variability (HRV) computation. It performs powerful local analysis to enable accurate as well as easy-to-use, round-the-clock in-house, remote or mobile cardiac health checking. Here, photoplethysmogram (PPG) is the sole physiological signal considered for cardiac health management. It is to be noted that PPG carries significant necessary features what is available from electrocardiogram (ECG) signal. Unlike ECG, extraction of PPG is noninvasive, easy and affordable using smartphone or other low cost sensors. However, PPG is frequently contaminated with various kinds of motion artifacts and noise. Our robust concoction of signal processing and machine learning techniques exhibit higher accuracy in the detection and removal of the corrupt PPG signal segments. The proposed mechanism substantially improves the detection capability of the cardiac condition. Efficacy of our scheme is depicted using publicly available MIT-Physionet database as well as through our own field-collected real-life PPG data.

Remote cardiac health management is an important healthcare application. We have developed Heartmate that enables basic screening of cardiac health using low cost sensors or smartphone-inbuilt sensors without manual intervention. It consists of robust denoising algorithm along with effective anomaly analytics for physiological signals. Heartmate identifies and eliminates signal corruption as well as detects cardiac anomaly condition from physiological cardiac signals like heart sound or phonocardiogram (PCG) and photoplethysmogram (PPG).

Phonocardiogram (PCG) records heart sound and murmurs, which contains significant information of cardiac health. Analysis of PCG signal has the potential to detect abnormal cardiac condition. However, the presence of noise and motion artifacts in PCG hinders the accuracy of clinical event detection. Thus, noise detection and elimination are crucial to ensure accurate clinical analysis. In this paper, we present a robust denoising technique, Proclean that precisely detects the noisy PCG signal through pattern recognition, and statistical learning. We propose a novel self-discriminant learner that ensures to obtain distinct feature set to distinguish clean and noisy PCG signals without human-in-loop. We demonstrate that our proposed denoising leads to higher accuracy in subsequent clinical analytics for medical investigation. Our extensive experimentations with publicly available MIT-Physionet datasets show that we achieve more than 85% accuracy for noisy PCG signal detection. Further, we establish that physiological abnormality detection improves by more than 20%, when our proposed denoising mechanism is applied.

In this paper, we present a methodology for classifying normal, atrial fibrillation (AF), non-AF related other abnormal heart rhythms and noisy recordings by analysing single lead ECG signal of short duration.In a two layer binary cascaded approach proposed in our methodology, an unlabelled recording is initially classified into one of the two intermediate classes ('normal+others' and 'AF+noisy') at the first layer before actual classification at the second layer.The Physionet Challenge 2017 dataset containing more than 8500 ECG recordings are used for creation of training models and interval validation.The proposed methodology yields an average F1-score of 0.91, 0.79 and 0.77 respectively in classifying normal, AF and other rhythms on the training dataset using 5-fold cross validation.Results also show that, the said methodology, when applied on a hidden test set maintained by the challenge organisers yields F1-score values of 0.92, 0.86 and 0.74 in classifying the same.

In this paper we leverage the power of smartphone to enable proactive in-house heart condition monitoring. We introduce Heart-Trend, a nonparametric model to analyze and detect heart abnormality conditions like arrhythmia from photoplethysmogram (PPG) signal. It does on-demand heart status monitoring using smartphones (can also be implemented in PC/ICU monitors) and facilitates timely detection of heart condition deterioration to permit early diagnosis and prevention of fatal heart diseases. Proposed robust anomaly analytics engine accurately detects the morphological trend to find abnormal heart condition in real time through machine learning based trend prediction. PPG signal is frequently corrupted by ambient noise, and motion artifacts, which lead to high amount of false alarms. We introduce precise denoising technique that identifies and eliminates the corrupted segments of clinical signal to minimize its impact on the decision process and analytics. We demonstrate that Heart-Trend ensures high detection capability with lower false alarm rates.

We aim to develop a reliable and robust algorithm that accurately analyses a single short PCG recording (10-60s) from a single precordial location to determine the presence of heart abnormality for the Physionet/ Computing-in-Cardiology 2016 challenge. We extract timing information for the fundamental Heart Sounds i.e. S1 and S2 using Hidden Markov Model based Springer's improved version of Schmidt's method. These values are then used to generate statistical features set in temporal, frequency, time-frequency and wavelet domain. We choose the optimal feature set out of the pool of overall 54 features using mutual information based minimum Redundancy Maximum Relevance (mRMR) technique. In order to cope with bad signals, we also check the signal quality of the PCG signal. Signals are rejected for further normal abnormal classification when the outside/background noise has rendered them useless for processing. Then, non-linear radial basis function based Support Vector Machine (SVM) classifier along with ensemble based methods is used to train with the reduced optimal feature sets, on a balanced training set chosen from the group of all PCG datasets. Our algorithm is tested with hidden Physionet Challenge 2016 datasets and performance achieved is: Sensitivity (Se) = 0.7749, Specificity (Sp) = 0.7891 and Overall Score calculated as mean (Se, Sp) = 0.7820.

We propose here derivation algorithms for physiological parameters like beat start point, systolic peak, pulse duration, peak-to-peak distance related to heart rate, dicrotic minima, diastolic peak from Photoplethysmogram (PPG) signals robustly. Our methods are based on unsupervised learning mainly following morphology as well as discrete nature of the signal. Statistical learning has been used as a special aid to infer most probable feature values mainly to cope up with presence of noise, which is assumed to be insignificant compared to signal values at each investigation window. Performance of the proposed method is found to be better than other standard methods, yielding precision and sensitivity more than 97% obtained from three real life data sets.