Food Frequency Questionnaire Personalisation Using Multi-Target Regression.

Fondazione Bruno Kessler is developing a mobile app prototype for empowering citizens to improve their health conditions through different lifestyle interventions that will be incorporated into a mobile application for lifestyle promotion of the Province of Trento in the context of the Trentino Salute 4.0 Competence Center. The envisioned interventions are based on promoting behaviour change in various domains such as physical activity, mental health and nutrition. In particular, the nutrition component is a self-monitoring module that collects dietary habits to analyse them and recommend healthier eating behaviours. Dietary assessment is completed using a Food Frequency Questionnaire on the Mediterranean diet that is presented to the user as a grid of images. The questionnaire returns feedback on 11 aspects of nutrition. Although the questionnaire used in the application only consists of 24 questions, it still could be a bit overwhelming and a bit crowded when shown on the screen. In this paper, we tried to find a machine-learning-based solution to reduce the number of questions in the questionnaire. We proposed a method that uses the user's previous answers as additional information to find the goals that need more attention. We compared this method with a case where the subset of questions is randomly selected and with a case where the subset is chosen using feature selection. We also explored how large the subset should be to obtain good predictions. All the experiments are conducted as a multi-target regression problem, which means several goals are predicted simultaneously. The proposed method adjusts well to the user in question and has the slightest error when predicting the goals.

Choosing the Best Sensor Fusion Method: A Machine-Learning Approach.

Multi-sensor fusion refers to methods used for combining information coming from several sensors (in some cases, different ones) with the aim to make one sensor compensate for the weaknesses of others or to improve the overall accuracy or the reliability of a decision-making process. Indeed, this area has made progress, and the combined use of several sensors has been so successful that many authors proposed variants of fusion methods, to the point that it is now hard to tell which of them is the best for a given set of sensors and a given application context. To address the issue of choosing an adequate fusion method, we recently proposed a machine-learning data-driven approach able to predict the best merging strategy. This approach uses a meta-data set with the Statistical signatures extracted from data sets of a particular domain, from which we train a prediction model. However, the mentioned work is restricted to the recognition of human activities. In this paper, we propose to extend our previous work to other very different contexts, such as gas detection and grammatical face expression identification, in order to test its generality. The extensions of the method are presented in this paper. Our experimental results show that our extended model predicts the best fusion method well for a given data set, making us able to claim a broad generality for our sensor fusion method.

Multi-Sensor Fusion for Activity Recognition-A Survey.

In Ambient Intelligence (AmI), the activity a user is engaged in is an essential part of the context, so its recognition is of paramount importance for applications in areas like sports, medicine, personal safety, and so forth. The concurrent use of multiple sensors for recognition of human activities in AmI is a good practice because the information missed by one sensor can sometimes be provided by the others and many works have shown an accuracy improvement compared to single sensors. However, there are many different ways of integrating the information of each sensor and almost every author reporting sensor fusion for activity recognition uses a different variant or combination of fusion methods, so the need for clear guidelines and generalizations in sensor data integration seems evident. In this survey we review, following a classification, the many fusion methods for information acquired from sensors that have been proposed in the literature for activity recognition; we examine their relative merits, either as they are reported and sometimes even replicated and a comparison of these methods is made, as well as an assessment of the trends in the area.

Virtual Sensors for Optimal Integration of Human Activity Data.

Sensors are becoming more and more ubiquitous as their price and availability continue to improve, and as they are the source of information for many important tasks. However, the use of sensors has to deal with noise and failures. The lack of reliability in the sensors has led to many forms of redundancy, but simple solutions are not always the best, and the precise way in which several sensors are combined has a big impact on the overall result. In this paper, we discuss how to deal with the combination of information coming from different sensors, acting thus as "virtual sensors", in the context of human activity recognition, in a systematic way, aiming for optimality. To achieve this goal, we construct meta-datasets containing the "signatures" of individual datasets, and apply machine-learning methods in order to distinguish when each possible combination method could be actually the best. We present specific results based on experimentation, supporting our claims of optimality.

Smartphone-based self-monitoring in bipolar disorder: evaluation of usability and feasibility of two systems.

BACKGROUND: The aims of the present multicenter pilot study were to examine the feasibility and usability of two different smartphone-based monitoring systems (the Pulso system and the Trilogis-Monsenso system) from two IT companies in patients with bipolar disorder, developed and selected to be testes as a part of a European Union funded Pre-Commercial Procurement (the NYMPHA-MD project). METHODS: Patients with bipolar disorder (ICD-10), > 18 years of age during a remitted, partial remitted or mild to moderate depressive state (HDRS-17 < 25) from Italy, Spain and Denmark were included. Patients were randomized 1:1 to the use of one of two smartphone-based monitoring systems. The randomization was stratified according to study location (Italy, Spain, Denmark) and all patients were followed for a 4 weeks study period. Usability and feasibility were evaluated using the Computer System Usability Questionnaire, and the Usefulness, Satisfaction, and Ease of use Questionnaire. RESULTS: A total of 60 patients aged 18-69 years with bipolar disorder (ICD-10) recruited from Italy, Spain, Denmark were included-59 patients completed the study. In Denmark, the patients evaluated the Trilogis-Monsenso system with a statistically significant higher usability compared with the Pulso system. In Italy and Spain, the patients evaluated no statistically significant difference between the two systems in any of the categories, except for the usefulness category favoring the Trilogis-Monsenso system (z = 2.68, p < 0.01). CONCLUSIONS: Both monitoring systems showed acceptable usability and feasibility. There were differences in patient-based evaluations of the two monitoring systems related to the country of the study. Studies investigating the usability and feasibility during longer follow-up periods could perhaps reveal different findings. Future randomized controlled trials investigating the possible positive and negative effects of smartphone-based monitoring systems are needed.

Machine Learning and Data Analytics in Pervasive Health.

INTRODUCTION: This accompanying editorial provides a brief introduction to this focus theme, focused on "Machine Learning and Data Analytics in Pervasive Health". OBJECTIVE: The innovative use of machine learning technologies combining small and big data analytics will support a better provisioning of healthcare to citizens. This focus theme aims to present contributions at the crossroads of pervasive health technologies and data analytics as key enablers for achieving personalised medicine for diagnosis and treatment purposes. METHODS: A call for paper was announced to all participants of the "11th International Conference on Pervasive Computing Technologies for Healthcare", to different working groups of the International Medical Informatics Association (IMIA) and European Federation of Medical Informatics (EFMI) and was published in June 2017 on the website of Methods of Information in Medicine. A peer review process was conducted to select the papers for this focus theme. RESULTS: Four papers were selected to be included in this focus theme. The paper topics cover a broad range of machine learning and data analytics applications in healthcare including detection of injurious subtypes of patient-ventilator asynchrony, early detection of cognitive impairment, effective use of small data sets for estimating the performance of radiotherapy in bladder cancer treatment, and the use negation detection in and information extraction from unstructured medical texts. CONCLUSIONS: The use of machine learning and data analytics technologies in healthcare is facing a renewed impulse due to the availability of large amounts and new sources of human behavioral and physiological data, such as that captured by mobile and pervasive devices traditionally considered as nonmainstream for healthcare provision and management.

The Bipolar Illness Onset study: research protocol for the BIO cohort study.

INTRODUCTION: Bipolar disorder is an often disabling mental illness with a lifetime prevalence of 1%-2%, a high risk of recurrence of manic and depressive episodes, a lifelong elevated risk of suicide and a substantial heritability. The course of illness is frequently characterised by progressive shortening of interepisode intervals with each recurrence and increasing cognitive dysfunction in a subset of individuals with this condition. Clinically, diagnostic boundaries between bipolar disorder and other psychiatric disorders such as unipolar depression are unclear although pharmacological and psychological treatment strategies differ substantially. Patients with bipolar disorder are often misdiagnosed and the mean delay between onset and diagnosis is 5-10 years. Although the risk of relapse of depression and mania is high it is for most patients impossible to predict and consequently prevent upcoming episodes in an individual tailored way. The identification of objective biomarkers can both inform bipolar disorder diagnosis and provide biological targets for the development of new and personalised treatments. Accurate diagnosis of bipolar disorder in its early stages could help prevent the long-term detrimental effects of the illness.The present Bipolar Illness Onset study aims to identify (1) a composite blood-based biomarker, (2) a composite electronic smartphone-based biomarker and (3) a neurocognitive and neuroimaging-based signature for bipolar disorder. METHODS AND ANALYSIS: The study will include 300 patients with newly diagnosed/first-episode bipolar disorder, 200 of their healthy siblings or offspring and 100 healthy individuals without a family history of affective disorder. All participants will be followed longitudinally with repeated blood samples and other biological tissues, self-monitored and automatically generated smartphone data, neuropsychological tests and a subset of the cohort with neuroimaging during a 5 to 10-year study period. ETHICS AND DISSEMINATION: The study has been approved by the Local Ethical Committee (H-7-2014-007) and the data agency, Capital Region of Copenhagen (RHP-2015-023), and the findings will be widely disseminated at international conferences and meetings including conferences for the International Society for Bipolar Disorders and the World Federation of Societies for Biological Psychiatry and in scientific peer-reviewed papers. TRIAL REGISTRATION NUMBER: NCT02888262.

Wearable Therapy - Detecting Information from Wearables and Mobiles that are Relevant to Clinical and Self-directed Therapy.

BACKGROUND: This accompanying editorial provides a brief introduction into the focus theme "Wearable Therapy". OBJECTIVES: The focus theme "Wearable Therapy" aims to present contributions which target wearable and mobile technologies to support clinical and self-directed therapy. METHODS: A call for papers was announced to all participants of the "9th International Conference on Pervasive Computing Technologies for Healthcare" and was published in November 2015. A peer review process was conducted to select the papers for the focus theme. RESULTS: Six papers were selected to be included in this focus theme. The paper topics cover a broad range including an approach to build a health informatics research program, a comprehensive literature review of self-quantification for health self-management, methods for affective state detection of informal care givers, social-aware handling of falls, smart shoes for supporting self-directed therapy of alcohol addicts, and reference information model for pervasive health systems. CONCLUSIONS: More empirical evidence is needed that confirms sustainable effects of employing wearable and mobile technology for clinical and self-directed therapy. Inconsistencies between different conceptual approaches need to be revealed in order to enable more systematic investigations and comparisons.

Stress modelling and prediction in presence of scarce data.

OBJECTIVE: Stress at work is a significant occupational health concern. Recent studies have used various sensing modalities to model stress behaviour based on non-obtrusive data obtained from smartphones. However, when the data for a subject is scarce it becomes a challenge to obtain a good model. METHODS: We propose an approach based on a combination of techniques: semi-supervised learning, ensemble methods and transfer learning to build a model of a subject with scarce data. Our approach is based on the comparison of decision trees to select the closest subject for knowledge transfer. RESULTS: We present a real-life, unconstrained study carried out with 30 employees within two organisations. The results show that using information (instances or model) from similar subjects can improve the accuracy of the subjects with scarce data. However, using transfer learning from dissimilar subjects can have a detrimental effect on the accuracy. Our proposed ensemble approach increased the accuracy by ≈10% to 71.58% compared to not using any transfer learning technique. CONCLUSIONS: In contrast to high precision but highly obtrusive sensors, using smartphone sensors for measuring daily behaviours allowed us to quantify behaviour changes, relevant to occupational stress. Furthermore, we have shown that use of transfer learning to select data from close models is a useful approach to improve accuracy in presence of scarce data.

Automatic Stress Detection in Working Environments From Smartphones' Accelerometer Data: A First Step.

Increase in workload across many organizations and consequent increase in occupational stress are negatively affecting the health of the workforce. Measuring stress and other human psychological dynamics is difficult due to subjective nature of selfreporting and variability between and within individuals. With the advent of smartphones, it is now possible to monitor diverse aspects of human behavior, including objectively measured behavior related to psychological state and consequently stress. We have used data from the smartphone's built-in accelerometer to detect behavior that correlates with subjects stress levels. Accelerometer sensor was chosen because it raises fewer privacy concerns (e.g., in comparison to location, video, or audio recording), and because its low-power consumption makes it suitable to be embedded in smaller wearable devices, such as fitness trackers. About 30 subjects from two different organizations were provided with smartphones. The study lasted for eight weeks and was conducted in real working environments, with no constraints whatsoever placed upon smartphone usage. The subjects reported their perceived stress levels three times during their working hours. Using combination of statistical models to classify selfreported stress levels, we achieved a maximum overall accuracy of 71% for user-specific models and an accuracy of 60% for the use of similar-users models, relying solely on data from a single accelerometer.

Smartphone-based recognition of states and state changes in bipolar disorder patients.

Today's health care is difficult to imagine without the possibility to objectively measure various physiological parameters related to patients' symptoms (from temperature through blood pressure to complex tomographic procedures). Psychiatric care remains a notable exception that heavily relies on patient interviews and self-assessment. This is due to the fact that mental illnesses manifest themselves mainly in the way patients behave throughout their daily life and, until recently there were no "behavior measurement devices." This is now changing with the progress in wearable activity recognition and sensor enabled smartphones. In this paper, we introduce a system, which, based on smartphone-sensing is able to recognize depressive and manic states and detect state changes of patients suffering from bipolar disorder. Drawing upon a real-life dataset of ten patients, recorded over a time period of 12 weeks (in total over 800 days of data tracing 17 state changes) by four different sensing modalities, we could extract features corresponding to all disease-relevant aspects in behavior. Using these features, we gain recognition accuracies of 76% by fusing all sensor modalities and state change detection precision and recall of over 97%. This paper furthermore outlines the applicability of this system in the physician-patient relations in order to facilitate the life and treatment of bipolar patients.

Investigating correlation between verbal interactions and perceived stress.

While moderate exposure to stress at work can act as productivity booster, prolonged exposure not only decreases productivity, but it can also lead to an array of health related problems. Therefore, monitoring stress levels and more importantly correlated stressors, becomes prerequisite for a productive workforce. Considering that verbal interaction is an integral part of workplace environments, we report the results of our study that investigates correlation between perceived stress levels and verbal interaction. 28 workers were monitored over 6 weeks through their smartphones during their daily, real-world behaviour, capturing both verbal interaction and perceived stress levels. Results show that more than half of participants show correlation between perceived stress levels and verbal interaction, while this correlation is observed for over 90% of highly stressed participants.

Speech activity detection using accelerometer.

The level of social activity is linked to the overall wellbeing and to various disorders, including stress. In this regard, a myriad of automatic solutions for monitoring social interactions have been proposed, usually including audio data analysis. Such approaches often face legal and ethical issues and they may also raise privacy concerns in monitored subjects thus affecting their natural behaviour. In this paper we present an accelerometer-based speech detection which does not require capturing sensitive data while being an easily applicable and a cost-effective solution.

Smartphone-centred wearable sensors network for monitoring patients with bipolar disorder.

Bipolar Disorder is a severe form of mental illness. It is characterized by alternated episodes of mania and depression, and it is treated typically with a combination of pharmacotherapy and psychotherapy. Recognizing early warning signs of upcoming phases of mania or depression would be of great help for a personalized medical treatment. Unfortunately, this is a difficult task to be performed for both patient and doctors. In this paper we present the MONARCA wearable system, which is meant for recognizing early warning signs and predict maniac or depressive episodes. The system is a smartphone-centred and minimally invasive wearable sensors network that is being developing in the framework of the MONARCA European project.