Data Mining Practical Machine Learning Tools and Techniques

March 5, 2019 e1 WRITING GROUP MEMBERS Emelia J. Benjamin, MD, ScM, FAHA, Chair Paul Muntner, PhD, MHS, FAHA, Vice Chair Alvaro Alonso, MD, PhD, FAHA Marcio S. Bittencourt, MD, PhD, MPH Clifton W. Callaway, MD, FAHA April P. Carson, PhD, MSPH, FAHA Alanna M. Chamberlain, PhD Alexander R. Chang, MD, MS Susan Cheng, MD, MMSc, MPH, FAHA Sandeep R. Das, MD, MPH, MBA, FAHA Francesca N. Delling, MD, MPH Luc Djousse, MD, ScD, MPH Mitchell S.V. Elkind, MD, MS, FAHA Jane F. Ferguson, PhD, FAHA Myriam Fornage, PhD, FAHA Lori Chaffin Jordan, MD, PhD, FAHA Sadiya S. Khan, MD, MSc Brett M. Kissela, MD, MS Kristen L. Knutson, PhD Tak W. Kwan, MD, FAHA Daniel T. Lackland, DrPH, FAHA Tené T. Lewis, PhD Judith H. Lichtman, PhD, MPH, FAHA Chris T. Longenecker, MD Matthew Shane Loop, PhD Pamela L. Lutsey, PhD, MPH, FAHA Seth S. Martin, MD, MHS, FAHA Kunihiro Matsushita, MD, PhD, FAHA Andrew E. Moran, MD, MPH, FAHA Michael E. Mussolino, PhD, FAHA Martin O’Flaherty, MD, MSc, PhD Ambarish Pandey, MD, MSCS Amanda M. Perak, MD, MS Wayne D. Rosamond, PhD, MS, FAHA Gregory A. Roth, MD, MPH, FAHA Uchechukwu K.A. Sampson, MD, MBA, MPH, FAHA Gary M. Satou, MD, FAHA Emily B. Schroeder, MD, PhD, FAHA Svati H. Shah, MD, MHS, FAHA Nicole L. Spartano, PhD Andrew Stokes, PhD David L. Tirschwell, MD, MS, MSc, FAHA Connie W. Tsao, MD, MPH, Vice Chair Elect Mintu P. Turakhia, MD, MAS, FAHA Lisa B. VanWagner, MD, MSc, FAST John T. Wilkins, MD, MS, FAHA Sally S. Wong, PhD, RD, CDN, FAHA Salim S. Virani, MD, PhD, FAHA, Chair Elect On behalf of the American Heart Association Council on Epidemiology and Prevention Statistics Committee and Stroke Statistics Subcommittee

Heart Disease and Stroke Statistics—2019 Update: A Report From the American Heart Association

Background: The American Heart Association, in conjunction with the National Institutes of Health, annually reports on the most up-to-date statistics related to heart disease, stroke, and cardiovas...

Heart Disease and Stroke Statistics—2020 Update: A Report From the American Heart Association

NAFLD is one of the most important causes of liver disease worldwide and will probably emerge as the leading cause of end-stage liver disease in the coming decades, with the disease affecting both adults and children. The epidemiology and demographic characteristics of NAFLD vary worldwide, usually parallel to the prevalence of obesity, but a substantial proportion of patients are lean. The large number of patients with NAFLD with potential for progressive liver disease creates challenges for screening, as the diagnosis of NASH necessitates invasive liver biopsy. Furthermore, individuals with NAFLD have a high frequency of metabolic comorbidities and could place a growing strain on health-care systems from their need for management. While awaiting the development effective therapies, this disease warrants the attention of primary care physicians, specialists and health policy makers.

/pdf/global-burden-of-nafld-and-nash-trends-predictions-risk-2rbbbzfuoo.pdf

Global burden of NAFLD and NASH: trends, predictions, risk factors and prevention

Background: The American Heart Association, in conjunction with the National Institutes of Health, annually reports the most up-to-date statistics related to heart disease, stroke, and cardiovascul...

Heart Disease and Stroke Statistics-2021 Update: A Report From the American Heart Association.

Human activity recognition (HAR) in ubiquitous computing is beginning to adopt deep learning to substitute for well-established analysis techniques that rely on hand-crafted feature extraction and classification techniques. From these isolated applications of custom deep architectures it is, however, difficult to gain an overview of their suitability for problems ranging from the recognition of manipulative gestures to the segmentation and identification of physical activities like running or ascending stairs. In this paper we rigorously explore deep, convolutional, and recurrent approaches across three representative datasets that contain movement data captured with wearable sensors. We describe how to train recurrent approaches in this setting, introduce a novel regularisation approach, and illustrate how they outperform the state-of-the-art on a large benchmark dataset. Across thousands of recognition experiments with randomly sampled model configurations we investigate the suitability of each model for different tasks in HAR, explore the impact of hyperparameters using the fANOVA framework, and provide guidelines for the practitioner who wants to apply deep learning in their problem setting.

Deep, Convolutional, and Recurrent Models for Human Activity Recognition using Wearables

The majority of activity recognition systems in wearable computing rely on a set of statistical measures, such as means and moments, extracted from short frames of continuous sensor measurements to perform recognition. These features implicitly quantify the distribution of data observed in each frame. However, feature selection remains challenging and labour intensive, rendering a more generic method to quantify distributions in accelerometer data much desired. In this paper we present the ECDF representation, a novel approach to preserve characteristics of arbitrary distributions for feature extraction, which is particularly suitable for embedded applications. In extensive experiments on six publicly available datasets we demonstrate that it outperforms common approaches to feature extraction across a wide variety of tasks.

On preserving statistical characteristics of accelerometry data using their empirical cumulative distribution

Recently, deep learning (DL) methods have been introduced very successfully into human activity recognition (HAR) scenarios in ubiquitous and wearable computing. Especially the prospect of overcoming the need for manual feature design combined with superior classification capabilities render deep neural networks very attractive for real-life HAR application. Even though DL-based approaches now outperform the state-of-the-art in a number of recognitions tasks of the field, yet substantial challenges remain. Most prominently, issues with real-life datasets, typically including imbalanced datasets and problematic data quality, still limit the effectiveness of activity recognition using wearables. In this paper we tackle such challenges through Ensembles of deep Long Short Term Memory (LSTM) networks. We have developed modified training procedures for LSTM networks and combine sets of diverse LSTM learners into classifier collectives. We demonstrate, both formally and empirically, that Ensembles of deep LSTM learners outperform the individual LSTM networks. Through an extensive experimental evaluation on three standard benchmarks (Opportunity, PAMAP2, Skoda) we demonstrate the excellent recognition capabilities of our approach and its potential for real-life applications of human activity recognition.

Ensembles of Deep LSTM Learners for Activity Recognition using Wearables

Background and aims Physical activity is a key determinant of metabolic control and is recommended for people with non-alcoholic fatty liver disease (NAFLD), usually alongside weight loss and dietary change. To date, no studies have reported the relationship between objectively measured sedentary behaviour and physical activity, liver fat and metabolic control in people with NAFLD, limiting the potential to target sedentary behaviour in clinical practice. This study determined the level of sedentary behaviour and physical activity in people with NAFLD, and investigated links between physical activity, liver fat and glucose control. Methods Sedentary behaviour, physical activity and energy expenditure were assessed in 37 adults with NAFLD using a validated multisensor array over 7 days. Liver fat and glucose control were assessed, respectively, by 1 H-MRS and fasting blood samples. Patterns of sedentary behaviour were assessed by power law analyses of the lengths of sedentary bouts fitted from raw sedentary data. An age and sex-matched healthy control group wore the activity monitor for the same time period. Results People with NAFLD spent approximately half an hour extra a day being sedentary (1318±68 vs1289±60 mins/day; p<0.05) and walked 18% fewer steps (8483±2926 vs 10377±3529 steps/ day; p<0.01). As a consequence, active energy expenditure was reduced by 40% (432±258 vs 732±345 kcal/day; p<0.01) and total energy expenditure was lower in NAFLD (2690±440 vs 2901±511 kcal/day; p<0.01). Power law analyses of the lengths of sedentary bouts demonstrated that patients with NAFLD also have a lower number of transitions from being sedentary to active compared with controls (13±0.03 vs15 ±0.03%; p<0.05). Conclusions People with NAFLD spend more time sedentary and undertake less physical activity on a daily basis than healthy controls. High levels of sedentary behaviour and low levels of physical activity represent a therapeutic target that may prevent progression of metabolic conditions and weight gain in people with NAFLD and should be considered in clinical care.

https://fg.bmj.com/content/flgastro/6/1/44.full.pdf

Non-alcoholic fatty liver disease is associated with higher levels of objectively measured sedentary behaviour and lower levels of physical activity than matched healthy controls

Health and well-being of dogs, either domesticated pets or service animals, are major concerns that are taken seriously for ethical, emotional, and financial reasons. Welfare assessments in dogs rely on objective observations of both frequency and variability of individual behaviour traits, which is often difficult to obtain in a dog's everyday life. In this paper we have identified a set of activities, which are linked to behaviour traits that are relevant for a dog's wellbeing. We developed a collar-worn accelerometry platform that records dog behaviours in naturalistic environments. A statistical classification framework is used for recognising dog activities. In an experimental evaluation we analysed the naturalistic behaviour of 18 dogs and were able to recognise a total of 17 different activities with approximately 70% classification accuracy. The presented system is the first of its kind that allows for robust and detailed analysis of dog activities in naturalistic environments.

Thomas Ploetz

Papers

Deep, Convolutional, and Recurrent Models for Human Activity Recognition using Wearables

On preserving statistical characteristics of accelerometry data using their empirical cumulative distribution

Ensembles of Deep LSTM Learners for Activity Recognition using Wearables

Non-alcoholic fatty liver disease is associated with higher levels of objectively measured sedentary behaviour and lower levels of physical activity than matched healthy controls

Dog's life: wearable activity recognition for dogs