Flexible Machine Learning Algorithms for Clinical Gait Assessment Tools

The current gold standard of gait diagnostics is dependent on large, expensive motion-capture laboratories and highly trained clinical and technical staff. Wearable sensor systems combined with machine learning may help to improve the accessibility of objective gait assessments in a broad clinical context. However, current algorithms lack flexibility and require large training datasets with tedious manual labelling of data. The current study tests the validity of a novel machine learning algorithm for automated gait partitioning of laboratory-based and sensor-based gait data. The developed artificial intelligence tool was used in patients with a central neurological lesion and severe gait impairments. To build the novel algorithm, 2% and 3% of the entire dataset (567 and 368 steps in total, respectively) were required for assessments with laboratory equipment and inertial measurement units. The mean errors of machine learning-based gait partitions were 0.021 s for the laboratory-based datasets and 0.034 s for the sensor-based datasets. Combining reinforcement learning with a deep neural network allows significant reduction in the size of the training datasets to <5%. The low number of required training data provides end-users with a high degree of flexibility. Non-experts can easily adjust the developed algorithm and modify the training library depending on the measurement system and clinical population.

Spousal similarities in cardiometabolic risk factors: A cross-sectional comparison between Dutch and Japanese data from two large biobank studies

BACKGROUND AND AIMS

Few studies have examined and compared spousal concordance in different populations. This study aimed to quantify and compare spousal similarities in cardiometabolic risk factors and diseases between Dutch and Japanese populations.

METHODS

This cross-sectional study included 28,265 Dutch Lifelines Cohort Study spouse pairs (2006-2013) and 5,391 Japanese Tohoku Medical Megabank Organization (ToMMo) Cohort Study pairs (2013-2016). Spousal similarities in cardiometabolic risk factors were evaluated using Pearson's correlation or logistic regression analyses adjusted for spousal age.

RESULTS

The husbands' and wives' average ages in the Lifelines and ToMMo cohorts were 50.0 and 47.7 years and 63.2 and 60.4 years, respectively. Significant spousal similarities occurred with all cardiometabolic risk factors and diseases of interest in both cohorts. The age-adjusted correlation coefficients ranged from 0.032 to 0.263, with the strongest correlations observed in anthropometric traits. Spousal odds ratios [95% confidence interval] for the Lifelines vs. ToMMo cohort ranged from 1.45 (1.36-1.55) vs. 1.20 (1.05-1.38) for hypertension to 6.86 (6.30-7.48) vs. 4.60 (3.52-6.02) for current smoking. An increasing trend in spousal concordance with age was observed for sufficient physical activity in both cohorts. For current smoking, those aged 20-39 years showed the strongest concordance between pairs in both cohorts. The Dutch pairs showed stronger similarities in anthropometric traits and lifestyle habits (smoking and drinking) than their Japanese counterparts.

CONCLUSIONS

Spouses showed similarities in several cardiometabolic risk factors among Dutch and Japanese populations, with regional and cultural influences on spousal similarities.

Development of a Biobank from a Legacy Collection in Universitas Gadjah Mada, Indonesia: Proposed Approach for Centralized Biobank Development in Low-Resource Institutions

Introduction: The establishment of a biobank requires specific expertise along with relatively expensive infrastructure and appropriate technology. This causes certain challenges in biobank implementation for research in low-middle-income countries. Biobank development with established specimens and data collection (legacy collection) was an approach used in the Faculty of Medicine, Public Health and Nursing, Universitas Gadjah Mada. This approach aimed to identify the resources available at present, while providing nontechnical information for further development of a centralized biobank. Materials and Methods: Retrospective modeling was done in 2015 by recruiting existing specimen collections and their associated data. The steps were as follows: (1) informing research stakeholders through discussion with experts and stakeholders; (2) identifying specimen collections to be used; (3) determining the system, infrastructure, and consumables needed; (4) determining inclusion criteria; (5) building an in-house database system; (6) organizing data and physical specimen collections; and (7) validating data and physical sample arrangement. All technical procedures were built into standard operating procedures. Results: The model included specimens from one -80°C freezer. The associated data included demographic, clinical diagnosis, and physical sample information. Samples came from six studies, collected between 2001 and 2014. A web-based database was built based on the MySQL programming system. Information on biospecimens from a total of 4196 subjects collected in 11,358 vials was entered into the database, following physical rearrangement of vials in the -80°C freezer with one-dimensional barcodes taped to vials, boxes, and racks. A validation test was done for data concordance between the database and physical arrangement in the -80°C freezer, showing no discrepancies. Conclusion: This report demonstrated current technical and nontechnical insights to further develop a centralized biobank for health research at an academic institution in Indonesia.