AI & Machine Learning in Bioinformatics and Healthcare Informatics

Machine learning (ML) in healthcare data analytics is attracting much attention because of the unprecedented power of ML to extract knowledge that improves the decision-making process. At the same time, laws and ethics codes drafted by countries to govern healthcare data are becoming stringent. Although healthcare practitioners are struggling with an enforced governance framework, we see the emergence of distributed learning-based frameworks disrupting traditional-ML-model development. Splitfed learning (SFL) is one of the recent developments in distributed machine learning that empowers healthcare practitioners to preserve the privacy of input data and enables them to train ML models. However, SFL has some extra communication and computation overheads at the client side due to the requirement of client-side model synchronization. For a resource-constrained client side (hospitals with limited computational powers), removing such conditions is required to gain efficiency in the learning. In this regard, this paper studies SFL without client-side model synchronization. The resulting architecture is known as multi-head split learning (MHSL). At the same time, it is important to investigate information leakage, which indicates how much information is gained by the server related to the raw data directly out of the smashed data—the output of the client-side model portion—passed to it by the client. Our empirical studies examine the Resnet-18 and Conv1-D architecture model on the ECG and HAM-10000 datasets under IID data distribution. The results find that SFL provides 1.81% and 2.36% better accuracy than MHSL on the ECG and HAM-10000 datasets, respectively (for cut-layer value set to 1). Analysis of experimentation with various client-side model portions demonstrates that it has an impact on the overall performance. With an increase in layers in the client-side model portion, SFL performance improves while MHSL performance degrades. Experiment results also demonstrate that information leakage provided by mutual information score values in SFL is more than MHSL for ECG and HAM-10000 datasets by $2\times {10}^{-5}$ and $4\times {10}^{-3}$, respectively. Full article

Human Activity Recognition (HAR) is increasingly used in a variety of applications, including health care, fitness tracking, and rehabilitation. To reduce the impact on the user’s daily activities, wearable technologies have been advanced throughout the years. In this study, an improved smart insole-based HAR system is proposed. The impact of data segmentation, sensors used, and feature selection on HAR was fully investigated. The Support Vector Machine (SVM), a supervised learning algorithm, has been used to recognise six ambulation activities: downstairs, sit to stand, sitting, standing, upstairs, and walking. Considering the impact that data segmentation can have on the classification, the sliding window size was optimised, identifying the length of 10 s with 50% of overlap as the best performing. The inertial sensors and pressure sensors embedded into the smart insoles have been assessed to determine the importance that each one has in the classification. A feature selection technique has been applied to reduce the number of features from 272 to 227 to improve the robustness of the proposed system and to investigate the importance of features in the dataset. According to the findings, the inertial sensors are reliable for the recognition of dynamic activities, while pressure sensors are reliable for stationary activities; however, the highest accuracy ($94.66\%$) was achieved by combining both types of sensors. Full article

The relationship between the host and the microbiome, or the assemblage of microorganisms (including bacteria, archaea, fungi, and viruses), has been proven crucial for its health and disease development. The high dimensionality of microbiome datasets has often been addressed as a major difficulty for data analysis, such as the use of machine-learning (ML) and deep-learning (DL) models. Here, we present BiGAMi, a bi-objective genetic algorithm fitness function for feature selection in microbial datasets to train high-performing phenotype classifiers. The proposed fitness function allowed us to build classifiers that outperformed the baseline performance estimated by the original studies by using as few as 0.04% to 2.32% features of the original dataset. In 35 out of 42 performance comparisons between BiGAMi and other feature selection methods evaluated here (sequential forward selection, SelectKBest, and GARS), BiGAMi achieved its results by selecting 6–93% fewer features. This study showed that the application of a bi-objective GA fitness function against microbiome datasets succeeded in selecting small subsets of bacteria whose contribution to understood diseases and the host state was already experimentally proven. Applying this feature selection approach to novel diseases is expected to quickly reveal the microbes most relevant to a specific condition. Full article