An Unsupervised Machine Learning Clustering and Prediction of Differential Clinical Phenotypes of COVID-19 Patients Based on Blood Tests-A Hong Kong Population Study.

Background: To better understand the different clinical phenotypes across the disease spectrum in patients with COVID-19 using an unsupervised machine learning clustering approach. Materials and Methods: A population-based retrospective study was conducted utilizing demographics, clinical characteristics, comorbidities, and clinical outcomes of 7,606 COVID-19-positive patients on admission to public hospitals in Hong Kong in the year 2020. An unsupervised machine learning clustering was used to explore this large cohort. Results: Four clusters of differing clinical phenotypes based on data at initial admission was derived in which 86.6% of the deceased cases were aggregated in one of the clusters without prior knowledge of their clinical outcomes. Other distinctive clinical characteristics of this cluster were old age and high concurrent comorbidities as well as laboratory characteristics of lower hemoglobin/hematocrit levels, higher neutrophil, C-reactive protein, lactate dehydrogenase, and creatinine levels. The clinical patterns captured by the cluster analysis was validated on other temporally distinct cohorts in 2021. The phenotypes aligned with existing literature. Conclusion: The study demonstrated the usefulness of unsupervised machine learning techniques with the potential to uncover latent clinical phenotypes. It could serve as a more robust classification for patient triaging and patient-tailored treatment strategies.

A Microfluidic System for One-Chip Harvesting of Single-Cell-Laden Hydrogels in Culture Medium.

Single-cell analysis has shown great potential to fully quantify the distribution of cellular behaviors among a population of individuals. Through isolation and preservation of single cells in the aqueous phase, droplet encapsulation followed by gelation enables high-throughput analysis in biocompatible microgels. However, the lack of control over the number of cells encapsulated and complicated gelation processes significantly limit its efficiency. Here, a microfluidic system for one-chip harvesting of single-cell-laden microgels is presented. Through ultraviolet irradiation, an on-chip gelation technique is seamlessly combined with droplet generation to realize high-throughput fabrication of microscale hydrogels in microfluidic channel. Moreover, a sorting module is introduced to simultaneously complete cell-laden microgel selection and transfer into culture medium. To demonstrate the efficiency of this method, two types of single cells are respectively encapsulated and collected, showing desirable single-cell encapsulation and cell viability. This technique realizes integrated droplet gelation, microgel sorting, and transfer into culture medium, allowing high-throughput analysis of single cells and comprehensive understanding of the cellular specificity.