A review on multimodal machine learning in medical diagnostics.

Nowadays, the increasing number of medical diagnostic data and clinical data provide more complementary references for doctors to make diagnosis to patients. For example, with medical data, such as electrocardiography (ECG), machine learning algorithms can be used to identify and diagnose heart disease to reduce the workload of doctors. However, ECG data is always exposed to various kinds of noise and interference in reality, and medical diagnostics only based on one-dimensional ECG data is not trustable enough. By extracting new features from other types of medical data, we can implement enhanced recognition methods, called multimodal learning. Multimodal learning helps models to process data from a range of different sources, eliminate the requirement for training each single learning modality, and improve the robustness of models with the diversity of data. Growing number of articles in recent years have been devoted to investigating how to extract data from different sources and build accurate multimodal machine learning models, or deep learning models for medical diagnostics. This paper reviews and summarizes several recent papers that dealing with multimodal machine learning in disease detection, and identify topics for future research.

Deletion of INMAP postpones mitotic exit and induces apoptosis by disabling the formation of mitotic spindle.

INMAP was first identified as a spindle protein that plays important roles in cell-cycle progression, and previous studies have revealed that its abnormal expression leads to mitotic disorder and the growth inhibition of human tumor xenografts, but the underlying mechanism is still unclear. In this study, we knocked out INMAP in HEK293T cells, a strain of human embryonic renal cells, through CRISPR-Cas9 gene editing technology, resulting in obvious cell growth inhibition. In this system, the deletion of INMAP caused obviously apoptosis. And we also found that knockout of INMAP caused micronuclei formation, chromosome aberration, and γH2AX expression upregulation, suggesting DNA damage induction and genomic stability impairment. As a principal component of spindle, the expression of ß-tubulin, detected through Western blot, is obviously upregulated in HEK293T-INMAP-/-. Meanwhile, the level of Cyclin B is also upregulated, whereas, that of Cyclin E, downregulated, with the postponement of mitotic exit and the assembly anomaly of spindle. These results suggest that the deletion of INMAP block the formation of spindle, leading to arrest of cell cycle and DNA damage, finally blocking cell proliferation and inducing apoptosis. Therefore, INMAP is an indispensable factor for genomic integrity and normal mitotic exit.