Receive a weekly summary and discussion of the top papers of the week by leading researchers in the field.

General General

MS-Net: Sleep apnea detection in PPG using multi-scale block and shadow module one-dimensional convolutional neural network.

In Computers in biology and medicine

Sleep Apnea (SA) is a respiratory disorder that affects sleep. However, the SA detection method based on polysomnography is complex and not suitable for home use. The detection approach using Photoplethysmography is low cost and convenient, which can be used to widely detect SA. This study proposed a method combining a multi-scale one-dimensional convolutional neural network and a shadow one-dimensional convolutional neural network based on dual-channel input. The time-series feature information of different segments were extracted from multi-scale temporal structure. Moreover, shadow module was adopted to make full use of the redundant information generated after multi-scale convolution operation, which improved the accuracy and ensured the portability of the model. At the same time, we introduced balanced bootstrapping and class weight, which effectively alleviated the problem of unbalanced classes. Our method achieved the result of 82.0% average accuracy, 74.4% average sensitivity and 85.1% average specificity for per-segment SA detection, and reached 93.6% average accuracy for per-recording SA detection after 5-fold cross validation. Experimental results show that this method has good robustness. It can be regarded as an effective aid in SA detection in household use.

Wei Keming, Zou Lang, Liu Guanzheng, Wang Changhong

2023-Jan-09

Multi-scale convolution, Photoplethysmography (PPG), Shadow module, Sleep Apnea (SA)

Surgery Surgery

Artificial intelligence to de-escalate loco-regional breast cancer treatment.

In Breast (Edinburgh, Scotland)

In this review, we evaluate the potential and recent advancements in using artificial intelligence techniques to de-escalate loco-regional breast cancer therapy, with a special focus on surgical treatment after neoadjuvant systemic treatment (NAST). The increasing use and efficacy of NAST make the optimal loco-regional management of patients with pathologic complete response (pCR) a clinically relevant knowledge gap. It is hypothesized that patients with pCR do not benefit from therapeutic surgery because all tumor has already been eradicated by NAST. It is unclear, however, how residual cancer after NAST can be reliably excluded prior to surgery to identify patients eligible for omitting breast cancer surgery. Evidence from clinical trials evaluating the potential of imaging and minimally-invasive biopsies to exclude residual cancer suggests that there is a high risk of missing residual cancer. More recently, AI-based algorithms have shown promising results to reliably exclude residual cancer after NAST. This example illustrates the great potential of AI-based algorithms to further de-escalate and individualize loco-regional breast cancer treatment.

Pfob André, Heil Joerg

2023-Feb-20

Artificial intelligence, Complete response, De-escalation, Machine learning, Neoadjuvant systemic treatment, Vacuum-assisted biopsy

General General

A Cre-LoxP-based approach for combinatorial chromosome rearrangements in human HAP1 cells.

In Chromosome research : an international journal on the molecular, supramolecular and evolutionary aspects of chromosome biology

Alterations of human karyotype caused by chromosomal rearrangements are often associated with considerable phenotypic effects. Studying molecular mechanisms underlying these effects requires an efficient and scalable experimental model. Here, we propose a Cre-LoxP-based approach for the generation of combinatorial diversity of chromosomal rearrangements. We demonstrate that using the developed system, both intra- and inter-chromosomal rearrangements can be induced in the human haploid HAP1 cells, although the latter is significantly less effective. The obtained genetically modified HAP1 cell line can be used to dissect genomic effects associated with intra-chromosomal structural variations.

Khabarova Anna, Koksharova Galina, Salnikov Pavel, Belokopytova Polina, Mungalov Roman, Pristyazhnuk Inna, Nurislamov Artem, Gridina Maria, Fishman Veniamin

2023-Feb-26

Cell line models, Chromosome rearrangement, Cre/LoxP system, Genome editing

General General

Comprehensive landscape of immune-based classifier related to early diagnosis and macrophage M1 in spinal cord injury.

In Aging ; h5-index 49.0

Numerous studies have documented that immune responses are crucial in the pathophysiology of spinal cord injury (SCI). Our study aimed to uncover the function of immune-related genes (IRGs) in SCI. Here, we comprehensively evaluated the transcriptome data of SCI and healthy controls (HC) obtained from the GEO Database integrating bioinformatics and experiments. First, a total of 2067 DEGs were identified between the SCI and HC groups. Functional enrichment analysis revealed substantial immune-related pathways and functions that were abnormally activated in the SCI group. Immune analysis revealed that myeloid immune cells were predominantly upregulated in SCI patients, while a large number of lymphoid immune cells were dramatically downregulated. Subsequently, 51 major IRGs were screened as key genes involved in SCI based on the intersection of the results of WGCNA analysis, DEGs, and IRGs. Based on the expression profiles of these genes, two distinct immune modulation patterns were recognized exhibiting opposite immune characteristics. Moreover, 2 core IRGs (FCER1G and NFATC2) were determined to accurately predict the occurrence of SCI via machine learning. qPCR analysis was used to validate the expression of core IRGs in an external independent cohort. Finally, the expression of these core IRGs was validated by sequencing, WB, and IF analysis in vivo. We found that these two core IRGs were closely associated with immune cells and verified the co-localization of FCER1G with macrophage M1 via IF analysis. Our study revealed the key role of immune-related genes in SCI and contributed to a fresh perspective for early diagnosis and treatment of SCI.

Zhang Zhao, Zhu Zhijie, Wang Xuankang, Liu Dong, Liu Xincheng, Mi Zhenzhou, Tao Huiren, Fan Hongbin

2023-Feb-23

diagnosis, immune, machine learning, macrophage, spinal cord injury

General General

Inequities in Mental Health Care facing Racialized Immigrant Older Adults with Mental Disorders despite Universal Coverage: A Population-based Study in Canada.

In The journals of gerontology. Series B, Psychological sciences and social sciences

OBJECTIVES : Contemporary immigration scholarship has typically treated immigrants with diverse racial backgrounds as a monolithic population. Knowledge gaps remain in understanding how racial and nativity inequities in mental health care intersect and unfold in midlife and old age. This study aims to examine the joint impact of race, migration, and old age in shaping mental health treatment.

METHODS : Pooled data were obtained from the Canadian Community Health Survey (2015-2018) and restricted to respondents (aged ≥ 45 years) with mood or anxiety disorders (n=9,099). We employed multivariable logistic regression to estimate associations between race-migration nexus and past-year mental health consultations (MHC). We used Classification and Regression Tree (CART) analysis to identify intersecting determinants of MHC.

RESULTS : Compared to Canadian-born Whites, racialized immigrants had greater mental health needs: poor/fair SRMH (OR=2.23, 99% CI: 1.67 - 2.99), perceived life stressful (OR=1.49, 99% CI: 1.14 - 1.95), psychiatric comorbidity (OR=1.42, 99%CI: 1.06 - 1.89) and unmet needs for care (OR=2.02, 99% CI: 1.36 - 3.02); in sharp contrast, they were less likely to access mental health services across most indicators: overall past-year MHC (OR=0.54, 99% CI: 0.41 - 0.71) and consultations with family doctors (OR=0.67, 99% CI: 0.50 - 0.89), psychologists (OR=0.67, 99% CI: 0.50 - 0.89), and social workers (OR=0.67, 99% CI: 0.50 - 0.89), with the exception of psychiatrist visits (p=0.324). The CART algorithm identifies three groups at risk of MHC service underuse: racialized immigrants aged ≥ 55 years; immigrants without high school diplomas; and linguistic minorities who were home renters.

DISCUSSION : To safeguard health care equity for medically underserved communities in Canada, multisectoral efforts need to guarantee culturally responsive mental health care, multilingual services, and affordable housing for racialized immigrant older adults with mental disorders.

Lin Shen Lamson

2023-Feb-26

Geriatric psychiatry, Machine Learning, Mental health treatment, Migration, Minority aging

Radiology Radiology

Knowledge-enhanced Pre-training for Auto-diagnosis of Chest Radiology Images

ArXiv Preprint

Despite of the success of multi-modal foundation models pre-trained on large-scale data in natural language understanding and vision recognition, its counterpart in medical and clinical domains remains preliminary, due to the fine-grained recognition nature of the medical tasks with high demands on domain knowledge. Here, we propose a knowledge-enhanced vision-language pre-training approach for auto-diagnosis on chest X-ray images. The algorithm, named Knowledge-enhanced Auto Diagnosis~(KAD), first trains a knowledge encoder based on an existing medical knowledge graph, i.e., learning neural embeddings of the definitions and relationships between medical concepts and then leverages the pre-trained knowledge encoder to guide the visual representation learning with paired chest X-rays and radiology reports. We experimentally validate KAD's effectiveness on three external X-ray datasets. The zero-shot performance of KAD is not only comparable to that of the fully-supervised models but also, for the first time, superior to the average of three expert radiologists for three (out of five) pathologies with statistical significance. When the few-shot annotation is available, KAD also surpasses all existing approaches in finetuning settings, demonstrating the potential for application in different clinical scenarios.

Xiaoman Zhang, Chaoyi Wu, Ya Zhang, Yanfeng Wang, Weidi Xie

2023-02-27