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

General General

The nonalcoholic fatty liver risk in prediction of unfavorable outcome after stroke: A nationwide registry analysis.

In Computers in biology and medicine

Few researches have looked at the relationship between nonalcoholic fatty liver disease (NAFLD) at the time of admission and the long-term outcomes of patients suffering from acute ischemic stroke (AIS). We aimed to probe the relationship between NAFLD risk evaluated by NAFLD indices and long-term endpoints, along with the prognostic value of merging NAFLD indices with established risk markers for the prognosis of AIS patients. The fatty liver index (FLI) and the Hepatic steatosis index (HSI) were used to evaluate NAFLD risk in the Third China National Stroke Registry (CNSR-III), a large, prospective, national, multicenter cohort registry study. NAFLD was defined as FLI ≥35 for males and FLI ≥ 20 for females, as well as HSI>36. Death or major disability (modified Rankin Scale score ≥3) were the primary outcomes following the beginning of a stroke. On patient outcomes, the prognostic performance of two objective NAFLD parameters was evaluated. NAFLD was detected in 32.10-51.90% of AIS patients. After 1-year, 14.5% of the participants had died or suffered a severe outcome. After controlling for known risk factors, NAFLD was associated with a modest probability of adverse outcome (odds ratio,0.72[95% CI, 0.61-0.86] for FLI; odds ratio,0.68[95% CI, 0.55-0.85] for HSI). The inclusion of the two NAFLD indicators in the conventional prediction model was justified by the integrated discrimination index, continuing to increase the model's overall predictive value for long-term adverse outcomes. NAFLD risk was linked to a lower risk of long-term death or major disability in people with AIS. The predictive value of objective NAFLD after AIS was demonstrated in our study.

Chen Keyang, Pan Yuesong, Xiang Xianglong, Meng Xia, Yao Dongxiao, Lin Li, Li Xiaokun, Wang Yongjun

2023-Feb-28

Data mining, Medical diagnosis, Non-alcoholic fatty liver disease, Stroke functional outcome, Stroke prognosis

General General

A review of deep learning-based multiple-lesion recognition from medical images: classification, detection and segmentation.

In Computers in biology and medicine

Deep learning-based methods have become the dominant methodology in medical image processing with the advancement of deep learning in natural image classification, detection, and segmentation. Deep learning-based approaches have proven to be quite effective in single lesion recognition and segmentation. Multiple-lesion recognition is more difficult than single-lesion recognition due to the little variation between lesions or the too wide range of lesions involved. Several studies have recently explored deep learning-based algorithms to solve the multiple-lesion recognition challenge. This paper includes an in-depth overview and analysis of deep learning-based methods for multiple-lesion recognition developed in recent years, including multiple-lesion recognition in diverse body areas and recognition of whole-body multiple diseases. We discuss the challenges that still persist in the multiple-lesion recognition tasks by critically assessing these efforts. Finally, we outline existing problems and potential future research areas, with the hope that this review will help researchers in developing future approaches that will drive additional advances.

Jiang Huiyan, Diao Zhaoshuo, Shi Tianyu, Zhou Yang, Wang Feiyu, Hu Wenrui, Zhu Xiaolin, Luo Shijie, Tong Guoyu, Yao Yu-Dong

2023-Mar-01

Classification, Deep learning, Detection, Medical image, Segmentation

General General

Identification of small open reading frames in plant lncRNA using class-imbalance learning.

In Computers in biology and medicine

Recently, small open reading frames (sORFs) in long noncoding RNA (lncRNA) have been demonstrated to encode small peptides that can help study the mechanisms of growth and development in organisms. Since machine learning-based computational methods are less costly compared with biological experiments, they can be used to identify sORFs and provide a basis for biological experiments. However, few computational methods and data resources have been exploited for identifying sORFs in plant lncRNA. Besides, machine learning models produce underperforming classifiers when faced with a class-imbalance problem. In this study, an alternative method called SMOTE based on weighted cosine distance (WCDSMOTE) which enables interaction with feature selection is put forward to synthesize minority class samples and weighted edited nearest neighbor (WENN) is applied to clean up majority class samples, thus, hybrid sampling WCDSMOTE-ENN is proposed to deal with imbalanced datasets with the multi-angle feature. A heterogeneous classifier ensemble is introduced to complete the classification task. Therefore, a novel computational method that is based on class-imbalance learning to identify the sORFs with coding potential in plant lncRNA (sORFplnc) is presented. Experimental results manifest that sORFplnc outperforms existing computational methods in identifying sORFs with coding potential. We anticipate that the proposed work can be a reference for relevant research and contribute to agriculture and biomedicine.

Zhao Siyuan, Meng Jun, Wekesa Jael Sanyanda, Luan Yushi

2023-Mar-11

Class-imbalance learning, Ensemble learning, Feature selection, Hybrid resampling, lncRNA, sORFs

Public Health Public Health

Machine-learning analysis of opioid use disorder informed by MOR, DOR, KOR, NOR and ZOR-based interactome networks.

In Computers in biology and medicine

Opioid use disorder (OUD) continuously poses major public health challenges and social implications worldwide with dramatic rise of opioid dependence leading to potential abuse. Despite that a few pharmacological agents have been approved for OUD treatment, the efficacy of said agents for OUD requires further improvement in order to provide safer and more effective pharmacological and psychosocial treatments. Proteins including mu, delta, kappa, nociceptin, and zeta opioid receptors are the direct targets of opioids and play critical roles in therapeutic treatments. The protein-protein interaction (PPI) networks of the these receptors increase the complexity in the drug development process for an effective opioid addiction treatment. The report below presents a PPI-network informed machine-learning study of OUD. We have examined more than 500 proteins in the five opioid receptor networks and subsequently collected 74 inhibitor datasets. Machine learning models were constructed by pairing gradient boosting decision tree (GBDT) algorithm with two advanced natural language processing (NLP)-based autoencoder and Transformer fingerprints for molecules. With these models, we systematically carried out evaluations of screening and repurposing potential of more than 120,000 drug candidates for four opioid receptors. In addition, absorption, distribution, metabolism, excretion, and toxicity (ADMET) properties were also considered in the screening of potential drug candidates. Our machine-learning tools determined a few inhibitor compounds with desired potency and ADMET properties for nociceptin opioid receptors. Our approach offers a valuable and promising tool for the pharmacological development of OUD treatments.

Feng Hongsong, Elladki Rana, Jiang Jian, Wei Guo-Wei

2023-Mar-08

Cross-prediction, Machine-learning, Opioid receptor, Opioid use disorder, Repurposing, Side effect

General General

Attention is not all you need: the complicated case of ethically using large language models in healthcare and medicine.

In EBioMedicine

Large Language Models (LLMs) are a key component of generative artificial intelligence (AI) applications for creating new content including text, imagery, audio, code, and videos in response to textual instructions. Without human oversight, guidance and responsible design and operation, such generative AI applications will remain a party trick with substantial potential for creating and spreading misinformation or harmful and inaccurate content at unprecedented scale. However, if positioned and developed responsibly as companions to humans augmenting but not replacing their role in decision making, knowledge retrieval and other cognitive processes, they could evolve into highly efficient, trustworthy, assistive tools for information management. This perspective describes how such tools could transform data management workflows in healthcare and medicine, explains how the underlying technology works, provides an assessment of risks and limitations, and proposes an ethical, technical, and cultural framework for responsible design, development, and deployment. It seeks to incentivise users, developers, providers, and regulators of generative AI that utilises LLMs to collectively prepare for the transformational role this technology could play in evidence-based sectors.

Harrer Stefan

2023-Mar-14

AI ethics, AI trustworthiness, Augmented human intelligence, Foundation models, Generative artificial intelligence, Information management, Large language models

General General

BCM-DTI: A fragment-oriented method for drug-target interaction prediction using deep learning.

In Computational biology and chemistry

The identification of drug-target interaction (DTI) is significant in drug discovery and development, which is usually of high cost in time and money due to large amount of molecule and protein space. The application of deep learning in predicting DTI pairs can overcome these limitations through feature engineering. However, most works do the features extraction using the whole drug and target, which do not take the theoretical basis of pharmacological reaction that the interaction is closely related to some substructure of molecule and protein into consideration, thus poor in performance. On the other hand, some substructure-oriented studies only consider a single type of fragment, e.g., functional group. To address these issues, we propose an end-to-end predicting framework for drug-target interaction named BCM-DTI that takes diverse fragment types into account, including branch chain, common substructure and motif/fragments, and applies a feature learning module based on CNN to learn the synergistic effect between these fragments. We implement BCM-DTI on four public datasets, and the results show that BCM-DTI outperforms state-of-the-art approaches and requires lower training cost.

Dou Liang, Zhang Zhen, Liu Dan, Qian Ying, Zhang Qian

2023-Mar-05

Deep learning, Drug–target interaction, Fragment