Artificial Neural Networks in Medicine

Artificial neural networks (ANNs) have proven to be efficacious for modeling decision problems in medicine, including diagnosis, prognosis, resource allocation, and cost reduction problems. Research using ANNs to solve medical domain problems has been increasing regularly and is continuing to grow dramatically. This chapter examines recent trends and advances in ANNs and provides references to a large portion of recent research, as well as looking at the future direction of research for ANN in medicine.

Digital phenotyping and the (data) shadow of Alzheimer's disease

In this paper, we examine the practice and promises of digital phenotyping. We build on work on the ‘data self’ to focus on a medical domain in which the value and nature of knowledge and relations with data have been played out with particular persistence, that of Alzheimer's disease research. Drawing on research with researchers and developers, we consider the intersection of hopes and concerns related to both digital tools and Alzheimer's disease using the metaphor of the ‘data shadow’. We suggest that as a tool for engaging with the nature of the data self, the shadow is usefully able to capture both the dynamic and distorted nature of data representations, and the unease and concern associated with encounters between individuals or groups and data about them. We then consider what the data shadow ‘is’ in relation to ageing data subjects, and the nature of the representation of the individual's cognitive state and dementia risk that is produced by digital tools. Second, we consider what the data shadow ‘does’, through researchers and practitioners’ discussions of digital phenotyping practices in the dementia field as alternately empowering, enabling and threatening.

Overlooked Trustworthiness of Explainability in Medical AI

While various methods have been proposed to explain AI models, the trustworthiness of the generated explanation received little examination. This paper reveals that such explanations could be vulnerable to subtle perturbations on the input and generate misleading results. On the public CheXpert dataset, we demonstrate that specially designed adversarial perturbations can easily tamper saliency maps towards the desired explanations while preserving the original model predictions. AI researchers, practitioners, and authoritative agencies in the medical domain should use caution when explaining AI models because such an explanation could be irrelevant, misleading, and even adversarially manipulated without changing the model output.

KNOWLEDGE-BASED VS EVIDENCE-BASED – COULD SPELL THE DIFFERENCE BETWEEN HEALTH & ILL-HEALTH!

Dear Reader, It has been so truly said by Otto von Bismarck [former President of Prussia (German State) in 19th century] — ‘Only a fool learns from his own mistakes. The wise man learns from the mistakes of others.’ It is the 10% existent wise men that lead - 90% trudge behind as followers – be it the political scenario, spiritual realm or world of science. Wise men become powerful and in the current Forbes list of such top 10 are 6 politicians, 1 religious head & 3 mega global entrepreneurs. In enterprises, when it comes to science and discovery, only 3 out of the top 10 have excelled in contributing to the world of medicine! Leaders are rare & leaders in medical domain are even rarer!

Enhancing unsupervised medical entity linking with multi-instance learning

Background A lot of medical mentions can be extracted from a huge amount of medical texts. In order to make use of these medical mentions, a prerequisite step is to link those medical mentions to a medical domain knowledge base (KB). This linkage of mention to a well-defined, unambiguous KB is a necessary part of the downstream application such as disease diagnosis and prescription of drugs. Such demand becomes more urgent in colloquial and informal situations like online medical consultation, where the medical language is more casual and vaguer. In this article, we propose an unsupervised method to link the Chinese medical symptom mentions to the ICD10 classification in a colloquial background. Methods We propose an unsupervised entity linking model using multi-instance learning (MIL). Our approach builds on a basic unsupervised entity linking method (named BEL), which is an embedding similarity-based EL model in this paper, and uses MIL training paradigm to boost the performance of BEL. First, we construct a dataset from an unlabeled large-scale Chinese medical consultation corpus with the help of BEL. Subsequently, we use a variety of encoders to obtain the representations of mention-context and the ICD10 entities. Then the representations are fed into a ranking network to score candidate entities. Results We evaluate the proposed model on the test dataset annotated by professional doctors. The evaluation results show that our method achieves 60.34% accuracy, exceeding the fundamental BEL by 1.72%. Conclusions We propose an unsupervised entity linking method to the entity linking in the medical domain, using MIL training manner. We annotate a test set for evaluation. The experimental results show that our model behaves better than the fundamental model BEL, and provides an insight for future research.

Symbiosis and Dysbiosis of the Human Mycobiome

The influence of microbiological species has gained increased visibility and traction in the medical domain with major revelations about the role of bacteria on symbiosis and dysbiosis. A large reason for these revelations can be attributed to advances in deep-sequencing technologies. However, the research on the role of fungi has lagged. With the continued utilization of sequencing technologies in conjunction with traditional culture assays, we have the opportunity to shed light on the complex interplay between the bacteriome and the mycobiome as they relate to human health. In this review, we aim to offer a comprehensive overview of the human mycobiome in healthy and diseased states in a systematic way. The authors hope that the reader will utilize this review as a scaffolding to formulate their understanding of the mycobiome and pursue further research.

Disease Named Entity Recognition (D-NER) Evaluation

Named Entity Recognition (NER) is a key task in Natural Language Processing (NLP). In medical domain, NER is very important phase in all end-to-end systems. In this paper, we investigate the performance of NER for disease (D-NER). TaggerOne was evaluated on 52 cardiovascular-related clinical case reports against hand annotation for diseases. Different training sets have been used to evaluate the performance of TaggerOne as a famous tool for NER in biomedical domain.

A knowledge graph based question answering method for medical domain

Question answering (QA) is a hot field of research in Natural Language Processing. A big challenge in this field is to answer questions from knowledge-dependable domain. Since traditional QA hardly satisfies some knowledge-dependable situations, such as disease diagnosis, drug recommendation, etc. In recent years, researches focus on knowledge-based question answering (KBQA). However, there still exist some problems in KBQA, traditional KBQA is limited by a range of historical cases and takes too much human labor. To address the problems, in this paper, we propose an approach of knowledge graph based question answering (KGQA) method for medical domain, which firstly constructs a medical knowledge graph by extracting named entities and relations between the entities from medical documents. Then, in order to understand a question, it extracts the key information in the question according to the named entities, and meanwhile, it recognizes the questions’ intentions by adopting information gain. The next an inference method based on weighted path ranking on the knowledge graph is proposed to score the related entities according to the key information and intention of a given question. Finally, it extracts the inferred candidate entities to construct answers. Our approach can understand questions, connect the questions to the knowledge graph and inference the answers on the knowledge graph. Theoretical analysis and real-life experimental results show the efficiency of our approach.

Goal-Driven Visual Question Generation from Radiology Images

Visual Question Generation (VQG) from images is a rising research topic in both fields of natural language processing and computer vision. Although there are some recent efforts towards generating questions from images in the open domain, the VQG task in the medical domain has not been well-studied so far due to the lack of labeled data. In this paper, we introduce a goal-driven VQG approach for radiology images called VQGRaD that generates questions targeting specific image aspects such as modality and abnormality. In particular, we study generating natural language questions based on the visual content of the image and on additional information such as the image caption and the question category. VQGRaD encodes the dense vectors of different inputs into two latent spaces, which allows generating, for a specific question category, relevant questions about the images, with or without their captions. We also explore the impact of domain knowledge incorporation (e.g., medical entities and semantic types) and data augmentation techniques on visual question generation in the medical domain. Experiments performed on the VQA-RAD dataset of clinical visual questions showed that VQGRaD achieves 61.86% BLEU score and outperforms strong baselines. We also performed a blinded human evaluation of the grammaticality, fluency, and relevance of the generated questions. The human evaluation demonstrated the better quality of VQGRaD outputs and showed that incorporating medical entities improves the quality of the generated questions. Using the test data and evaluation process of the ImageCLEF 2020 VQA-Med challenge, we found that relying on the proposed data augmentation technique to generate new training samples by applying different kinds of transformations, can mitigate the lack of data, avoid overfitting, and bring a substantial improvement in medical VQG.