Background: Conversational agents, also known as chatbots, are computer programs designed to simulate human text or verbal conversations. They are increasingly used in a range of fields, including health care. By enabling better accessibility, personalization, and efficiency, conversational agents have the potential to improve patient care.
Objective: This study aimed to review the current applications, gaps, and challenges in the literature on conversational agents in health care and provide recommendations for their future research, design, and application.
Methods: We performed a scoping review. A broad literature search was performed in MEDLINE (Medical Literature Analysis and Retrieval System Online; Ovid), EMBASE (Excerpta Medica database; Ovid), PubMed, Scopus, and Cochrane Central with the search terms “conversational agents,” “conversational AI,” “chatbots,” and associated synonyms. We also searched the gray literature using sources such as the OCLC (Online Computer Library Center) WorldCat database and ResearchGate in April 2019. Reference lists of relevant articles were checked for further articles. Screening and data extraction were performed in parallel by 2 reviewers. The included evidence was analyzed narratively by employing the principles of thematic analysis.
Results: The literature search yielded 47 study reports (45 articles and 2 ongoing clinical trials) that matched the inclusion criteria. The identified conversational agents were largely delivered via smartphone apps (n=23) and used free text only as the main input (n=19) and output (n=30) modality. Case studies describing chatbot development (n=18) were the most prevalent, and only 11 randomized controlled trials were identified. The 3 most commonly reported conversational agent applications in the literature were treatment and monitoring, health care service support, and patient education.
Conclusions: The literature on conversational agents in health care is largely descriptive and aimed at treatment and monitoring and health service support. It mostly reports on text-based, artificial intelligence–driven, and smartphone app–delivered conversational agents. There is an urgent need for a robust evaluation of diverse health care conversational agents’ formats, focusing on their acceptability, safety, and effectiveness.

/pdf/conversational-agents-in-health-care-scoping-review-and-vmy2djyc16.pdf

Conversational Agents in Health Care: Scoping Review and Conceptual Analysis.

Cervical cancer is one of the most common and deadliest cancers among women. Despite that, this cancer is entirely treatable if it is detected at a precancerous stage. Pap smear test is the most extensively performed screening method for early detection of cervical cancer. However, this hand-operated screening approach suffers from a high false-positive result because of human errors. To improve the accuracy and manual screening practice, computer-aided diagnosis methods based on deep learning is developed widely to segment and classify the cervical cytology images automatically. In this survey, we provide a comprehensive study of the state of the art approaches based on deep learning for the analysis of cervical cytology images. Firstly, we introduce deep learning and its simplified architectures that have been used in this field. Secondly, we discuss the publicly available cervical cytopathology datasets and evaluation metrics for segmentation and classification tasks. Then, a thorough review of the recent development of deep learning for the segmentation and classification of cervical cytology images is presented. Finally, we investigate the existing methodology along with the most suitable techniques for the analysis of pap smear cells.

/pdf/a-survey-for-cervical-cytopathology-image-analysis-using-2b0y8mba9s.pdf

A Survey for Cervical Cytopathology Image Analysis Using Deep Learning

DeepCervix: A deep learning-based framework for the classification of cervical cells using hybrid deep feature fusion techniques.

Detection of cervical cancer cells based on strong feature CNN-SVM network

Health knowledge graph provides an ideal technical means to integrate heterogeneous data resources and enhance knowledge-based services There are many challenges for the construction of health knowledge graph such as complex concepts and relationships, various medical standards, heterogeneous data structures, poor data quality, highly accurate and interpretable services, etc In this paper, firstly, we propose Health Knowledge Graph Builder (HKGB), an end-to-end platform which could be used to construct disease-specific and extensible health knowledge graphs from multiple sources Secondly, we analyze the capabilities and requirements of clinicians, design the tasks to involve the clinicians and implement a clinician-in-the-loop toolset to integrate the clinicians prior knowledge into the construction of health knowledge graphs Thirdly, we design an extensible mechanism to add new diseases to an existing knowledge graph Fourthly, we present a quantitative effort estimation algorithm to quantitatively evaluate the effort of clinicians during the construction, and use it to calculate the workloads such as 4427 person days for knee osteoarthritis domain Finally, we have developed several knowledge graph based tools to facilitate real applications

HKGB: An Inclusive, Extensible, Intelligent, Semi-auto-constructed Knowledge Graph Framework for Healthcare with Clinicians’ Expertise Incorporated

Cervical cancer is a disease that affects 266,000 deaths worldwide and is the fourth highest incidence of cancer in women. This cancer can be diagnosed through a Pap smear, where a cytopathologist observes a microscopic image of the cervix cells to determine whether the patient is normal or abnormal. The sensitivity and specificity of the Pap smear is known to be respectively 53.4% and 69.2%. Since the test is related to the patient's life, it is important to improve the accuracy of the test. A variety of systems have been proposed to help judge experts to improve the accuracy of tests in the medical field, but the development of these systems has been limited to areas where digitized test data are clearly present. In this paper, we design and propose a model that automatically classifies normal/abnormal states of cervical cells from microscopic images using convolutional neural network and several machine learning classifiers. As a result, the support vector machine showed the best performance with a 78% F1 score.

Diagnosing cervical cell images using pre-trained convolutional neural network as feature extractor

Cervical cancer is the women's fourth most common cancer worldwide, with 266,000 deaths in a year. Cervical cancer can be diagnosed by the Papanicolaou test. In this test, a cytopathologist observes a microscopic image of the cervix cells and decides whether the patient is abnormal or not. According to research, the accuracy of the cervical cytology is reported as 89.7%. Because it is associated with the patient's life, it is important to improve the accuracy of this test. Many systems have been proposed to help judge experts to improve the accuracy of tests in the medical field, but development has been limited to areas where there are cleanly quantified test data. In this paper, we design and train a model to automatically classify the normal/abnormal state of cervical cells from microscopic images by using a convolutional neural network and several machine learning classifiers. As a result, the support vector machine achieves the highest performance with 78% F1 score.

Automating Papanicolaou Test Using Deep Convolutional Activation Feature

Diffuse gliomas are the most common primary brain tumors and they vary considerably in their morphology, location, genetic alterations, and response to therapy. In 2016, the World Health Organization (WHO) provided new guidelines for making an integrated diagnosis that incorporates both morphologic and molecular features to diffuse gliomas. In this study, we demonstrate how deep learning approaches can be used for an automatic classification of glioma subtypes and grading using whole-slide images that were obtained from routine clinical practice. A deep transfer learning method using the ResNet50V2 model was trained to classify subtypes and grades of diffuse gliomas according to the WHO's new 2016 classification. The balanced accuracy of the diffuse glioma subtype classification model with majority voting was 0.8727. These results highlight an emerging role of deep learning in the future practice of pathologic diagnosis.

https://www.mdpi.com/1424-8220/21/10/3500/pdf

Classification of Diffuse Glioma Subtype from Clinical-Grade Pathological Images Using Deep Transfer Learning.

In this paper, we present two approaches to generate prognosis from general blood test results. The first approach is a knowledge-based approach using ripple-down rules (RDR). The knowledge-based approach with RDR converts knowledge of pathologists into a knowledge base with the minimum intervention of knowledge engineers. The second approach is a machine-learning(ML)-based approach using decision tree, random forest and deep neural network (DNN). The ML-based approach learns patterns of attributes from various cases of general blood test. Our experimental results show that there are indeed some important patterns of the attributes in general blood test results, and they are adequately encoded by the both approaches.

Medical Prognosis Generation from General Blood Test Results Using Knowledge-Based and Machine-Learning-Based Approaches

This paper describes how we build an initial knowledge-base of ripple-down rules (RDR) in medical domain. In medical domain, all decisions are made by the domain experts. Increasing a complexity of disease and various symptoms, there are some attempts to introduce an expert system in medical domain these days. To construct the expert system, it needs to extract the expert's knowledge. To do that, we use ripple-down rules (RDR) which allows experts to modify their knowledge base directly because it provides a systematic approach to do that. We also use Induct RDR which builds a knowledge base from existing data to reduce experts' burden of adding their knowledge from the bottom up. The expert system should produce multiple comments from a test set, which is multiple classification problem. However, Induct RDR only deals with a single classification problem. To handle this problem, we divide a test set into 18 categories which is almost the single classification problem and apply Induct RDR to each category independently. Using this approach, we can improve the missing rate about 70% compared to an approach not dividing into several categories.

/pdf/constructing-an-initial-knowledge-base-for-medical-domain-1bsqzid4ly.pdf

Jonghwan Hyeon

Papers

Diagnosing cervical cell images using pre-trained convolutional neural network as feature extractor

Automating Papanicolaou Test Using Deep Convolutional Activation Feature

Classification of Diffuse Glioma Subtype from Clinical-Grade Pathological Images Using Deep Transfer Learning.

Medical Prognosis Generation from General Blood Test Results Using Knowledge-Based and Machine-Learning-Based Approaches

Constructing an initial knowledge base for medical domain expert system using induct RDR