Cui Tao

University of Texas Health Science Center at Houston · School of Biomedical Informatics

BACKGROUND Social Determinants of Health (SDoH) have been described by the World Health Organization as the conditions in which individuals are born, live, work, and age. These conditions can be grouped into three interrelated levels, macro-, meso-, and micro-level determinants. OBJECTIVE Providing a computable artifact that can link health data t...

Background The utilization of dermoscopic analysis is becoming increasingly critical for diagnosing skin diseases by physicians and even artificial intelligence. With the expansion of dermoscopy, its vocabulary has proliferated, but the rapid evolution of the vocabulary of dermoscopy without standardized control is counterproductive. We aimed to de...

BACKGROUND Dermoscopy is a growing field using microscopy to identify skin lesions by dermatologists and primary care physicians. For a given skin lesion, a wide variety of differential diagnoses exist, which may be challenging for inexperienced users to name and understand. OBJECTIVE In this study, we describe the creation of the Dermoscopy Diffe...

Conversation as trivial as “small talk” has a significant impact on human relationships, including in clinical care environments. Evidence suggests that small talk can improve health and clinical outcomes. This study aims to analyze the characteristics of domain-independent small talk collected from a sample of conversations. We reviewed the impact...

This is the poster representing our accepted abstract at the EASL congress 2023

Graph representation learning (GRL) has emerged as a pivotal field that has contributed significantly to breakthroughs in various fields, including biomedicine. The objective of this survey is to review the latest advancements in GRL methods and their applications in the biomedical field. We also highlight key challenges currently faced by GRL and...

Generating categories and classifications is a common function in life science research; however, categorizing the human population based on "race" remains controversial. There is an awareness and recognition of social-economic disparities with respect to health which are sometimes impacted by someone's ethnicity or race. This work describes an end...

Objective: Social determinants of health (SDoH) play critical roles in health outcomes and well-being. Understanding the interplay of SDoH and health outcomes is critical to reducing healthcare inequalities and transforming a "sick care" system into a "health-promoting" system. To address the SDOH terminology gap and better embed relevant elements...

Background: While hypertension is a modifiable risk factor of Alzheimer's disease and related dementias (ADRD), limited studies have been conducted on the effectiveness of antihypertensive medications (AHMs) in altering the progression from mild cognitive impairment (MCI) to ADRD; similarly, few studies have assessed drug-drug interactions of AHMs...

Objectives: Suicide presents a major public health challenge worldwide, affecting people across the lifespan. While previous studies revealed strong associations between Social Determinants of Health (SDoH) and suicide deaths, existing evidence is limited by the reliance on structured data. To resolve this, we aim to adapt a suicide-specific SDoH...

Model card reports provide a transparent description of machine learning models which includes information about their evaluation, limitations, intended use, etc. Federal health agencies have expressed an interest in model cards report for research studies using machine-learning based AI. Previously, we have developed an ontology model for model ca...

Background Existing studies on cardiovascular diseases (CVDs) often focus on individual‐level behavioral risk factors, but research examining social determinants is limited. This study applies a novel machine learning approach to identify the key predictors of county‐level care costs and prevalence of CVDs (including atrial fibrillation, acute myoc...

Background Automatic skin lesion recognition has shown to be effective in increasing access to reliable dermatology evaluation; however, most existing algorithms rely solely on images. Many diagnostic rules, including the 3-point checklist, are not considered by artificial intelligence algorithms, which comprise human knowledge and reflect the diag...

Social determinants of health (SDoH) have a significant impact on health outcomes and well-being. Addressing SDoH is the key to reducing healthcare inequalities and transforming a sick care system into a health-promoting system. To address the SDOH terminology gap and better embed relevant elements in advanced biomedical informatics, we propose an...

Background To date, there are no effective treatments for most neurodegenerative diseases. Knowledge graphs can provide comprehensive and semantic representation for heterogeneous data, and have been successfully leveraged in many biomedical applications including drug repurposing. Our objective is to construct a knowledge graph from literature to...

Background Model card reports aim to provide informative and transparent description of machine learning models to stakeholders. This report document is of interest to the National Institutes of Health’s Bridge2AI initiative to address the FAIR challenges with artificial intelligence-based machine learning models for biomedical research. We present...

Severe adverse events (AEs) after COVID-19 vaccination are not well studied in randomized controlled trials (RCTs) due to rarity and short follow-up. To monitor the safety of COVID-19 vaccines (“Pfizer” vaccine dose 1 and 2, “Moderna” vaccine dose 1 and 2, and “Janssen” vaccine single dose) in the U.S., especially regarding severe AEs, we compare t...

Measles is a highly contagious cause of febrile illness typically seen in young children. Recent years have witnessed the resurgence of measles cases in the United States. Prompt understanding of public perceptions of measles will allow public health agencies to respond appropriately promptly. We proposed a multi-task Convolutional Neural Network (...

Biomedical relation extraction plays a critical role in the construction of high-quality knowledge graphs and databases, which can further support many downstream applications. Pre-trained prompt tuning, as a new paradigm, has shown great potential in many natural language processing (NLP) tasks. Through inserting a piece of text into the original...

Ambiguity and misunderstanding of free-text clinical trial eligibility can affect the accuracy of translating trial investigators' mental model of the study population to the correct cohort identification queries. In this pilot study, to eliminate the ambiguity when parsing eligibility criteria, we built ontology-based representations to standardiz...

Background: Understanding consumers’ health information needs across all stages of the pregnancy trajectory is crucial to the development of mechanisms that allow them to retrieve high-quality, customized, and layperson-friendly health information. Objective: The objective of this study was to identify research gaps in pregnancy-related consumer i...

During the coronavirus disease pandemic (COVID-19), social media platforms such as Twitter have become a venue for individuals, health professionals, and government agencies to share COVID-19 information. Twitter has been a popular source of data for researchers, especially for public health studies. However, the use of Twitter data for research al...

The informed consent process is a complicated procedure involving permissions as well a variety of entities and actions. In this paper, we discuss the use of Semantic Web Rule Language (SWRL) to further extend the Informed Consent Ontology (ICO) to allow for semantic machine-based reasoning to manage and generate important permission-based informat...

To date, there are no effective treatments for most neurodegenerative diseases. Knowledge graphs can provide comprehensive and semantic representation for heterogeneous data, and have been successfully leveraged in many biomedical applications including drug repurposing. Our objective is to construct a knowledge graph from literature to study relat...

Background Contemporary risk scores for ischemic or bleeding event prediction after drug-eluting stent (DES) implantation are limited to the determination of a single time duration for dual antiplatelet therapy (DAPT) and lack flexibility in providing dynamic risk stratification. Objectives This study sought to develop artificial intelligence (AI)...

The quality of patient-provider communication can predict the healthcare outcomes in patients, and therefore, training dental providers to handle the communication effort with patients is crucial. In our previous work, we developed an ontology model that can standardize and represent patient-provider communication, which can later be integrated in...

Narratives can have a powerful impact on our health-related beliefs, attitudes, and behaviors. The human papillomavirus (HPV) vaccine can protect against human papillomavirus that leads to different types of cancers. However, HPV vaccination rates are low. This study explored the effectiveness of a narrative-based interactive game about the HPV vac...

Background Fast food with its abundance and availability to consumers may have health consequences due to the high calorie intake which is a major contributor to life threatening diseases. Providing nutritional information has some impact on consumer decisions to self regulate and promote healthier diets, and thus, government regulations have manda...

In 2019, the US Government announced its goal to end the HIV epidemic within 10 years, mirroring the initiatives set forth by UNAIDS. Public health prevention interventions are a crucial part of this ambitious goal. However, numerous challenges to this goal exist, including improving HIV awareness, increasing early HIV infection detection, ensuring...

LINKED CONTENT This article is linked to Wijarnpreecha et al and Huang & Nguyen papers. To view these articles, visit https://doi.org/10.1111/apt.16590 and https://doi.org/10.1111/apt.16576

To date, there are no effective treatments for most neurodegenerative diseases. However, certain foods may be associated with these diseases and bring an opportunity to prevent or delay neurodegenerative progression. Our objective is to construct a knowledge graph for neurodegenerative diseases using literature mining to study their relations with...

Background: Contemporary risk scores for ischemic or bleeding endpoint prediction after drug-eluting stent (DES) implantation have limited predictive accuracy and fixed prediction windows. Objective: This study aimed to dynamically predict the ischemic and bleeding risks in different follow-up windows for patients with DES leveraging cutting-edge m...

The informed consent process is a complicated procedure involving permissions as well a variety of entities and actions. In this paper, we discuss the use of Semantic Web Rule Language (SWRL) to further extend the Informed Consent Ontology (ICO) to allow for semantic machine-based reasoning to manage and generate important permission-based informat...

LINKED CONTENT This article is linked to Wijarnpreecha et al and Gillespie & Hayes papers. To view these articles, visit https://doi.org/10.1111/apt.16490 and https://doi.org/10.1111/apt.16512

Background The rapid growth of social media as an information channel has made it possible to quickly spread inaccurate or false vaccine information, thus creating obstacles for vaccine promotion. Objective The aim of this study is to develop and evaluate an intelligent automated protocol for identifying and classifying human papillomavirus (HPV)...

BACKGROUND Understanding consumers’ health information needs across all stages of the pregnancy trajectory is crucial to the development of mechanisms that allow them to retrieve high-quality, customized, and layperson-friendly health information. OBJECTIVE The objective of this study was to identify research gaps in pregnancy-related consumer inf...

Background Previous studies have demonstrated an association between nonselective beta-blockers (NSBBs) and lower risk of hepatocellular carcinoma (HCC) in cirrhosis. However, there has been no population-based study investigating the risk of HCC among cirrhotic patients treated using carvedilol. Aims To determine the risk of HCC among cirrhotic p...

Patient-provider communication plays a major role in healthcare with its main goal being to improve the patient’s health and build a trustworthy relationship between the patient and the doctor. Provider’s efficiency and effectiveness in communication can be improved through training in order to meet the essential elements of communication that are...

Deep learning (DL)-based predictive models from electronic health records (EHRs) deliver impressive performance in many clinical tasks. Large training cohorts, however, are often required by these models to achieve high accuracy, hindering the adoption of DL-based models in scenarios with limited training data. Recently, bidirectional encoder repre...

Objective Clinical trials are an essential part of the effort to find safe and effective prevention and treatment for COVID-19. Given the rapid growth of COVID-19 clinical trials, there is an urgent need for a better clinical trial information retrieval that supports searching by specifying criteria including both eligibility criteria and structure...

Objective: Automated analysis of vaccine postmarketing surveillance narrative reports is important to understand the progression of rare but severe vaccine adverse events (AEs). This study implemented and evaluated state-of-the-art deep learning algorithms for named entity recognition to extract nervous system disorder-related events from vaccine...

Purpose: Severe adverse events (AEs), such as Guillain-Barré syndrome (GBS) occur rarely after influenza vaccination. We identify highly associated AEs with GBS and develop prediction models for GBS using the U.S. Vaccine Adverse Event Reporting System (VAERS) reports following trivalent influenza vaccination (FLU3). Methods: This study analyzed...

With vast amounts ofpatients' medical information, electronic health records (EHRs) are becoming one of the most important data sources in biomedical and health care research. Effectively integrating data from multiple clinical sites can help provide more generalized real-world evidence that is clinically meaningful. To analyze the clinical data fr...

Because they contain detailed individual-level data on various patient characteristics including their medical conditions and treatment histories, electronic health record (EHR) systems have been widely adopted as an efficient source for health research. Compared to data from a single health system, real-world data (RWD) from multiple clinical site...

Background: Social media platforms such as YouTube are hotbeds for the spread of misinformation about vaccines. Objective: To explore how individuals are exposed to anti-vaccine misinformation on YouTube. Methods: Four networks of videos based on YouTube recommendations were collected in November 2019. Two search networks were created from pro...

A variety of severe health issues can be attributed to poor nutrition and poor eating behaviors. Research has explored the impact of nutritional knowledge on an individual’s inclination to purchase and consume certain foods. This paper introduces the Ontology of Fast Food Facts, a knowledge base that models consumer nutritional data from major fast...

Background Dyadic-based social networks analyses have been effective in a variety of behavioral- and health-related research areas. We introduce an ontology-driven approach towards social network analysis through encoding social data and inferring new information from the data. Methods The Friend of a Friend (FOAF) ontology is a lightweight social...

Background Previously, we introduced our Patient Health Information Dialogue Ontology (PHIDO) that manages the dialogue and contextual information of the session between an agent and a health consumer. In this study, we take the next step and introduce the Conversational Ontology Operator (COO), the software engine harnessing PHIDO. We also develop...

Background Semantic web technology has been applied widely in the biomedical informatics field. Large numbers of biomedical datasets are available online in the resource description framework (RDF) format. Semantic relationship mining among genes, disorders, and drugs is widely used in, for example, precision medicine and drug repositioning. Howeve...

BACKGROUND The rapid growth of social media as an information channel has made it possible to quickly spread inaccurate or false vaccine information and thus create obstacles for vaccine promotion. OBJECTIVE To develop and evaluate an intelligent automated protocol to identify and classify HPV vaccine misinformation on social media, using machine...

Objective: Young men who have sex with men (YMSM) bear a disproportionate burden of HIV infection in the United States and their risks of acquiring HIV may be shaped by complex multi-layer social networks. These networks are formed through not only direct contact with social/sex partners but also indirect anonymous contacts encountered when attend...

Importance Human papillomavirus (HPV) vaccine hesitancy or refusal is common among parents of adolescents. An understanding of public perceptions from the perspective of behavior change theories can facilitate effective and targeted vaccine promotion strategies. Objective To develop and validate deep learning models for understanding public percep...

Background: Identifying the key factors of Guillain-Barré syndrome (GBS) and predicting its occurrence are vital for improving the prognosis of patients with GBS. However, there are scarcely any publications on a forewarning model of GBS. A Bayesian network (BN) model, which is known to be an accurate, interpretable, and interaction-sensitive grap...

BACKGROUND Identifying the key factors of Guillain-Barré syndrome (GBS) and predicting its occurrence are vital for improving the prognosis of patients with GBS. However, there are scarcely any publications on a forewarning model of GBS. A Bayesian network (BN) model, which is known to be an accurate, interpretable, and interaction-sensitive graph...

Objective: Predictive disease modeling using electronic health record data is a growing field. Although clinical data in their raw form can be used directly for predictive modeling, it is a common practice to map data to standard terminologies to facilitate data aggregation and reuse. There is, however, a lack of systematic investigation of how di...

Because they contain detailed individual-level data on various patient characteristics including their medical conditions and treatment histories, electronic health record (EHR) systems have been widely adopted as an efficient source for health research. Compared to data from a single health system, real-world data (RWD) from multiple clinical site...

BACKGROUND Social media platforms such as YouTube are hotbeds for the spread of misinformation about vaccines. OBJECTIVE To explore how individuals are exposed to anti-vaccine misinformation on YouTube. METHODS Four networks of videos based on YouTube recommendations were collected in November 2019. Two search networks were created from pro- and...

With vast amounts of patients' medical information, electronic health records (EHRs) are becoming one of the most important data sources in biomedical and health care research. Effectively integrating data from multiple clinical sites can help provide more generalized real-world evidence that is clinically meaningful. To analyze the clinical data f...

Many clinical workflows depend on interactive computer systems for highly technical, conceptual work products, such as diagnoses, treatment plans, care coordination, and case management. We describe an automatic logic reasoner to verify objective specifications for these highly technical, but abstract, work products that are essential to care. The...

Background To compare the incidence and risk factors of serious infections among patients of seven common rheumatic diseases including rheumatoid arthritis (RA), systemic lupus erythematosus (SLE), polymyalgia rheumatica (PMR), Sjögren's syndrome (SS), systemic sclerosis (SSc), systemic vasculitis (VA), and other diffuse connective tissue diseases...

Background Asthma exacerbation is an acute or subacute episode of progressive worsening of asthma symptoms and can have a significant impact on patients’ quality of life. However, efficient methods that can help identify personalized risk factors and make early predictions are lacking. Objective This study aims to use advanced deep learning models...

The aim of this study is to develop an educational video game and to assess its feasibility to influence youths’ interest in e-cigarettes. We first built a prototype storytelling game with facts about e-cigarettes, and then recruited 30 participants to evaluate the game. Each participant took pre- and post-game surveys on their knowledge, risk awar...

Objective: The goal of this study is to develop a robust Time Event Ontology (TEO), which can formally represent and reason both structured and unstructured temporal information. Materials and methods: Using our previous Clinical Narrative Temporal Relation Ontology 1.0 and 2.0 as a starting point, we redesigned concept primitives (clinical even...

HIV (human immunodeficiency virus) can damage a human's immune system and cause Acquired Immunodeficiency Syndrome (AIDS) which could lead to severe outcomes, including death. While HIV infections have decreased over the last decade, there is still a significant population where the infection permeates. PrEP and PEP are two proven preventive measur...

The human papillomavirus (HPV) vaccine is the most effective way to prevent HPV-related cancers. Integrating provider vaccine counseling is crucial to improving HPV vaccine completion rates. Automating the counseling experience through a conversational agent could help improve HPV vaccine coverage and reduce the burden of vaccine counseling for pro...

Deep learning (DL) based predictive models from electronic health records (EHR) deliver impressive performance in many clinical tasks. Large training cohorts, however, are often required to achieve high accuracy, hindering the adoption of DL-based models in scenarios with limited training data size. Recently, bidirectional encoder representations f...

Natural language processing (NLP) is useful for extracting information from clinical narratives, and both traditional machine learning methods and more-recent deep learning methods have been successful in various clinical NLP tasks. These methods often depend on traditional word embeddings that are outputs of language models (LMs). Recently, method...