Jing Mei

• IBM

Visual Question Answering (VQA) becomes one of the most active research problems in the medical imaging domain. A well-known VQA challenge is the intrinsic diversity between the image and text modalities, and in the medical VQA task, there is another critical problem relying on the limited size of labelled image-question-answer data. In this study...

There has been an emerging interest in managing healthcare cost in the time of value-based care. However, many challenges arise in analyzing high-dimensional healthcare operational data and identifying actionable opportunities for cost saving in an effective way. In this paper, we proposed a comprehensive analytic pipeline for healthcare operationa...

Background Disease-drug associations provide essential information for drug discovery and disease treatment. Many disease-drug associations remain unobserved or unknown, and trials to confirm these associations are time-consuming and expensive. To better understand and explore these valuable associations, it would be useful to develop computational...

COVID-19 is threatening the health of the entire human population. In order to control the spread of the disease, epidemiological investigations should be conducted, to trace the infection source of each confirmed patient and isolate their close contacts. However, the analysis on a mass of case reports in epidemiological investigation is extremely...

Objective As Electronic Health Records (EHR) data accumulated explosively in recent years, the tremendous amount of patient clinical data provided opportunities to discover real world evidence. In this study, a graphical disease network, named progressive cardiovascular disease network (progCDN), was built to delineate the progression profiles of c...

With the successful adoption of machine learning on electronic health records (EHRs), numerous computational models have been deployed to address a variety of clinical problems. However, due to the heterogeneity of EHRs, models trained on different patient groups suffer from poor generalizability. How to mitigate domain shifts between the source pa...

Patient similarity plays an important role in precision evidence-based medicine. While great efforts have been made to derive clinically meaningful similarity measures, how to accurately and efficiently retrieve similar patients from large scale healthcare data remains less explored. Similar patient retrieval has become increasingly important and c...

Electronic Health Records (EHRs) have been widely used in healthcare studies recently, such as the analyses for patient diagnostic outcome and understanding of disease progression. EHR is a treasure for researchers who conduct the Real-World study to discovering Real-World Evidence (RWE). In this paper, we design an end-to-end learning system for d...

As Electronic Health Records (EHR) data accumulated explosively in recent years, the tremendous amount of patient clinical data provided opportunities to discover real world evidence. In this study, a graphical disease network, named progressive cardiovascular disease network (progCDN), was built based on EHR data from 14.3 million patients ¹ to de...

In real world applications like healthcare, it is usually difficult to build a machine learning prediction model that works universally well across different institutions. At the same time, the available model is often proprietary, i.e., neither the model parameter nor the data set used for model training is accessible. In consequence, leveraging t...

The use of social media runs through our lives, and users' emotions are also affected by it. Previous studies have reported social organizations and psychologists using social media to find depressed patients. However, due to the variety of content published by users, it isn't effortless for the system to consider the text, image, and even the hidd...

The use of social media runs through our lives, and users' emotions are also affected by it. Previous studies have reported social organizations and psychologists using social media to find depressed patients. However, due to the variety of content published by users, it isn't effortless for the system to consider the text, image, and even the hidd...

Background: Previous studies have suggested that Sodium Glucose Cotransporter-2(SGLT2) inhibitor may play cardio-protective role in type 2 diabetes mellitus (T2DM) patients. However, its effects on cardiovascular events for T2DM patients with atrial fibrillation (AF) have less been addressed. Therefore, we performed a large-scale multi-center retro...

Background: Studies have shown that acute coronary syndrome (ACS) has a higher incidence of MACE in diabetic patients than in nondiabetic patients by 39%. The complexity of the MACE limits clinical predictions, the success rate is shallow. Several existing MACE risk prediction models, including some developed specifically for ACS patients, also stu...

Background: Type 2 diabetes mellitus (T2DM) is a risk factor of Atrial Fibrillation (AF). However, few publications studied the, especially the profile changes due to aging. In this study, we created a statistical strategy to delineate the disease progression profile of the T2DM patients with AF across different age groups. Method: From IBM Explory...

Background: MiRNAs play an important role in complex human diseases, and the identification of disease and miRNA associations can accelerate drug development, individualized diagnosis, and treatment of diseases. From a miRNA perspective, the molecular mechanisms of many complex diseases, such as metabolic disease, are not fully understood. However,...

An important task in biomedical literature precise search is to identify paper describing a certain disease. The tradi- tional topic identification approaches based on neural network can be used to recognize the disease topic of literature. To achieve better performance, we propose a novel word graph-based method for disease topic identification in...

Background Approximately 42.5 million adults have been affected by mental illness in the United States in 2013, and 173 million people have been affected by a diagnosable psychiatric disorder in China. An increasing number of people tend to seek health information on the Web, and it is important to understand the factors associated with individuals...

Background: Since January 2020, COVID-19 swept over China and then the world, causing a global public health crisis. People's adoption of preventive and intervening behaviors is critical in curbing the spread of the virus. Objective: To evaluate Chinese people's adoption of health behaviors in responding to COVID-19 and to identify key determina...

BACKGROUND Since January 2020, the coronavirus disease (COVID-19) swept over China and then the world, causing a global public health crisis. People’s adoption of preventive and intervening behaviors is critical in curbing the spread of the virus. OBJECTIVE The aim of this study is to evaluate Chinese people’s adoption of health behaviors in respo...

The PICO framework (Population, Intervention, Comparison, and Outcome) is usually used to formulate evidence in the medical domain. The major task of PICO extraction is to extract sentences from medical literature and classify them into each class. However, in most circumstances, there will be more than one evidences in an extracted sentence even i...

Clinical trials are key and essential processes for researchers to develop new treatments as well as evaluate their effectiveness and safety, whilst more than half of all clinical trials experience delays, which leads to a considerable amount of cost. In this paper, we present a cost-effective framework to reduce the time and monetary cost in the s...

Secondary use of regional EHR data suffers several problems, including data selection bias and limited data size caused by data incompleteness. Here, we propose knowledge learning symbiosis (KLS) as a framework to incorporate domain knowledge to address the problems and make better secondary use of EHR data. Under the framework, we introduce three...

Cluster analysis aims at separating patients into phenotypically heterogenous groups and defining therapeutically homogeneous patient subclasses. It is an important approach in data-driven disease classification and subtyping. Acute coronary syndrome (ACS) is a syndrome due to sudden decrease of coronary artery blood flow, where disease classificat...

BACKGROUND Approximately 42.5 million adults have been affected by mental illness in the United States in 2013, and 173 million people have been affected by a diagnosable psychiatric disorder in China. An increasing number of people tend to seek health information on the Web, and it is important to understand the factors associated with individuals...

Cluster analysis aims at separating patients into phenotypically heterogenous groups and defining therapeutically homogeneous patient subclasses. It is an important approach in data-driven disease classification and subtyping. Acute coronary syndrome (ACS) is a syndrome due to sudden decrease of coronary artery blood flow, where disease classificat...

Risk assessment services fulfil the task of generating a risk report from personal information and are developed for purposes like disease prognosis, resource utilization prioritization, and informing clinical interventions. A major component of a risk assessment service is a risk prediction model. For a model to be easily integrated into risk asse...

Disease-symptom relation is an important biomedical relation that can be used for clinical decision support including building medical diagnostic systems. Here we present a study on mining disease-symptom relation from massive biomedical literature and constructing biomedical knowledge graph from the relation. From 15,970,134 MEDLINE/PubMed citatio...

In healthcare, applying deep learning models to electronic health records (EHRs) has drawn considerable attention. EHR data consist of a sequence of medical visits, i.e. a multivariate time series of diagnosis, medications, physical examinations, lab tests, etc. This sequential nature makes EHR well matching the power of Recurrent Neural Network (R...

Increasing learning ability from massive medical data and building learning methods robust to data quality issues are key factors toward building data-driven clinical decision support systems for medicine prescription decision support. Here, we attempted accordingly to address the factors using a multi-task neural network approach, benefiting from...

Precision medicine requires the precision disease risk prediction models. In literature, there have been a lot well-established (inter-)national risk models, but when applying them into the local population, the prediction performance becomes unsatisfactory. To address the localization issue, this paper exploits the way to develop knowledge-enhance...

With the better availability of healthcare data, such as Electronic Health Records (EHR), more and more data analytics methodologies are developed aiming at digging insights from them to improve the quality of care delivery. There are many challenges on analyzing EHR, such as high dimensionality and event sparsity. Moreover, different from other ap...

Clinical decision support systems are information technology systems that assist clinical decision-making tasks, which have been shown to enhance clinical performance. Cluster analysis, which groups similar patients together, aims to separate patient cases into phenotypically heterogenous groups and defining therapeutically homogeneous patient subc...

In clinical practice, many patients may have unknown or missing values for some predictors, causing that the developed risk models cannot be directly applied on these patients. In this paper, we propose an incremental learning approach to apply a developed risk model on new patients with unknown predictor values, which imputes a patient's unknown v...

In healthcare, applying deep learning models to electronic health records (EHRs) has drawn considerable attention. This sequential nature of EHR data make them wellmatched for the power of Recurrent Neural Network (RNN). In this poster, we propose "Deep Diabetologist" - using RNNs for EHR sequential data modeling to provide personalized hypoglycemi...

Along with the growth of numbers of patients with chronic diseases, personal health self-management becomes critical. The heterogeneity of self-management requirements makes the detail design and implementation of self-management program a non-trivial work. In this paper we address the problem with the Personal Health Advisor (PHA) application by i...

Hybrid process models are considered an attractive approach for modeling knowledge-intensive processes. A hybrid process model combines both imperative and declarative modeling, which can handle both the structured and the flexible parts of a business process. However, it is difficult and timeconsuming to create and refine a hybrid process model du...

A care/clinical pathway defines a standardized care process for a specific patient group, which consists of clinical goals, activities, data attributes, and constraints describing temporal dependencies and data preconditions of the activities. The constraints, which are the key elements to represent the best practices, are difficult to define due t...

Treatment recommendation is a nontrivial task - it requires not only domain knowledge from evidence-based medicine, but also data insights from descriptive, predictive and prescriptive analysis. A single treatment recommendation system is usually trained or modeled with a limited (size or quality) source. This paper proposes a decision fusion frame...

A care/clinical pathway (CP) is a standardized care process where temporal and data constraints of clinical activities are defined to ensure quality of care. In actual care practice, various situations of compliance and non-compliance with CPs can be observed. Analysis of these CP variation patterns (CPVPs) can help improve care quality and enhance...

Care pathways play significant roles in delivering evidence-based and coordinated care to patients with specific conditions. In order to put care pathways into practice, clinical institutions always need to adapt them based on local care settings so that the best local practices can be incorporated and used to develop refined pathways. However, it...

Treatment recommendation systems aim to providing clinical decision supports, e.g. with integration of Computerized Physician Order Entry (CPOE). One of the most significant issue is the quality of recommendations which needs to be quantified, before getting the acceptance from physicians. In computer science, such evaluations are typically perform...

A computer-implemented method, computer-implemented system, and a computer program product for answering a database-based query of a computerized database system. The method includes: generating a canonical individual ind' with respect to a role and a concept, for an existential restriction in an ontology used in the computerized database system; c...

Care pathways (CPs) as a means of healthcare quality control are getting increasing attention due to widespread recognition in the healthcare industry of the need for well coordinated, evidence based and personalized care. To keep the promise, CPs require continuous refinement in order to stay up to date with regard to both clinical guidelines and...

A care pathway (CP) is a standardized process that consists of multiple care stages, clinical activities and their relations, aimed at ensuring and enhancing the quality of care. However, actual care may deviate from the planned CP, and analysis of these deviations can help clinicians refine the CP and reduce medical errors. In this paper, we propo...

The computerization of care pathways (CPs) has drawn considerable attention, for improving quality of health care and reducing costs. A well-known big challenge of implementing CPs is their flexibility and ad hoc variations in execution of clinical tasks. We observe that case management suits well to address this problem, and this paper proposes a...

With the rapid development of Semantic Web, more and more RDF repositories, such as Linking Open Data (LOD), are available on the web. Generally, there are two services provided for exploring those RDF repositories, one is the keyword lookup, and the other is the SPARQL endpoint. Most users choose the lookup service, and millions of web logs have b...

A method and a system for evaluating data. The method comprises: receiving an Object Constraint Language (OCL) expression-based evaluation request; transforming at least part of the OCL expressions in the evaluation request into query requests; querying relevant data based on the query requests; and evaluating data obtained from the querying based...

This work proposes to leverage an advanced modeling technique, namely Markov Decision Process, to evaluate sequential clinical interventions in disease management. We have demonstrated our evaluation framework on a diabetes case study over two real data sets, and discovered valuable clinical insights towards better interventions during disease prog...

We demonstrate how data mining techniques can help recommend effective medications when physicians need to control the glucose level of patients with type 2 diabetes. We first identify the factors that may affect physicians' medication decisions and then develop a patient-similarity based approach to automatically recommend medications for a patien...

Although, clinical guidelines are regarded as best practices for clinicians, clinician activities are not always compliant with guideline recommendations. This paper aims to improve clinician compliance with guidelines. We have developed an engine to automatically report three non-compliance situations: 1) guideline recommendations exist, and the c...

Few clinical guideline-based decision support systems (DSS) have been successfully applied in chronic disease management. This paper investigates how clinical guideline-based DSS can help to put innovative chronic care models into practice and improve the quality of chronic care. A prototype of a guideline-based collaborative chronic care system ca...

GELLO, an expression language for clinical decision support, has been approved as an HL7/ANSI normative standard for years. Unfortunately, there are few GELLO engines available in use, and the limited tooling seems to hamper a widespread adoption of GELLO. The objective of this paper is to validate the availability of implementing an OCL-compliant...

In this paper, we present the design and implementation of a regional health information system that reconciles patient clinical data from heterogeneous Point of Services(POS) applications and supports complicated clinical queries. We propose to design a simple XML format for the representation of clinical documents and a messaging-based protocol f...

Since Representational State Transfer (REST) architecture was proposed by Fielding in early 1990s for distributed hypermedia systems, it has become a popular architectural style of choice in various computing environments. However, REST was not originally designed to support enterprise requirements, in particular the accountability requirements tha...

The Health Level 7 Clinical Document Architecture (CDA) is widely accepted as the format for electronic clinical document. With the rich ontological references in CDA documents, the ontology-based semantic query could be performed to retrieve CDA documents. In this paper, we present iSMART (interactive Semantic MedicAl Record reTrieval), a prototyp...

Conjunctive query answering for EL++\mathcal{EL}^{++} ontologies has recently drawn much attention, as the Description Logic EL++\mathcal{EL}^{++} captures the expressivity of many large ontologies in the biomedical domain and is the foundation for the OWL 2 EL profile. In this paper, we propose a practical approach for conjunctive query answering...

Nowadays, more and more URIs reside on Data Web, as pub- lished for linked open data, dereferencing URIs challenges the current Web to embrace Semantic Web. Although, quite a few practical recipes for publishing URIs have been pro- vided to make URIs dereferencable, we believe a fundamen- tal investigation of publishing and dereferencing URIs would...

Object Oriented (OO) programming is dominant in the current software development. Starting from the design of OO models for applications, developers also expect to address issues on the data of models and the semantics of models. Objects, being the data of models, could be stored in relational databases, and ontologies appear as a good candidate fo...

Metadata that describes the structure and semantics of data sources takes a significant role in enterprise information integration. Enterprise information integration always involves an increasing set of types of metadata that are dispersed in various repositories, modeled by various tools, represented in various formats. There is a crucial require...

Reasoning with large amounts of data together with ontological knowledge is becoming a pertinent issue. In this chapter, we will give an overviewof well-known ontology repositories, including native stores and database based stores, and highlight strengths and limitations of each store. We take Minerva as an example to analyze ontology storage in d...

Uniting ontologies and rules has become a central topic in the Semantic Web. Bridging the discrepancy between these two knowledge representations, this paper introduces DatalogDL as a family of hybrid languages, where Datalog rules are parameterized by various DL (description logic) languages ranging from to . Making DatalogDL a decidable system wi...

A unifying logic is built on top of ontologies and rules for the revised Semantic Web Architecture. This paper proposesALCu P, which integrates a description logic (DL) that makes a unique names assump- tion with general rules that have the form of Datalog Programs per- mitting default negation in the body. An ALCu P knowledge base (KB) consists of...

With the fast development of Semantic Web, more and more RDF and OWL ontologies are created and shared. The eective man- agement, such as storage, inference and query, of these ontologies on databases gains increasing attention. This paper addresses ontology query answering on databases by means of Datalog programs. Via epistemic operators, integri...

An unresolved issue in SWRL (the Semantic Web Rule Language) is whether the intended semantics of its RDF representation can be described as an extension of the W3C RDF semantics. In this paper we propose to make the model-theoretic semantics of SWRL compatible with RDF by interpreting SWRL rules in RDF graphs. For dealing with SWRL/RDF rules, we r...

Combining ontologies with rules has become a central topic in the Semantic Web. Bridging the discrepancy between these two knowledge representations, this paper introduces DatalogDL as a family of hybrid languages, where Datalog rules are parameterized by various DL (description logic) languages ranging from ALC to SHI Q. Making DatalogDL a decidab...

Web-based collaboration (eCollaboration) is becoming increasingly popular. The crucial first step of a consulting collaboration is expert finding. This paper describes the Find-XpRT project for finding experts via rules and taxonomies. We implemented rules for a client finding an expert to collaborate with, for an experts decision making on whether...

This paper presents the open source reference implementation of RuleML based on modular XML Schema definitions and bidirectional OO jDREW interpreters written in Java. For the family of RuleML sublanguages, schema modularization and RDF rules are discussed. The central bidirectional interpreters are introduced via jDREW principles, and explained w....

The wide scale usage of OWL for the formalization of real-world ontologies is currently influenced by important limitations which concern both its expressivity and the efficiency of OWL specific reasoning tools. While the expressivity limitations may be overcame by extending the OWL language (e.g. with rules), the reasoning with such heterogeneous...

Abstract The Prot´eg´e OWL Plugin provides a SWRL editor, which enables the formalization of SWRL rules in conjunction with OWL ontologies. In this paper we aim at extending the usability of this tool and examining two approaches for SWRL reasoning support: one is SWRL in Jess, and the other is SWRL in Sesame. In the first one, we make use of a Jes...

In Semantic Web, using rules to add more expressive power has drawn considerable attention. Recently ORL (OWL Rules Language) has been presented where OWL is extended with Horn clause rules. In this paper we propose an extension to OWL with more general rules involving not only atoms but also literals with classical negation and negation as failure...

The problem that "XML formally governs syntax only - not semantics" has been a serious barrier for XML-based data integration and the extension of current Web to Semantic Web. To address this prob- lem, we propose the XML Semantics Definition Language(XSDL) to ex- press XML author's intended meaning and propose a model-theoretic se- mantics for XML...

Representing knowledge in OWL provides two important limitations;

1. ABSTRACT We present iSMART, a system for intelligent S emantic M edicAl Record reT rival. Health Level 7 Clinical Docu-ment Architecture (CDA) [4], a standard based on XML, is well recognized for the representation and exchange of medi-cal records. In CDAs, medical ontologies/terminologies, e.g. SNOMED CT [2], are used to specify the semantic me...

The ORDBase architecture is introduced as a common plat-form for Web ontologies, rules, and data. The ontology base (here using OWL) is well-suited to represent structured knowledge. The rule base (here using RuleML) is the key to inferencing, whose predefined rules serve for translating the OWL semantics, also user-defined rules are con-sidered. T...