Search

Drug safety is a severe clinical pharmacology and toxicology problem that has caused immense medical and social burdens every year. Regretfully, a reproducible method to assess drug safety systematically and quantitatively is still missing. In this study, we developed an advanced machine learning model for de novo drug safety assessment by solving the multilayer drug‐gene‐adverse drug reaction (ADR) interaction network. For the first time, the drug safety was assessed in a broad landscape of 1,156 distinct ADRs. We also designed a parameter ToxicityScore to quantify the overall drug safety. Moreover, we determined association strength for every 3,807,631 gene‐ADR interactions, which clues mechanistic exploration of ADRs. For convenience, we deployed the model as a web service ADRAlert‐gene at http://www.bio-add.org/ADRAlert/. In summary, this study offers insights into prioritizing safe drug therapy. It helps reduce the attrition rate of new drug discovery by providing a reliable ADR profile in the early preclinical stage.

Objective Epilepsy is among the most common chronic neurologic diseases. There is a need for more data on patient perspectives of treatment to guide patient-centered care initiatives. Patients with epilepsy share their experiences on social media anonymously, but little is known about those discussions. Our aim was to learn what patients with epilepsy discuss regarding their condition and identify treatment-related themes from online patient support groups. Methods A total of 355,838 posts were collected from three online support groups for patients with epilepsy through a crawling script, and an analytical pipeline was built to identify patient conversation content through leveraging of multiple text mining methods. Results were also displayed by network visualization methods. Results Patients with epilepsy sought information about medical treatments, shared their treatment experiences, and sought help from other posters. Key themes related to treatments included the search for optimal personalized treatment strategies as well as identifying and coping with adverse effects. Significance This study showed the feasibility of learning about concerns of patients with epilepsy, especially treatment issues, through text mining methods. However, some manual selection and filtering were necessary to ensure quality results for the treatment analysis. Providers should be aware of online discussions and use analyses of such discussions to help guide effective patient engagement during care.

The coronavirus disease 2019 (COVID-19) pandemic has significantly affected utilization of preventative health care, including vaccines. We aimed to assess HPV vaccination rates during the pandemic, and conduct a simulation model-based analysis to estimate the impact of current coverage and future pandemic recovery scenarios on disease outcomes. The model population included females and males of all ages in the US. The model compares pre-COVID vaccine uptake to 3 reduced coverage scenarios with varying recovery speed. Vaccine coverage was obtained from Truven Marketscan™. Substantially reduced coverage between March- August 2020 was observed compared to 2018-2019. The model predicted that 130,853 to 213,926 additional cases of genital warts; 22,503 to 48,157 cases of CIN1; 48,682 to 110,192 cases of CIN2/3; and 2,882 to 6,487 cases of cervical cancer will occur over the next 100 years, compared to status quo. Providers should plan efforts to recover HPV vaccination and minimize potential long-term consequences.

Data on disease burden are often used for assessing population health, evaluating the effectiveness of interventions, formulating health policies, and planning future resource allocation. We investigated whether Internet usage and social media data, specifically the search volume on Google, page view count on Wikipedia, and disease mentioning frequency on Twitter, correlated with the disease burden, measured by prevalence and treatment cost, for 1633 diseases over an 11-year period. We also applied least absolute shrinkage and selection operator to predict the burden of diseases. We found that Google search volume is relatively strongly correlated with the burdens for 39 of 1633 diseases, including viral hepatitis, diabetes mellitus, multiple sclerosis, and hemorrhoids. Wikipedia and Twitter data strongly correlated with the burdens of 15 and 7 diseases, respectively. However, an accurate analysis must consider each condition’s characteristics, including acute/chronic nature, severity, familiarity to the public, and the presence of stigma.

Data mapping plays an important role in data integration and exchanges among institutions and organizations with different data standards. However, traditional rule-based approaches and machine learning methods fail to achieve satisfactory results for the data mapping problem. In this paper, we propose a novel and sophisticated deep learning framework for data mapping called mixture feature embedding convolutional neural network (MfeCNN). The MfeCNN model converts the data mapping task to a multiple classification problem. In the model, we incorporated multimodal learning and multiview embedding into a CNN for mixture feature tensor generation and classification prediction. Multimodal features were extracted from various linguistic spaces with a medical natural language processing package. Then, powerful feature embeddings were learned by using the CNN. As many as 10 classes could be simultaneously classified by a softmax prediction layer based on multiview embedding. MfeCNN achieved the best results on unbalanced data (average F1 score, 82.4%) among the traditional state-of-the-art machine learning models and CNN without mixture feature embedding. Our model also outperformed a very deep CNN with 29 layers, which took free texts as inputs. The combination of mixture feature embedding and a deep neural network can achieve high accuracy for data mapping and multiple classification.

Objective: The present study was to compare the incidence of septal defect (SD) in patients with atrial fibrillation (AF) who received radiofrequency ablation or cryoablation. Methods: A total of 293 AF patients were performed with radiofrequency ablation and cryoablation. Cardiac ultrasonography was performed to calculate left atrial diameter (LAD), left atrial ejection fraction (LAEF%), strain rate (SR), left ventricular systolic (SRs), left ventricular diastolic (SRe), and left atrial systole (SRa) before surgery, 3 months and 1 year after surgery. The patients were followed up to observe statin and angiotensin-converting enzyme inhibitor (ACEI)/angiotensin receptor blocker (ARB) medication, AF recurrence, 6-min walk test, stroke, any symptoms caused by arrhythmia, and re-hospitalization. Results: The levels of LAD and SD were higher, while SRe and SRa were lower in the cryoablation group in the comparison with the radiofrequency ablation group after surgery (P

Introduction: News media play an important role in raising public awareness, framing public opinions, affecting policy formulation, and acknowledgment of public health issues. Traditional qualitative content analysis for news sentiments and focuses are time-consuming and may not efficiently convey sentiments nor the focuses of news media. Methods: We used descriptive statistics and state-of-art text mining to conduct sentiment analysis and topic modeling, to efficiently analyze over 3 million Reuters news articles during 2007–2017 for identifying their coverage, sentiments, and focuses for public health issues. Based on the top keywords from public health scientific journals, we identified 10 major public health issues (i.e., “air pollution,” “alcohol drinking,” “asthma,” “depression,” “diet,” “exercise,” “obesity,” “pregnancy,” “sexual behavior,” and “smoking”). Results: The news coverage for seven public health issues, “Smoking,” “Exercise,” “Alcohol drinking,” “Diet,” “Obesity,” “Depression,” and “Asthma” decreased over time. The news coverage for “Sexual behavior,” “Pregnancy,” and “Air pollution” fluctuated during 2007–2017. The sentiments of the news articles for three of the public health issues, “exercise,” “alcohol drinking,” and “diet” were predominately positive and associated such as “energy.” Sentiments for the remaining seven public health issues were mainly negative, linked to negative terms, e.g., diseases. The results of topic modeling reflected the media’s focus on public health issues. Conclusions: Text mining methods may address the limitations of traditional qualitative approaches. Using big data to understand public health needs is a novel approach that could help clinical and translational science awards programs focus on community-engaged research efforts to address community priorities.

Atrial fibrillation (AF) is a commonly encountered heart arrhythmia and a risk factor for cardiovascular system. The purpose of the present study was to explore the role of long non-coding RNA myocardial infarction-associated transcript (MIAT) in AF and AF-induced myocardial fibrosis and the possible mechanisms involved in this process. We successfully induced an AF rat model. Expression of MIAT presented a dramatic increase, while microRNA (miR)-133a-3p presented a dramatic decrease in atrium tissues of rats with AF induction. In addition, we also found that MIAT was highly expressed and miR-133a-3p was significantly reduced in peripheral blood leukocyte of AF patients. For biological function exploration of MIAT/miR-133a-3p axis, MIAT was knocked down using small hairpin RNA (shRNA) lentivirus injection and the rescue experiments were performed simultaneously by inhibiting miR-133a-3p using anti-miR-133a-3p lentivirus injection in rats with AF. MIAT downregulation significantly alleviated AF, increased atrial effective refractory period (AERP), and reduced the duration of AF as well as cardiomyocytes apoptosis. Whereas these effects of MIAT downregulation on AF were reversed by anti-miR-133a-3p administration. Luciferase reporter revealed that miR-133a-3p was directly regulated by MIAT. Moreover, MIAT knockdown effectively reduced AF-induced atrial fibrosis by detecting reduced collagen in the right atria and inhibited expression of fibrosis-related gene expression of collagen I, collagen III, connective tissue growth factor (CTGF) and transforming growth factor-β1 (TGF-β1) in rats with AF, these findings were in contrast with the findings for rats with inhibition of miR-133a-3p. In conclusion, our study demonstrated the role of MIAT downregulation in alleviating AF and AF-induced myocardial fibrosis, and the functional regulatory pathway of MIAT targeting miR-133a-3p.

Background Accurate information in provider directories are vital in health care including health information exchange, health benefits exchange, quality reporting, and in the reimbursement and delivery of care. Maintaining provider directory data and keeping it up to date is challenging. The objective of this study is to determine the feasibility of using natural language processing (NLP) techniques to combine disparate resources and acquire accurate information on health providers. Methods Publically available state licensure lists in Connecticut were obtained along with National Plan and Provider Enumeration System (NPPES) public use files. Connecticut licensure lists textual information of each health professional who is licensed to practice within the state. A NLP-based system was developed based on healthcare provider taxonomy code, location, name and address information to identify textual data within the state and federal records. Qualitative and quantitative evaluation were performed, and the recall and precision were calculated. Results We identified nurse midwives, nurse practitioners, and dentists in the State of Connecticut. The recall and precision were 0.95 and 0.93 respectively. Using the system, we were able to accurately acquire 6849 of the 7177 records of health provider directory information. Conclusions The authors demonstrated that the NLP- based approach was effective at acquiring health provider information. Furthermore, the NLP-based system can always be applied to update information further reducing processing burdens as data changes.

Background Patient portals tethered to electronic health records systems have become attractive web platforms since the enacting of the Medicare Access and Children’s Health Insurance Program Reauthorization Act and the introduction of the Meaningful Use program in the United States. Patients can conveniently access their health records and seek consultation from providers through secure web portals. With increasing adoption and patient engagement, the volume of patient secure messages has risen substantially, which opens up new research and development opportunities for patient-centered care. Objective This study aims to develop a data model for patient secure messages based on the Fast Healthcare Interoperability Resources (FHIR) standard to identify and extract significant information. Methods We initiated the first draft of the data model by analyzing FHIR and manually reviewing 100 sentences randomly sampled from more than 2 million patient-generated secure messages obtained from the online patient portal at the Mayo Clinic Rochester between February 18, 2010, and December 31, 2017. We then annotated additional sets of 100 randomly selected sentences using the Multi-purpose Annotation Environment tool and updated the data model and annotation guideline iteratively until the interannotator agreement was satisfactory. We then created a larger corpus by annotating 1200 randomly selected sentences and calculated the frequency of the identified medical concepts in these sentences. Finally, we performed topic modeling analysis to learn the hidden topics of patient secure messages related to 3 highly mentioned microconcepts, namely, fatigue, prednisone, and patient visit, and to evaluate the proposed data model independently. Results The proposed data model has a 3-level hierarchical structure of health system concepts, including 3 macroconcepts, 28 mesoconcepts, and 85 microconcepts. Foundation and base macroconcepts comprise 33.99% (841/2474), clinical macroconcepts comprise 64.38% (1593/2474), and financial macroconcepts comprise 1.61% (40/2474) of the annotated corpus. The top 3 mesoconcepts among the 28 mesoconcepts are condition (505/2474, 20.41%), medication (424/2474, 17.13%), and practitioner (243/2474, 9.82%). Topic modeling identified hidden topics of patient secure messages related to fatigue, prednisone, and patient visit. A total of 89.2% (107/120) of the top-ranked topic keywords are actually the health concepts of the data model. Conclusions Our data model and annotated corpus enable us to identify and understand important medical concepts in patient secure messages and prepare us for further natural language processing analysis of such free texts. The data model could be potentially used to automatically identify other types of patient narratives, such as those in various social media and patient forums. In the future, we plan to develop a machine learning and natural language processing solution to enable automatic triaging solutions to reduce the workload of clinicians and perform more granular content analysis to understand patients’ needs and improve patient-centered care.

Background Patient narrative data in online health care forums (communities) are receiving increasing attention from the scientific community for implementing patient-centered care. Natural language processing (NLP) methods are gaining more and more attention because of the enormous data volume. However, state-of-the-art NLP still cannot meet the need of high-resolution analysis of patients’ narratives. Manual qualitative analysis still plays a pivotal role in answering complicated research questions from analyzing patient narratives. Objective This study aimed to develop a systematic framework for qualitative analysis of patient-generated narratives in online health care forums. Methods Our systematic framework consists of 4 phases: (1) data collection, (2) data preparation, (3) content analysis, and (4) interpretation of the results. Data collection and data preparation phases are constructed based on text mining methods for identifying appropriate online health forums for data collection, differentiating posts of patients from other stakeholders, protecting patients’ privacy, sampling, and choosing the unit of analysis. Content analysis phase is built on the framework method, which facilitates and accelerates the identification of patterns and themes by an interdisciplinary research team. In the end, the focus of interpretation of the results phase is to measure the data quality and interpret the findings regarding the dimensions and aspects of patients’ experiences and concerns in their original contexts. Results We demonstrated the usability of the proposed systematic framework using 2 case studies: one on determining factors affecting patients’ attitudes toward antidepressants and another on identifying the disease management strategies in patient with diabetes facing financial difficulties. The framework provides a clear step-by-step process for systematic content analysis of patient narratives and produces high-quality structured results that can be used for describing patterns or regularities in patients’ experiences, generating and testing hypotheses, and identifying areas of improvement in the health care systems. Conclusions The systematic framework is a rigorous and standardized method for qualitative analysis of patient narratives. Findings obtained through such a process indicate authentic dimensions and aspects of patient experiences and shed light on patients’ concerns, needs, preferences, and values, which are the core of patient-centered care. International Registered Report Identifier (IRRID) RR1-10.2196/13914

Binge drinking is a severe health problem faced by many US colleges and universities. College students often post drinking-related text and images on social media, portraying their alcohol use as socially desirable. In this project, we investigated the feasibility of mining the heterogeneous data (e.g. text, images, and videos) on Facebook to identify drinking-related contents. We manually annotated 4266 posts during 21 October 2011 and 3 November 2014 from “I’m Shmacked” group on Facebook, where 511 posts were drinking-related. Our machine learning models show that by combining heterogeneous data types, we were able to identify drinking-related posts with an F1-score of 0.81. Prediction models built on text data were more reliable compared to those built on image and video data for predicting drinking-related contents. As the first step of our efforts in this direction, this feasibility study showed promise toward unleashing the potential of mining social media to identify students who binge drink.

Background: The human Monoamine Transporters (hMATs), primarily including hSERT, hNET and hDAT, are important targets for the treatment of depression and other behavioral disorders with more than the availability of 30 approved drugs. Objective: This paper is to review the recent progress in the binding mode and inhibitory mechanism of hMATs inhibitors with the central or allosteric binding sites, for the benefit of future hMATs inhibitor design and discovery. The Structure-Activity Relationship (SAR) and the selectivity for hit/lead compounds to hMATs that are evaluated by in vitro and in vivo experiments will be highlighted. Methods: PubMed and Web of Science databases were searched for protein-ligand interaction, novel inhibitors design and synthesis studies related to hMATs. Results: Literature data indicate that since the first crystal structure determinations of the homologous bacterial Leucine Transporter (LeuT) complexed with clomipramine, a sizable database of over 100 experimental structures or computational models has been accumulated that now defines a substantial degree of structural variability hMATs-ligands recognition. In the meanwhile, a number of novel hMATs inhibitors have been discovered by medicinal chemistry with significant help from computational models. Conclusion: The reported new compounds act on hMATs as well as the structures of the transporters complexed with diverse ligands by either experiment or computational modeling have shed light on the poly-pharmacology, multimodal and allosteric regulation of the drugs to transporters. All of the studies will greatly promote the Structure-Based Drug Design (SBDD) of structurally novel scaffolds with high activity and selectivity for hMATs.

Multiple data sources are preferred in adverse drug event (ADEs) surveillance owing to inadequacies of single source. However, analytic methods to monitor potential ADEs after prolonged drug exposure are still lacking. In this study we propose a method aiming to screen potential ADEs by combining FDA Adverse Event Reporting System (FAERS) and Electronic Medical Record (EMR). The proposed method uses natural language processing (NLP) techniques to extract treatment outcome information captured in unstructured text and adopts case-crossover design in EMR. Performances were evaluated using two ADE knowledge bases: Adverse Drug Reaction Classification System (ADReCS) and SIDER. We tested our method in ADE signal detection of conventional disease-modifying antirheumatic drugs (DMARDs) in rheumatoid arthritis patients. Findings showed that recall greatly increased when combining FAERS with EMR compared with FAERS alone and EMR alone, especially for flexible mapping strategy. Precision (FAERS + EMR) in detecting ADEs improved using ADReCS as gold standard compared with SIDER. In addition, signals detected from EMR have considerably overlapped with signals detected from FAERS or ADE knowledge bases, implying the importance of EMR for pharmacovigilance. ADE signals detected from EMR and/or FAERS but not in existing knowledge bases provide hypothesis for future study.

Introduction Accurate information in provider directories are vital in health care including health information exchange, health benefits exchange, quality reporting, and in the reimbursement and delivery of care. Maintaining provider directory data and keeping it up to date is challenging. The objective of this study is to determine the feasibility of using NLP techniques to combine disparate resources and acquire accurate information on health providers. Methods Publically available state licensure lists in Connecticut were obtained along with National Plan and Provider Enumeration System (NPPES) public use files. Connecticut licensure lists textual information of each health professional who is licensed to practice within the state. A NLP-based system was developed based on Healthcare Provider Taxonomy code, location, and name and address information to identify textual data within the state and federal records. Qualitative and quantitative evaluation were performed, and the recall and precision were calculated. Results We identified nurse midwives, nurse practitioners, and dentists in the State of Connecticut. The recall and precision were 0.95 and 0.93 respectively. Using the system, we were able to accurately acquire 6,849 of the 7,177 records of health provider directory information. Conclusion The authors demonstrated that the NLP based approach was effective at acquiring health provider information. Furthermore, the NLP-based system can be re-applied on the updated information further reducing processing burdens as data changes.

The object of the study was to develop a quick and reproducible accelerated in vitro release method to predict and deduce the function of the real time (37 °C) release for long acting PLGA microspheres. The method could be described in several steps. First, the release of the microspheres were studied using the sample and separate method at 37 °C with normal orbital shaking and elevated temperatures with magnetic stirring to further accelerate the release. Second, the most similar profile at elevated temperatures with the real time release was chosen with the help of the n value in the fitted Korsmeyer-Peppas Function. Third, the Weibull function and conversion ratio were used to deduce the function of real time release according to the chosen profile at elevated temperatures. The key point in this study was to provide a quick and precise method to predict the real time release for long acting progesterone PLGA microspheres. So the elevated temperatures coupled with magnetic stirring were used to accelerate the release further, and when there have many similar release profiles with the real time release at elevated temperatures, releasing time at elevated temperatures and the R2 of the final deduced function will be used to help choosing the most similar release profile with the real time release. Four different types of progesterone PLGA microspheres were used to verify the method, and all the deduced function correlated well with the real time releases, for R2 = 0.9912, 0.9781, 0.9918 and 0.9972, respectively., Graphical abstract Different types of PLGA were used to make the microspheres with different drug loading rates and particle size distributions. The release profiles at elevated temperatures coupled with magnetic stirring were used to deduce the function of the release at 37 °C with the use of Korsmeyer-Peppas Equation and Weibull Function. Even with different types of microspheres, the deduced functions fitted well with the profiles at 37 °C for R2 = 0.9912, 0.9781, 0.9918 and 0.9972 (from A to D in the figures). Image, graphical abstract

The HL7 Fast Healthcare Interoperability Resources (FHIR) specification is emerging as a next generation standards framework for the exchange of electronic health records (EHR) data. The rich semantic representation and sophisticated structure definition of the FHIR requires a relatively deep learning curve to understand and utilize. The objective of our study is to design and develop a user-friendly interface for navigating and manipulating the FHIR specification. We prototyped a visualization platform for interactively exploring FHIR core resources and profiles. We evaluated the utility of the FHIR visualization platform using the evaluation metrics mainly focusing on its usability, interactive mechanisms and content expressiveness. We demonstrated that the visualization techniques are helpful for navigating the HL7 FHIR specification and aiding its profiling.

Delivering safe and effective therapeutic treatment to patients is one of the grand challenges in modern medicine. However, drug safety research has been progressing slowly in recent years, compared to other fields such as biotechnologies and precision medicine, due to the mechanistic complexity of adverse drug reactions (ADRs). To fill up this gap, we develop a new database, the Adverse Drug Reaction Classification System-Target Profile (ADReCS-Target, http://bioinf.xmu.edu.cn/ADReCS-Target), which provides comprehensive information about ADRs caused by drug interaction with protein, gene and genetic variation. In total, ADReCS-Target includes 66,573 pairwise relations, among which 1710 are protein–ADR associations, 2613 are genetic variation–ADR associations, and 63,298 are gene–ADR associations. In a case study of exploring the mechanism of rash, we find that HLAs, C1QA and APOA1 are the key gene players and thus can be potential targets (or biomarkers) in monitoring or countermining rashes. In summary, ADReCS-Target can be a useful resource for the biomedical scientific community by serving researchers in the fields of drug development, clinical pharmacology, precision medicine, and from web lab to high-throughput computational platform. Particularly, it helps to identify drug with better ADR profile and design safer drug therapy regimen.

Background To deliver evidence-based medicine, clinicians often reference resources that are useful to their respective medical practices. Owing to their busy schedules, however, clinicians typically find it challenging to locate these relevant resources out of the rapidly growing number of journals and articles currently being published. The literature-recommender system may provide a possible solution to this issue if the individual needs of clinicians can be identified and applied. Methods We thus collected from the CiteULike website a sample of 96 clinicians and 6,221 scientific articles that they read. We examined the journal distributions, publication types, reading times, and geographic locations. We then compared the distributions of MeSH terms associated with these articles with those of randomly sampled MEDLINE articles using two-sample Z-test and multiple comparison correction, in order to identify the important topics relevant to clinicians. Results We determined that the sampled clinicians followed the latest literature in a timely manner and read papers that are considered landmarks in medical research history. They preferred to read scientific discoveries from human experiments instead of molecular-, cellular- or animal-model-based experiments. Furthermore, the country of publication may impact reading preferences, particularly for clinicians from Egypt, India, Norway, Senegal, and South Africa. Conclusion These findings provide useful guidance for developing personalized literature-recommender systems for clinicians. Electronic supplementary material The online version of this article (doi:10.1186/s12911-017-0463-z) contains supplementary material, which is available to authorized users.

One common health problem in the US faced by colleges and universities is binge drinking. College students often post drinking related texts and images on social media as a socially desirable identity. Some public health and clinical research scholars have surveyed different social media sites manually to understand their behavior patterns. In this paper, we investigate the feasibility of mining the heterogeneous data scattered on social media to identify drinking-related contents, which is the first step towards unleashing the potential of social media in automatic detection of binge drinking users. We use the state-of-the-art algorithms such as Support Vector Machine and neural networks to classify drinking from non-drinking posts, which contain not only text, but also images and videos. Our results show that combining heterogeneous data types, we are able to identify drinking related posts with an overall accuracy of 82%. Prediction models based on text data is more reliable compared to the other two models built on image and video data for predicting drinking related contents.

Human organ, as the basic structural and functional unit in human body, is made of a large community of different cell types that organically bound together. Each organ usually exerts highly specified physiological function; while several related organs work smartly together to perform complicated body functions. In this study, we present a computational effort to understand the roles of genes in building functional connection between organs. More specifically, we mined multiple transcriptome datasets sampled from 36 human organs and tissues, and quantitatively identified 3,149 genes whose expressions showed consensus modularly patterns: specific to one organ/tissue, selectively expressed in several functionally related tissues and ubiquitously expressed. These pattern genes imply intrinsic connections between organs. According to the expression abundance of the 766 selective genes, we consistently cluster the 36 human organs/tissues into seven functional groups: adipose & gland, brain, muscle, immune, metabolism, mucoid and nerve conduction. The organs and tissues in each group either work together to form organ systems or coordinate to perform particular body functions. The particular roles of specific genes and selective genes suggest that they could not only be used to mechanistically explore organ functions, but also be designed for selective biomarkers and therapeutic targets.