Using natural language processing to characterize and predict homeopathic product-associated adverse events in consumer reviews: comparison to reports to FDA Adverse Event Reporting System (FAERS).

OBJECTIVE: Apply natural language processing (NLP) to Amazon consumer reviews to identify adverse events (AEs) associated with unapproved over the counter (OTC) homeopathic drugs and compare findings with reports to the US Food and Drug Administration Adverse Event Reporting System (FAERS). MATERIALS AND METHODS: Data were extracted from publicly available Amazon reviews and analyzed using JMP 16 Pro Text Explorer. Topic modeling identified themes. Sentiment analysis (SA) explored consumer perceptions. A machine learning model optimized prediction of AEs in reviews. Reports for the same time interval and product class were obtained from the FAERS public dashboard and analyzed. RESULTS: Homeopathic cough/cold products were the largest category common to both data sources (Amazon = 616, FAERS = 445) and were analyzed further. Oral symptoms and unpleasant taste were described in both datasets. Amazon reviews describing an AE had lower Amazon ratings (X2 = 224.28, P < .0001). The optimal model for predicting AEs was Neural Boosted 5-fold combining topic modeling and Amazon ratings as predictors (mean AUC = 0.927). DISCUSSION: Topic modeling and SA of Amazon reviews provided information about consumers' perceptions and opinions of homeopathic OTC cough and cold products. Amazon ratings appear to be a good indicator of the presence or absence of AEs, and identified events were similar to FAERS. CONCLUSION: Amazon reviews may complement traditional data sources to identify AEs associated with unapproved OTC homeopathic products. This study is the first to use NLP in this context and lays the groundwork for future larger scale efforts.

Mapping 2 Decades of Research in Health Services Research, Health Policy, and Health Economics Journals.

OBJECTIVE: To identify major research topics and exhibit trends in these topics in 15 health services research, health policy, and health economics journals over 2 decades. DATA SOURCES: The study sample of 35,159 abstracts (1999-2020) were collected from PubMed for 15 journals. STUDY DESIGN: The study used a 3-phase approach for text analyses: (1) developing the corpus of 40,618 references from PubMed (excluding 5459 of those without abstract or author information); (2) preprocessing and generating the term list using natural language processing to eliminate irrelevant textual data and identify important terms and phrases; (3) analyzing the preprocessed text data using latent semantic analysis, topic analyses, and multiple correspondence analysis. PRINCIPAL FINDINGS: Application of analyses generated 16 major research topics: (1) implementation/intervention science; (2) HIV and women's health; (3) outcomes research and quality; (4) veterans/military studies; (5) provider/primary-care interventions; (6) geriatrics and formal/informal care; (7) policies and health outcomes; (8) medication treatment/therapy; (9) patient interventions; (10) health insurance legislation and policies; (11) public health policies; (12) literature reviews; (13) cost-effectiveness and economic evaluation; (14) cancer care; (15) workforce issues; and (16) socioeconomic status and disparities. The 2-dimensional map revealed that some journals have stronger associations with specific topics. Findings were not consistent with previous studies based on user perceptions. CONCLUSION: Findings of this study can be used by the stakeholders of health services research, policy, and economics to develop future research agendas, target journal submissions, and generate interdisciplinary solutions by examining overlapping journals for particular topics.

A text mining study of topics and trends in health care management journals: 1998-2018.

BACKGROUND: Advances in natural language processing and text mining provide a powerful approach to understanding trending themes in the health care management literature. PURPOSE: The aim of this study was to introduce machine learning, particularly text mining and natural language processing, as a viable approach to summarizing a subset of health care management research. The secondary aim of the study was to display the major foci of health care management research and to summarize the literature's evolution trends over a 20-year period. METHODOLOGY/APPROACH: Article abstracts (N = 2,813), from six health care management journals published from 1998 through 2018 were evaluated through latent semantic analysis, topic analysis, and multiple correspondence analysis. RESULTS: Using latent semantic analysis and topic analysis on 2,813 abstracts revealed eight distinct topics. Of the eight, three leadership and transformation, workforce well-being, and delivery of care issues were up-trending, whereas organizational performance, patient-centeredness, technology and innovation, and managerial issues and gender concerns exhibited downward trending. Finance exhibited peaks and troughs throughout the study period. Four journals, Frontiers of Health Services Management, Journal of Healthcare Management, Health Care Management Review, and Advances in Health Care Management, exhibited strong associations with finance, organizational performance, technology and innovation, managerial issues and gender concerns, and workforce well-being. The Journal of Health Management and the Journal of Health Organization and Management were more distant from the other journals and topics, except for delivery of care, and leadership and transformation. CONCLUSION: There was a close association of journals and research topics, and research topics evolved with changes in the health care environment. PRACTICE IMPLICATIONS: As scholars develop research agendas, focus should be on topics important to health care management practitioners for better informed decision-making.

Nursing-sensitive indicators for nursing care: A systematic review (1997-2017).

AIM: To provide a systematic review of the literature from 1997 to 2017 on nursing-sensitive indicators. DESIGN: A qualitative design with a deductive approach was used. DATA SOURCES: Original and Grey Literature references from Cochrane Library, Medline/PubMed, Embase, and CINAHL, Google Scholar Original and Grey Literature. REVIEW METHODS: Quality assessment was performed using the NIH Quality Assessment Tool for Observational Cohort and Cross-Sectional Studies. RESULTS: A total of 3,633 articles were identified, and thirty-nine studies met the inclusion criteria. The quantitative assessment of investigated relationships in these studies suggests that nursing staffing, mortality, and nosocomial infections were the most frequently reported nursing-sensitive indicators. CONCLUSION: This review provides a comprehensive list of nursing-sensitive indicators, their frequency of use, and the associations between these indicators and various outcome variables. Stakeholders of nursing research may use the findings to streamline the indicator development efforts and standardization of nursing-sensitive indicators. IMPACT: This review provides evidence-based results that health organizations can benefit from nursing care quality.

A critical analysis of COVID-19 research literature: Text mining approach.

OBJECTIVE: Among the stakeholders of COVID-19 research, clinicians particularly experience difficulty keeping up with the deluge of SARS-CoV-2 literature while performing their much needed clinical duties. By revealing major topics, this study proposes a text-mining approach as an alternative to navigating large volumes of COVID-19 literature. MATERIALS AND METHODS: We obtained 85,268 references from the NIH COVID-19 Portfolio as of November 21. After the exclusion based on inadequate abstracts, 65,262 articles remained in the final corpus. We utilized natural language processing to curate and generate the term list. We applied topic modeling analyses and multiple correspondence analyses to reveal the major topics and the associations among topics, journal countries, and publication sources. RESULTS: In our text mining analyses of NIH's COVID-19 Portfolio, we discovered two sets of eleven major research topics by analyzing abstracts and titles of the articles separately. The eleven major areas of COVID-19 research based on abstracts included the following topics: 1) Public Health, 2) Patient Care & Outcomes, 3) Epidemiologic Modeling, 4) Diagnosis and Complications, 5) Mechanism of Disease, 6) Health System Response, 7) Pandemic Control, 8) Protection/Prevention, 9) Mental/Behavioral Health, 10) Detection/Testing, 11) Treatment Options. Further analyses revealed that five (2,3,4,5, and 9) of the eleven abstract-based topics showed a significant correlation (ranked from moderate to weak) with title-based topics. CONCLUSION: By offering up the more dynamic, scalable, and responsive categorization of published literature, our study provides valuable insights to the stakeholders of COVID-19 research, particularly clinicians.

Identifying research themes and trends in the top 20 cancer journals through textual analysis.

BACKGROUND: The rapid growth in cancer research continues expanding the literature. Text mining approaches help make sense of large bodies of scientific literature and integrate the mounting data into the health care delivery system. Our objective is to generate a comprehensive understanding of the themes and trends in cancer research. METHODS: We employed a three-step text mining process of corpus generation and term-list creation and analysis, including latent semantic analysis for dimension reduction and factor analysis for topic identification to analyze 93,423 abstracts from the top 20 cancer/oncology journals for the period between 1999 and 2020. RESULTS: We identified 14 distinct topics in cancer literature. The results revealed the uptrend topics - including cell signaling (T-2), immunotherapy (T-3), clinical trials (T-5), disparities and epidemiology (T-7), cancer practice and policy (T-8), outcome research (T-9), and molecular therapeutics (T-10). - and downtrend topics such as cell death (T-1), early phase clinical trials (T-4), angiogenesis (T-6), cancer screening (T-12), and transplant (T-13). The topics of biomarkers(T-11) and cancer genetics(T-16) remained relatively stable. While the topics of angiogenesis (n = 10,490) and cell death (n = 10,258) included the highest number of abstracts, biomarkers (n = 3203), and cancer genetic (n = 4322) themes included the least number of articles. These findings suggest that despite having the lowest numbers of publications, certain topics such as cancer genetic (T-16) and biomarkers (T-11) have been exhibiting a stable trend and drawing a steady amount of attention from cancer researchers over the past 20 years. CONCLUSION: Findings of this study contribute explanatory insight about themes and trends in cancer research, which can help researchers and stakeholders to identify areas for future studies. POLICY SUMMARY STATEMENT: The findings indicate the increasing efforts to improve cancer practice and cancer care through policy efforts. Therefore, policymakers and other stakeholders may use the findings in prioritization and funding of specific topics.

Healthcare Research and Analytics Data Infrastructure Solution: A Data Warehouse for Health Services Research.

BACKGROUND: Health services researchers spend a substantial amount of time performing integration, cleansing, interpretation, and aggregation of raw data from multiple public or private data sources. Often, each researcher (or someone in their team) duplicates this effort for their own project, facing the same challenges and experiencing the same pitfalls discovered by those before them. OBJECTIVE: This paper described a design process for creating a data warehouse that includes the most frequently used databases in health services research. METHODS: The design is based on a conceptual iterative process model framework that utilizes the sociotechnical systems theory approach and includes the capacity for subsequent updates of the existing data sources and the addition of new ones. We introduce the theory and the framework and then explain how they are used to inform the methodology of this study. RESULTS: The application of the iterative process model to the design research process of problem identification and solution design for the Healthcare Research and Analytics Data Infrastructure Solution (HRADIS) is described. Each phase of the iterative model produced end products to inform the implementation of HRADIS. The analysis phase produced the problem statement and requirements documents. The projection phase produced a list of tasks and goals for the ideal system. Finally, the synthesis phase provided the process for a plan to implement HRADIS. HRADIS structures and integrates data dictionaries provided by the data sources, allowing the creation of dimensions and measures for a multidimensional business intelligence system. We discuss how HRADIS is complemented with a set of data mining, analytics, and visualization tools to enable researchers to more efficiently apply multiple methods to a given research project. HRADIS also includes a built-in security and account management framework for data governance purposes to ensure customized authorization depending on user roles and parts of the data the roles are authorized to access. CONCLUSIONS: To address existing inefficiencies during the obtaining, extracting, preprocessing, cleansing, and filtering stages of data processing in health services research, we envision HRADIS as a full-service data warehouse integrating frequently used data sources, processes, and methods along with a variety of data analytics and visualization tools. This paper presents the application of the iterative process model to build such a solution. It also includes a discussion on several prominent issues, lessons learned, reflections and recommendations, and future considerations, as this model was applied.

Text-mining analysis of mHealth research.

In recent years, because of the advancements in communication and networking technologies, mobile technologies have been developing at an unprecedented rate. mHealth, the use of mobile technologies in medicine, and the related research has also surged parallel to these technological advancements. Although there have been several attempts to review mHealth research through manual processes such as systematic reviews, the sheer magnitude of the number of studies published in recent years makes this task very challenging. The most recent developments in machine learning and text mining offer some potential solutions to address this challenge by allowing analyses of large volumes of texts through semi-automated processes. The objective of this study is to analyze the evolution of mHealth research by utilizing text-mining and natural language processing (NLP) analyses. The study sample included abstracts of 5,644 mHealth research articles, which were gathered from five academic search engines by using search terms such as mobile health, and mHealth. The analysis used the Text Explorer module of JMP Pro 13 and an iterative semi-automated process involving tokenizing, phrasing, and terming. After developing the document term matrix (DTM) analyses such as single value decomposition (SVD), topic, and hierarchical document clustering were performed, along with the topic-informed document clustering approach. The results were presented in the form of word-clouds and trend analyses. There were several major findings regarding research clusters and trends. First, our results confirmed time-dependent nature of terminology use in mHealth research. For example, in earlier versus recent years the use of terminology changed from "mobile phone" to "smartphone" and from "applications" to "apps". Second, ten clusters for mHealth research were identified including (I) Clinical Research on Lifestyle Management, (II) Community Health, (III) Literature Review, (IV) Medical Interventions, (V) Research Design, (VI) Infrastructure, (VII) Applications, (VIII) Research and Innovation in Health Technologies, (IX) Sensor-based Devices and Measurement Algorithms, (X) Survey-based Research. Third, the trend analyses indicated the infrastructure cluster as the highest percentage researched area until 2014. The Research and Innovation in Health Technologies cluster experienced the largest increase in numbers of publications in recent years, especially after 2014. This study is unique because it is the only known study utilizing text-mining analyses to reveal the streams and trends for mHealth research. The fast growth in mobile technologies is expected to lead to higher numbers of studies focusing on mHealth and its implications for various healthcare outcomes. Findings of this study can be utilized by researchers in identifying areas for future studies.