Comment Topic Evolution on a Cancer Institution's Facebook Page

Scalable Feature Engineering from Electronic Free Text Notes to Supplement Confounding Adjustment of Claims-Based Pharmacoepidemiologic Studies

Natural language processing (NLP) tools turn free-text notes (FTNs) from electronic health records (EHRs) into data features that can supplement confounding adjustment in pharmacoepidemiologic studies. However, current applications are difficult to scale. We used unsupervised NLP to generate high-dimensional feature spaces from FTNs to improve prediction of drug exposure and outcomes compared with claims-based analyses. We linked Medicare claims with EHR data to generate three cohort studies comparing different classes of medications on the risk of various clinical outcomes. We used "bag-of-words" to generate features for the top 20,000 most prevalent terms from FTNs. We compared machine learning (ML) prediction algorithms using different sets of candidate predictors: Set1 (39 researcher-specified variables), Set2 (Set1 + ML-selected claims codes), and Set3 (Set1 + ML-selected NLP-generated features), vs. Set4 (Set1 + 2 + 3). When modeling treatment choice, we observed a consistent pattern across the examples: ML models utilizing Set4 performed best followed by Set2, Set3, then Set1. When modeling the outcome risk, there was little to no improvement beyond models based on Set1. Supplementing claims data with NLP-generated features from free text notes improved prediction of prescribing choices but had little or no improvement on clinical risk prediction. These findings have implications for strategies to improve confounding using EHR data in pharmacoepidemiologic studies.

Facebook Users' Interactions, Organic Reach, and Engagement in a Smoking Cessation Intervention: Content Analysis

BACKGROUND

Facebook can be a suitable platform for public health interventions. Facebook users can express their reaction to the given social media content in many ways using interaction buttons. The analysis of these interactions can be advantageous in increasing reach and engagement of public health interventions.

OBJECTIVE

This research aimed at understanding how Facebook users' interactions correlate with organic reach and engagement regarding the same smoking cessation support contents.

METHODS

The study population consisted of Facebook users who were reached by a public smoking cessation support page without advertising. We included 1025 nonpaid Facebook posts (N=1025) which used smoking cessation strategies based on a motivational interviewing counseling style. The following data were collected from the "Post Details": the number of people who saw the given nonpaid content (organic reach) which consisted of fan and nonfan reach according to previous "page like" activity; each rate of "engagement indicators" (such as the symbols of "like," "love," "haha," "wow," "sad," "angry"; or other interactions: "shares," "comments," "clicks"); and the rate of negative Facebook interactions (eg, "post hides" or "unlike of page"). Overall, these data were analyzed with the Spearman correlation method.

RESULTS

Surprisingly, we found a significant negative correlation between organic reach and the "like" reaction (rs=-0.418; P<.001). The strongest significant positive correlations of organic reach were observed with the "haha" reaction (rs=0.396; P<.001), comments (rs=0.368; P<.001), and the "love" reaction (rs=0.264; P<.001). Furthermore, nonfan reach correlated positively with "shares" (rs=0.388; P<.001) and clicks (rs=0.135; P<.001), while fan reach correlated positively with the "haha" reaction (rs=0.457; P<.001), comments (rs=0.393; P<.001), and the "love" reaction (rs=0.310; P<.001). Contrary to expectations, the "like" reaction was sharply separated by significant negative correlations from "wow" (rs=-0.077; P=.013), "sad" (rs=-0.120; P<.001), "angry" reactions (rs=-0.136; P<.001), and comments (rs=-0.130; P<.001). Additionally, a high rate of negative Facebook interactions was significantly associated with "wow" (rs=0.076; P=.016) and "sad" reactions (rs=0.091; P=.003).

CONCLUSIONS

This study has shown that it is possible to hypothesize a disadvantage of the "like" reaction and advantages of other interactions (eg, the "haha" reaction or "comments") in content algorithmic ranking on Facebook. In addition, the correlational analysis revealed a need of a further categorization to fan-specific interactions (eg, "haha" or "love" reactions) and nonfan-specific interactions (eg, "shares" and "clicks"). Regarding the direction of the correlations, these findings suggest that some interactions (eg, negative Facebook interactions, "wow," "sad," and "angry" reactions) may decrease the engagement, while other interactions ("like," "love," "haha" reactions, "shares," and "clicks") may increase the engagement during Facebook-based smoking cessation interventions. This hypothesis-generating research offers an important insight into the relationship between organic reach, engagement, and Facebook users' interactions for public health professionals who design Facebook-based interventions.

A Collaborative Framework Based for Semantic Patients-Behavior Analysis and Highlight Topics Discovery of Alcoholic Beverages in Online Healthcare Forums

Medical data in online groups and social media contain valuable information, which is provided by both healthcare professionals and patients. In fact, patients can talk freely and share their personal experiences. These resources are a valuable opportunity for health professionals who can access patients' opinions, as well as discussions between patients. Recently, the data processing of the health community and, how to extract knowledge is a significant technical challenge. There are many online group and forums that users can discuss on healthcare issues. Therefore, we can examine these text documents for discovering knowledge and evaluating patients' behavior based on their opinions and discussions. For example, there are many questions and answering groups on Twitter or Facebook. Given the importance of the research, in this paper, we present a semantic framework based on topic model (LDA) and Random forest(RF) to predict and retrieval latent topics of healthcare text-documents from an online forum. We extract our healthcare records (patient-questions) from patient.info website as a real dataset. Experiments on our dataset show that social media forums could help for detecting significant patient safety problems on healthcare issues.

Characterizing Artificial Intelligence Applications in Cancer Research: A Latent Dirichlet Allocation Analysis

Background

Artificial intelligence (AI)–based therapeutics, devices, and systems are vital innovations in cancer control; particularly, they allow for diagnosis, screening, precise estimation of survival, informing therapy selection, and scaling up treatment services in a timely manner.

Objective

The aim of this study was to analyze the global trends, patterns, and development of interdisciplinary landscapes in AI and cancer research.

Methods

An exploratory factor analysis was conducted to identify research domains emerging from abstract contents. The Jaccard similarity index was utilized to identify the most frequently co-occurring terms. Latent Dirichlet Allocation was used for classifying papers into corresponding topics.

Results

From 1991 to 2018, the number of studies examining the application of AI in cancer care has grown to 3555 papers covering therapeutics, capacities, and factors associated with outcomes. Topics with the highest volume of publications include (1) machine learning, (2) comparative effectiveness evaluation of AI-assisted medical therapies, and (3) AI-based prediction. Noticeably, this classification has revealed topics examining the incremental effectiveness of AI applications, the quality of life, and functioning of patients receiving these innovations. The growing research productivity and expansion of multidisciplinary approaches are largely driven by machine learning, artificial neural networks, and AI in various clinical practices.

Conclusions

The research landscapes show that the development of AI in cancer care is focused on not only improving prediction in cancer screening and AI-assisted therapeutics but also on improving other corresponding areas such as precision and personalized medicine and patient-reported outcomes.

Cancer Informatics in 2017: A New Beginning and a Bright Future

Objective:  To summarize significant research contributions on cancer informatics published in 2017.

Methods:  An extensive search using PubMed/Medline, Google Scholar, and manual review was conducted to identify the scientific contributions published in 2017 that address topics in cancer informatics. The selection process comprised three steps: (i) 15 candidate best papers were first selected by the two section editors, (ii) external reviewers from internationally renowned research teams reviewed each candidate best paper, and (iii) the final selection of three best papers was conducted by the editorial board of the Yearbook.

Results:  Results: The three selected best papers present studies addressing many facets of cancer informatics, with immediate applicability in the research and clinical domains.

Conclusion: Cancer informatics is a broad and vigorous subfield of biomedical informatics. Strides in knowledge management, crowdsourcing, and visualization are especially notable in 2017.