Mengnan Zhao

Symptom clusters in women with breast cancer: an analysis of data from social media and a research study

AbstractPurposeUser-generated content on social media sites, such as health-related online forums, offers researchers a tantalizing amount of information, but concerns regarding scientific application of such data remain. This paper compares and contrasts symptom cluster patterns derived from messages on a breast cancer forum with those from a symptom checklist completed by breast cancer survivors participating in a research study.MethodsOver 50,000 messages generated by 12,991 users of the breast cancer forum on MedHelp.org were transformed into a standard form and examined for the co-occurrence of 25 symptoms. The k-medoid clustering method was used to determine appropriate placement of symptoms within clusters. Findings were compared with a similar analysis of a symptom checklist administered to 653 breast cancer survivors participating in a research study. ResultsThe following clusters were identified using forum data: menopausal/psychological, pain/fatigue, gastrointestinal, and miscellaneous. Study data generated the clusters: menopausal, pain, fatigue/sleep/gastrointestinal, psychological, and increased weight/appetite. Although the clusters are somewhat different, many symptoms that clustered together in the social media analysis remained together in the analysis of the study participants. Density of connections between symptoms, as reflected by rates of co-occurrence and similarity, was higher in the study data.ConclusionsThe copious amount of data generated by social media outlets can augment findings from traditional data sources. When different sources of information are combined, areas of overlap and discrepancy can be detected, perhaps giving researchers a more accurate picture of reality. However, data derived from social media must be used carefully and with understanding of its limitations.

Mining Online Heterogeneous Healthcare Networks for Drug Repositioning

Drug repositioning represents the application of known drugs for new indications and plays an important role in healthcare research and industry. With its increasing value in drug development, multiple approaches have been applied in its exercise, basically classified as drug-based and diseasebased approaches. Our study adopted a disease-based approach and utilized Adverse Drug Reactions (ADRs) as an intermediary to associate drugs with diseases for drug repositioning. Based on the collected health-related social media data, we constructed a heterogeneous healthcare network and developed three path-mining techniques to identify significant associations between ADRs and diseases and then determine the associations between potential drugs and diseases for repositioning. When an ADR has a strong association with a disease based on the drugs indicated for the disease, there is an underlying mechanism-of-action (MOA) between the disease and the ADR. The ADR can be considered as a clinical phenotypic biomarker of the disease. Others drugs that have a strong association with the ADR are prospective for repositioning [12]. The experiment results demonstrate the repositioning capability of the proposed method and the advantages of using social media data. The case studies and the ratio of supporting articles show its effectiveness and the potential for further drug development research.

Drug Repositioning to Accelerate Drug Development Using Social Media Data: Computational Study on Parkinson Disease

Background Due to the high cost and low success rate in new drug development, systematic drug repositioning methods are exploited to find new indications for existing drugs. Objective We sought to propose a new computational drug repositioning method to identify repositioning drugs for Parkinson disease (PD). Methods We developed a novel heterogeneous network mining repositioning method that constructed a 3-layer network of disease, drug, and adverse drug reaction and involved user-generated data from online health communities to identify potential candidate drugs for PD. Results We identified 44 non-Parkinson drugs by using the proposed approach, with data collected from both pharmaceutical databases and online health communities. Based on the further literature analysis, we found literature evidence for 28 drugs. Conclusions In summary, the proposed heterogeneous network mining repositioning approach is promising for identifying repositioning candidates for PD. It shows that adverse drug reactions are potential intermediaries to reveal relationships between disease and drug.

Automated Off-label Drug Use Detection from User Generated Content

Off-label drug use refers to using marketed drugs for indications that are not listed in their FDA labeling information. Such uses are very common and sometimes inevitable in clinical practice. To some extent, off-label drug uses provide a pathway for clinical innovation, however, they could cause serious adverse effects due to lacking scientific research and tests. Since identifying the off-label uses can provide a clue to the stakeholders including healthcare providers, patients, and medication manufacturers to further the investigation on drug efficacy and safety, it raises the demand for a systematic way to detect off-label uses. Given data contributed by health consumers in online health communities (OHCs), we developed an automated approach to detect off-label drug uses based on heterogeneous network mining. We constructed a heterogeneous healthcare network with medical entities (e.g. disease, drug, adverse drug reaction) mined from the text corpus, which involved 50 diseases, 1,297 drugs, and 185 ADRs, and determined 13 meta paths between the drugs and diseases. We developed three metrics to represent the meta-path-based topological features. With the network features, we trained the binary classifiers built on Random Forest algorithm to recognize the known drug-disease associations. The best classification model that used lift to measure path weights obtained F1-score of 0.87, based on which, we identified 1,009 candidates of off-label drug uses and examined their potential by searching evidence from PubMed and FAERS.

Determining Associations with Word Embedding in Heterogeneous Network for Detecting Off-Label Drug Uses

Off-label drug use is quite common in clinical practice and inevitable to some extent. Such uses might deliver effective treatment and suggest clinical innovation sometimes, however, they have the unknown risk to cause serious outcomes due to lacking scientific support. As gaining information about off-label drug use could present a clue to the stakeholders such as healthcare professionals and medication manufacturers to further the investigation on drug efficacy and safety, it raises the need to develop a systematic way to detect off-label drug uses. Considering the increasing discussions in online health communities (OHCs) among the health consumers, we proposed to harness the large volume of timely information in OHCs to develop an automated method for detecting off-label drug uses from health consumer generated data. From the text corpus, we extracted medical entities (diseases, drugs, and adverse drug reactions) with lexicon-based approaches and measured their interactions with word embedding models, based on which, we constructed a heterogeneous healthcare network. We defined several meta-path-based indicators to describe the drug-disease associations in the heterogeneous network and used them as features to train a binary classifier built on Random Forest algorithm, to recognize the known drug-disease associations. The classification model obtained better results when incorporating word embedding features and achieved the best performance when using both association rule mining features and word embedding features, with F1-score reaching 0.939, based on which, we identified 2,125 possible off-label drug uses and checked their potential by searching evidence in PubMed and FAERS.

Patterns of Interaction within Smoking Cessation Groups on Facebook: A Social Network Analysis

Social media represents a promising strategy to deliver and engage participants in smoking cessation intervention. Previous analyses have highlighted the potential of this medium as a resource for requesting or offering information, discussing smoking [1], and exchanging social support [2] in the context of a public quit smoking Facebook page. Here, we used social network analysis to characterize the extent of and relationship among users in a quit smoking intervention conducted through private groups on Facebook.

Extraction of Clinical Phenotypic Information from Online Heterogeneous Healthcare Networks

Millions of patients are affected by adverse drug reactions (ADRs) every year. It represents a substantial burden on healthcare resources. Pharmacovigilance using text and data analytics has drawn substantial attention in the recent years. These techniques are mainly extracting the associations between drugs and ADRs using data sources such as spontaneous reporting systems, electronic health records, medical literature, and pharmacological databases. In this work, we are not only interested in extracting the associations between drugs and ADRs but also the associations between diseases and ADRs. There is an association between a disease and an ADR when the drugs treating the disease are associated with the same ADR, which means there might be an underlying mechanism-of-action (MOA) between the disease and the ADR [1]. The ADR can be considered as a clinical phenotypic biomarker for the disease. In addition, we are adopting the social media data as the data source in analytics. The social media provides timely and large volume of health consumer contributed information that overcomes the limitations the traditional data sources. We propose to construct a heterogeneous healthcare network from social media data and develop three path-mining techniques to the clinical phenotypic information. The experiments results demonstrate that the proposed method is effective in detecting significant and novel ADR-disease associations. Case study shows that many of the association can be supported by existing academic literatures.