Toward multimodal signal detection of adverse drug reactions

Harpaz, Rave; DuMouchel, William; Schuemie, Martijn J.; Bodenreider, Olivier; Friedman, Carol; Horvitz, Eric; Ripple, Anna; Sorbello, Alfred; White, Ryen W.; Winnenburg, Rainer; Shah, Nigam H.

doi:10.1016/j.jbi.2017.10.013

Cited by 30 publications

(28 citation statements)

References 42 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Nevertheless, the PRS‐platform‐derived IOR can converge all the rats to have uniform tumor response. This augmented AI‐PRS platform is model independent, and can be applied toward virtually all classes of drugs, having been previously validated for indications ranging from infectious diseases to clinical immunosuppression and regenerative medicine . Future studies harness this platform to agnostically design novel drug combinations for subsequent individualization.…”

Section: Discussionmentioning

confidence: 99%

“…The broader definition of AI, particularly in the context of medicine, is the use of large data sets to train algorithms to iteratively solve for constants in these algorithms that can mediate improved image recognition for diagnostics, as well as drug discovery and development . With a few hundred experimental data points, we applied an artificial intelligence (AI)‐based neural networks approach to correlate drug–dose inputs with phenotypic outputs (tumor burden, toxicity markers) .…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Harnessing an Artificial Intelligence Platform to Dynamically Individualize Combination Therapy for Treating Colorectal Carcinoma in a Rat Model

Chang

et al. 2019

Advanced Therapeutics

View full text Add to dashboard Cite

Designing multi-drug regimens often involves target-and synergy prediction-based drug selection, and subsequent dose escalation to achieve the maximum tolerated dose (MTD) of each drug. This approach may improve efficacy, but not the optimal efficacy and often substantially increases toxicity. Drug interactions depend on many pathways in the omics networks and further complicate the design process. The virtually infinite drug-dose parameter space cannot be reconciled using conventional approaches, which are largely based on prediction. This barrier at least partially accounts for the low response rates that are observed with conventional mono-and combinatorial chemotherapy. A combination of nonstandard therapies for colorectal cancer (AGCH: adriamycin, gemcitabine, cisplatin, and herceptin) at ¼ MTD is used to treat the rats, the tumor response rates varied in a wide range. Some of the tumor response rates are close to that of control group. This work harnesses an artificial intelligence (AI) platform that is mechanism free and can dynamically optimize combinatorial therapy in rats. The individually optimized AGCH regimen reveal starkly different drug-dose parameters, which can converge each rat toward the same and low tumor response rate. Importantly, this AI-based drug-dose optimization technology is an actionable platform, which can achieve N-of-1 therapy.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Harnessing an Artificial Intelligence Platform to Dynamically Individualize Combination Therapy for Treating Colorectal Carcinoma in a Rat Model

Chang

et al. 2019

Advanced Therapeutics

View full text Add to dashboard Cite

show abstract

“…Scholars have made significant progress on topics revolving around the recognition of drug names, symptoms and ADRs in social media texts using automated or semiautomated methods [93]. Research efforts for the development of appropriate text mining methods and natural language processing (NLP) techniques are ongoing.…”

Section: Information Extraction From Social Mediamentioning

confidence: 99%

Harnessing social media data for pharmacovigilance: a review of current state of the art, challenges and future directions

Pappa

Stergioulas

2019

Int J Data Sci Anal

View full text Add to dashboard Cite

The ever-increasing supply of information combined with the growing knowledge elicitation capabilities of key emerging technologies presents pharmacovigilance with enormous opportunities. Currently, safety monitoring is expanding its evidence base, moving beyond traditional approaches towards sophisticated methods that can identify possible safety signals from multiple information sources, both structured and unstructured. In this context, health information posted online by patients represents a potentially valuable, yet currently left largely unexploited source of post-market safety data that could supplement data from traditional sources of drug safety information. As the use of social media data for pharmacovigilance is still in its infancy, the present paper explores the state of the art in the application of social data to adverse drug reaction detection; provides a thorough review of existing work in the field, highlighting important research efforts and achievements; and finally, discusses the current challenges and promising avenues for future work. Following a literature review methodology, a critical appraisal was conducted of carefully selected work on the use of social data in post-market surveillance, as presented in the recent scientific literature. Out of a sample of more than 1300 articles, which was the result of the literature search, the final selection of articles was made based on their relevance to the applications of social networking sites (SNS) to pharmacovigilance, and a thorough review of this corpus was completed with a total of 100 articles reviewed. The main contributions of this review include the mapping and systematisation of the current knowledge in the field by drawing comparisons of different approaches, types of social data and of relevant sources currently used in the field, and by developing new classifications of social data sources and taxonomies for social data for use in pharmacovigilance, as well as the identification of key challenges and the extraction of new insights in terms of potential for practical applications and future research directions in the area of pharmacovigilance. Publisher's Note Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

show abstract

“…Trials are limited in ADR detection because of their small sizes of patient groups, short durations, and a lack of enrolled patient diversity [4,5]. ADRs that become apparent in the post-market period result in over 2 million injuries and $75 billion annual health care cost [6,7]. Ongoing surveillance strategies are necessary to monitor the drug safety when drug use is expanded during the post-approval period.…”

Section: Introductionmentioning

confidence: 99%

“…SRSs can effectively detect rare ADRs by nature of their longitudinal profiling and wide reach of included reports, but suffer due to their reliance on voluntary patient or provider reporting; it is estimated that more than 90% of ADRs are under-reported [8,9]. ADR under-detection has motivated efforts to include complementary, alternative data sources for pharmacovigilance, including electronic health records and administrative claims [10,11,12], biomedical literature [13,14], internet search logs [15], patient posts in social media [16,17] and mulitimodal systems that jointly analyze multiple sources of information for ADR detection [7].…”

Section: Introductionmentioning

confidence: 99%

Early Detection of Adverse Drug Reactions in Social Health Networks: A Natural Language Processing Pipeline for Signal Detection (Preprint)

Nikfarjam¹,

Ransohoff²,

Callahan³

et al. 2018

Preprint

View full text Add to dashboard Cite

Importance: Adverse drug reactions (ADRs) occur in nearly all patients on chemotherapy, causing morbidity and therapy disruptions. Detection of such of ADRs is limited in clinical trials, which are underpowered to detect rare events. Early recognition of ADRs in the post-marketing phase could substantially reduce morbidity and decrease societal costs. Internet community health forums provide a mechanism for individuals to discuss real-time health concerns and can enable computational detection of ADRs.Objective: To identify cutaneous ADR signals in social health networks and compare the frequency and timing of these ADRs to clinical reports in the literature. Design:We present a natural language processing (NLP) based ADR signal generation pipeline based on patient posts on internet social health networks. We identify user posts from Inspire health forum related to two chemotherapy classes: erlotinib, an epidermal growth factor receptor inhibitor, and nivolumab and pembrolizumab, immune checkpoint inhibitors. We extract mentions of ADRs from unstructured content of patient posts. We then perform population-level association analyses and time-to-detection analyses.Results: Our system detected ADRs from patient reports with high precision (0.90) and at frequencies comparable to those documented in the literature, but an average of 7 months ahead of their literature reporting. Known ADRs associated with higher proportional reporting ratios compared to negative controls, demonstrating the robustness of our analyses. Additionally, we discovered the novel ADR of hypohidrosis reported by 23 patients in erlotinib related posts; this ADR was absent from 15 years of literature on this medication and we recently reported the finding in a clinical oncology journal. Conclusions and relevance:Several hundred million patients report health concerns in social health networks, yet this information is markedly underutilized for pharmacosurveillance. We demonstrate the ability of an NLP-based signal generation pipeline to accurately detect patient reports of ADRs months in advance of literature reporting, and the robustness of statistical analyses to validate system detections. Our findings suggest the important contributions that social health network data can play in contributing to more comprehensive and timely pharmacovigilance.

show abstract

Toward multimodal signal detection of adverse drug reactions

Cited by 30 publications

References 42 publications

Harnessing an Artificial Intelligence Platform to Dynamically Individualize Combination Therapy for Treating Colorectal Carcinoma in a Rat Model

Harnessing an Artificial Intelligence Platform to Dynamically Individualize Combination Therapy for Treating Colorectal Carcinoma in a Rat Model

Harnessing social media data for pharmacovigilance: a review of current state of the art, challenges and future directions

Early Detection of Adverse Drug Reactions in Social Health Networks: A Natural Language Processing Pipeline for Signal Detection (Preprint)

Contact Info

Product

Resources

About