Detecting adverse drug reactions in discharge summaries of electronic medical records using Readpeer

Tang, Yixuan; Yang, Jisong; Ang, Pei San; Dorajoo, Sreemanee Raaj; Foo, Belinda; Soh, Sally; Tan, Siew Har; Tham, Mun Yee; Ye, Qing; Sung, Cynthia; Tung, Anthony K. H.

doi:10.1016/j.ijmedinf.2019.04.017

Cited by 22 publications

(23 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Studies in this category retrieved data from different repositories such as DrugBank, Side Effect Resource, the Food and Drug Administration (FDA)’s adverse event reporting system, University of Massachusetts Medical School, Observational Medical Outcomes Partnership database, and Human Protein-Protein Interaction database to identify adverse drug interactions and reactions that can potentially negatively influence patient health [ 86 - 88 , 101 , 102 , 105 - 107 , 110 ]. Some studies also used AI to predict drug interactions by analyzing EHR data [ 88 ], unstructured discharge notes [ 90 ], and clinical charts [ 99 , 104 ]. One study also used AI to identify drugs that were withdrawn from the commercial markets by the FDA [ 100 ].…”

Section: Resultsmentioning

confidence: 99%

Role of Artificial Intelligence in Patient Safety Outcomes: Systematic Literature Review

2020

View full text Add to dashboard Cite

Background Artificial intelligence (AI) provides opportunities to identify the health risks of patients and thus influence patient safety outcomes. Objective The purpose of this systematic literature review was to identify and analyze quantitative studies utilizing or integrating AI to address and report clinical-level patient safety outcomes. Methods We restricted our search to the PubMed, PubMed Central, and Web of Science databases to retrieve research articles published in English between January 2009 and August 2019. We focused on quantitative studies that reported positive, negative, or intermediate changes in patient safety outcomes using AI apps, specifically those based on machine-learning algorithms and natural language processing. Quantitative studies reporting only AI performance but not its influence on patient safety outcomes were excluded from further review. Results We identified 53 eligible studies, which were summarized concerning their patient safety subcategories, the most frequently used AI, and reported performance metrics. Recognized safety subcategories were clinical alarms (n=9; mainly based on decision tree models), clinical reports (n=21; based on support vector machine models), and drug safety (n=23; mainly based on decision tree models). Analysis of these 53 studies also identified two essential findings: (1) the lack of a standardized benchmark and (2) heterogeneity in AI reporting. Conclusions This systematic review indicates that AI-enabled decision support systems, when implemented correctly, can aid in enhancing patient safety by improving error detection, patient stratification, and drug management. Future work is still needed for robust validation of these systems in prospective and real-world clinical environments to understand how well AI can predict safety outcomes in health care settings.

show abstract

Section: Resultsmentioning

confidence: 99%

Role of Artificial Intelligence in Patient Safety Outcomes: Systematic Literature Review

2020

View full text Add to dashboard Cite

show abstract

“…10 Expert configured natural language processing (NLP) framework in Hospital discharge summaries which offers a potentially resource of adverse event to evaluate drug safety in real-world practice. 11 Major positive attributes of the Risk management programs include active involvement of independent expert clinical advisory committees in identifying and evaluating risks through the assessment of reports of serious and unusual reactions, and regular communications about risks from HSA to HCPs by means of bulletins. 12…”

Section: Pv System In Singaporementioning

confidence: 99%

Pharmacovigilance in India and five ASEAN countries (Malaysia, Singapore, Thailand, Indonesia, Philippines): A comparison study

Dutta¹,

Banerjee²,

Pramanik³

et al. 2021

IJCAAP

View full text Add to dashboard Cite

The World Health Organization (WHO) defines PV as the science and activities related to the detection, assessment, understanding, and prevention of adverse effects or any other possible drug-related problems (WHO 2004). In 1968, during the 16th World Assembly the 16.36 resolution called for "a systematic collection of information on serious adverse drug reactions during the development and particularly after medicines have been made available for public use". This led to the formation of the WHO Programme for International Drug Monitoring (PIDM) in 1968. PV systems should include all entities and resources that protect the public from medicines-related harm (adverse reactions, poor product quality, medication errors, and therapeutic ineffectiveness), whether in personal healthcare or public health services. The PV system safeguards the public through efficient and timely identification, collection, and assessment of medicine-related adverse events and by communicating risks and benefits. The WHO has provided technical and normative leadership on PV since the development of the first voluntary notification scheme in 1961. As of January 2016, 123 countries have joined the WHO PIDM, and in addition 28 associate members are awaiting full membership. WHO has defined norms and guidelines for PV and has allowed information sharing among the participant countries. Another WHO PV-related activity is the work of the Council for International Organizations of Medical Sciences (CIOMS) which was established jointly by WHO and UNESCO in 1949. Starting with the publication of the Suspect Adverse Reaction Report Form (CIOMS Form I) by the CIOMS working group II, other CIOMS publications have greatly shaped the direction of PV. CIOMS publications have also greatly influenced the development of International Conference on Harmonization of Technical requirements for Registration of Pharmaceuticals for Human Use (ICH) E2A-E2F guidelines in drug safety. The standards for the electronic transmission of regulatory information regarding the individual case safety report (ICSR) has been changing over the last decade. The ICH adopted the E2B (R2) in February 2001 and the E2B (R3) in 2005, is being developed as the proposed harmonized international standards for health products safety reporting. These ICH guidelines have facilitated the adoption of harmonized standards for PV activities. This study contributes to filling the gap in the understanding of the PV systems capacity in Indian and five ASEAN countries namely Malaysia,

show abstract

“…e i = x i Ar (8) s is the weighted sum of the sentences' vector set; α i is the attention weight of sentence-level vector; e i is a function that scores the input sentence x i and predicting relationship r; A is a weighted diagonal matrix; r is a vector that indicates the relationship r. Finally, the sentence representation used for the relationship classification is obtained from the following equation:…”

Section: Attention Mechanismmentioning

confidence: 99%

Disease-Pertinent Knowledge Extraction in Online Health Communities Using GRU Based on a Double Attention Mechanism

Zhang

2020

IEEE Access

View full text Add to dashboard Cite

Relationship extraction among diseases, symptoms and tests has always been a concerning research issue in the biomedical field. Disease-pertinent relationship extraction for user-generated content in the online health community represents a research trend. By training the word embedding vectors for the medical-health field, conducting entity recognition and relationship annotation, and using deep learning technology, we construct a relation extraction model for extracting the relationships among diseases, symptoms and tests. Our relationship extraction model of the bidirectional gate recurrent unit (BiGRU) network based on character-level and sentence-level attention mechanisms achieved the best results on question-answer data in the online health community. Our research results can not only help physician diagnoses but also help patients perform health management, which has important industrial application value. INDEX TERMS Knowledge extraction, relationship extraction, attention mechanism, deep learning, bidirectional gated recurrent unit (BiGRU), online health community.

show abstract

Detecting adverse drug reactions in discharge summaries of electronic medical records using Readpeer

Cited by 22 publications

References 19 publications

Role of Artificial Intelligence in Patient Safety Outcomes: Systematic Literature Review

Role of Artificial Intelligence in Patient Safety Outcomes: Systematic Literature Review

Pharmacovigilance in India and five ASEAN countries (Malaysia, Singapore, Thailand, Indonesia, Philippines): A comparison study

Disease-Pertinent Knowledge Extraction in Online Health Communities Using GRU Based on a Double Attention Mechanism

Contact Info

Product

Resources

About