Cohort selection for clinical trials using multiple instance learning

Dai, Hong-Jie; Wang, Feng-Duo; Chen, Chih‐Wei; Su, Chu-Hsien; Jonnagaddala, Jitendra

doi:10.1016/j.jbi.2020.103438

Cited by 4 publications

(5 citation statements)

References 23 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A reliable candidate selection algorithm could help overcome several limitations that have been demonstrated in the standard procedures used today: the benefits of timeliness of intervention, with better outcomes associated with earlier treatment ( 97 ); racial disparities in the use of some surgeries ( 98 ); the lack of a unifying pathophysiology (Iverson) ( 99 ). Dai et al ( 100 ) tackled this problem from a generic standpoint, demonstrating that cohort selection of longitudinal patient records can be formulated as a multiple instance learning task. Candidate identification can be applied to very different medical topics: surgical intervention for drug-resistant pediatric epilepsy ( 101 ), risk factors for pediatric post-concussion symptoms ( 102 ), error reduction in determining eligibility for intravenous thrombolytic therapy ( 103 ).…”

Section: Resultsmentioning

confidence: 99%

Natural language processing in clinical neuroscience and psychiatry: A review

et al. 2022

View full text Add to dashboard Cite

Natural language processing (NLP) is rapidly becoming an important topic in the medical community. The ability to automatically analyze any type of medical document could be the key factor to fully exploit the data it contains. Cutting-edge artificial intelligence (AI) architectures, particularly machine learning and deep learning, have begun to be applied to this topic and have yielded promising results. We conducted a literature search for 1,024 papers that used NLP technology in neuroscience and psychiatry from 2010 to early 2022. After a selection process, 115 papers were evaluated. Each publication was classified into one of three categories: information extraction, classification, and data inference. Automated understanding of clinical reports in electronic health records has the potential to improve healthcare delivery. Overall, the performance of NLP applications is high, with an average F1-score and AUC above 85%. We also derived a composite measure in the form of Z-scores to better compare the performance of NLP models and their different classes as a whole. No statistical differences were found in the unbiased comparison. Strong asymmetry between English and non-English models, difficulty in obtaining high-quality annotated data, and train biases causing low generalizability are the main limitations. This review suggests that NLP could be an effective tool to help clinicians gain insights from medical reports, clinical research forms, and more, making NLP an effective tool to improve the quality of healthcare services.

show abstract

Section: Resultsmentioning

confidence: 99%

Natural language processing in clinical neuroscience and psychiatry: A review

et al. 2022

View full text Add to dashboard Cite

show abstract

“…feature engineering or labeling). Within the articles, corpora included notes from EHRs [33,83,90–92] as well as external sources such as biomedical publications [34,72,93–96] and articles from Wikipedia and Google News [32,69,97]. Among the methods used to train word embeddings, Word2vec [98] and Bidirectional Encoder Representations from Transformers (BERT) and variants [99–102] are the most frequently used (Supplementary Material Table S9).…”

Section: Resultsmentioning

confidence: 99%

“…Labels have also been derived from registry data [33], laboratory results [61,112,117], diagnosis codes [30,57,58,118–120], and rule-based algorithms [59,121–123] to enable more rapid development of labeled datasets. The most commonly used methods for classifying a binary phenotype are random forest [26,28,35,37,56,57,60,62,70,81,84,117,119,120,124–126], logistic regression [36,37,57,58,60,67,82,84,93,116,117,119,125,127,128], and support vector machine (SVM) [31,35,37,58,60,81,82,84,92,97,104,116,125,126] (Supplementary Material Table S12 ). It is important to note that in contrast to rule-based methods, most ML methods output a predicted score or probability of the phenotype for each patient.…”

Section: Resultsmentioning

confidence: 99%

“…However, there are inconsistencies in reporting of multiple metrics across the articles and model calibration is rarely assessed. Additionally, ML models were only compared with rule-based methods in 22 articles [25,26,36,37,60,[62][63][64][65][66]68,81,82,85,92,104,107,116,121,125,130,150] and exhibited improved performance in all but 4 studies [25,26,130,150]. Overall, we found limited reporting of data descriptors necessary for implementation of a phenotyping algorithm to a new setting.…”

Section: Evaluation and Reporting Methodsmentioning

confidence: 99%

“…feature engineering or labeling). Within the articles, corpora included notes from EHRs [33,83,[90][91][92] as well as external sources such as biomedical publications [34,72,[93][94][95][96] and articles from Wikipedia and Google News [32,69,97].…”

Section: Data Typesmentioning

confidence: 99%

See 2 more Smart Citations

Machine Learning Approaches for Electronic Health Records Phenotyping: A Methodical Review

Yang

Varghese²,

Stephenson

et al. 2022

Preprint

View full text Add to dashboard Cite

ObjectiveAccurate and rapid methods for phenotyping are a prerequisite to realizing the potential of electronic health records (EHRs) data for clinical and translational research. This study reviews the literature on machine learning (ML) approaches for phenotyping with respect to the phenotypes considered, the data sources and methods used, and the contributions within the wider context of EHR-based research.Materials and MethodsWe searched for relevant articles in PubMed and Web of Science published between January 1, 2018 and April 14, 2022. After screening, we collected data on 52 variables across 106 selected articles.ResultsML-based methods were developed for 156 unique phenotypes, primarily using EHR data from a single institution or health system. 72 of 106 articles leveraged unstructured data in clinical notes. In terms of methodology, supervised learning is the most prevalent ML paradigm (n = 64, 60.4%), with half of the articles employing deep learning. Semi-supervised and weakly-supervised approaches were applied to reduce the burden of obtaining gold-standard labeled data (n = 21, 19.8%), while unsupervised learning was used for phenotype discovery (n = 20, 18.9%). Federated learning has been applied to develop algorithms across multiple institutions while preserving data privacy (n = 2, 1.9%).DiscussionWhile the use of ML for phenotyping is growing, most articles applied traditional supervised ML to characterize the presence of common, chronic conditions.ConclusionContinued research in ML-based methods is warranted, with particular attention to the development of advanced methods for complex phenotypes and standards for reporting and evaluating phenotyping algorithms.

show abstract