Automated classification of eligibility criteria in clinical trials to facilitate patient-trial matching for specific patient populations

Leveraging artificial intelligence to advance implementation science: potential opportunities and cautions

BACKGROUND

The field of implementation science was developed to address the significant time delay between establishing an evidence-based practice and its widespread use. Although implementation science has contributed much toward bridging this gap, the evidence-to-practice chasm remains a challenge. There are some key aspects of implementation science in which advances are needed, including speed and assessing causality and mechanisms. The increasing availability of artificial intelligence applications offers opportunities to help address specific issues faced by the field of implementation science and expand its methods.

MAIN TEXT

This paper discusses the many ways artificial intelligence can address key challenges in applying implementation science methods while also considering potential pitfalls to the use of artificial intelligence. We answer the questions of "why" the field of implementation science should consider artificial intelligence, for "what" (the purpose and methods), and the "what" (consequences and challenges). We describe specific ways artificial intelligence can address implementation science challenges related to (1) speed, (2) sustainability, (3) equity, (4) generalizability, (5) assessing context and context-outcome relationships, and (6) assessing causality and mechanisms. Examples are provided from global health systems, public health, and precision health that illustrate both potential advantages and hazards of integrating artificial intelligence applications into implementation science methods. We conclude by providing recommendations and resources for implementation researchers and practitioners to leverage artificial intelligence in their work responsibly.

CONCLUSIONS

Artificial intelligence holds promise to advance implementation science methods ("why") and accelerate its goals of closing the evidence-to-practice gap ("purpose"). However, evaluation of artificial intelligence's potential unintended consequences must be considered and proactively monitored. Given the technical nature of artificial intelligence applications as well as their potential impact on the field, transdisciplinary collaboration is needed and may suggest the need for a subset of implementation scientists cross-trained in both fields to ensure artificial intelligence is used optimally and ethically.

Text Classification of Cancer Clinical Trial Eligibility Criteria

Automatic identification of clinical trials for which a patient is eligible is complicated by the fact that trial eligibility are stated in natural language. A potential solution to this problem is to employ text classification methods for common types of eligibility criteria. In this study, we focus on seven common exclusion criteria in cancer trials: prior malignancy, human immunodeficiency virus, hepatitis B, hepatitis C, psychiatric illness, drug/substance abuse, and autoimmune illness. Our dataset consists of 764 phase III cancer trials with these exclusions annotated at the trial level. We experiment with common transformer models as well as a new pre-trained clinical trial BERT model. Our results demonstrate the feasibility of automatically classifying common exclusion criteria. Additionally, we demonstrate the value of a pre-trained language model specifically for clinical trials, which yield the highest average performance across all criteria.

Predicting unplanned readmission due to cardiovascular disease in hospitalized patients with cancer: a machine learning approach

Cardiovascular disease (CVD) in cancer patients can affect the risk of unplanned readmissions, which have been reported to be costly and associated with worse mortality and prognosis. We aimed to demonstrate the feasibility of using machine learning techniques in predicting the risk of unplanned 180-day readmission attributable to CVD among hospitalized cancer patients using the 2017-2018 Nationwide Readmissions Database. We included hospitalized cancer patients, and the outcome was unplanned hospital readmission due to any CVD within 180 days after discharge. CVD included atrial fibrillation, coronary artery disease, heart failure, stroke, peripheral artery disease, cardiomegaly, and cardiomyopathy. Decision tree (DT), random forest, extreme gradient boost (XGBoost), and AdaBoost were implemented. Accuracy, precision, recall, F2 score, and receiver operating characteristic curve (AUC) were used to assess the model's performance. Among 358,629 hospitalized patients with cancer, 5.86% (n = 21,021) experienced unplanned readmission due to any CVD. The three ensemble algorithms outperformed the DT, with the XGBoost displaying the best performance. We found length of stay, age, and cancer surgery were important predictors of CVD-related unplanned hospitalization in cancer patients. Machine learning models can predict the risk of unplanned readmission due to CVD among hospitalized cancer patients.

Deep learning-based detection of patients with bone metastasis from Japanese radiology reports

PURPOSE

Deep learning (DL) is a state-of-the-art technique for developing artificial intelligence in various domains and it improves the performance of natural language processing (NLP). Therefore, we aimed to develop a DL-based NLP model that classifies the status of bone metastasis (BM) in radiology reports to detect patients with BM.

MATERIALS AND METHODS

The DL-based NLP model was developed by training long short-term memory using 1,749 free-text radiology reports written in Japanese. We adopted five-fold cross-validation and used 200 reports for testing the five models. The accuracy, sensitivity, specificity, precision, and area under the receiver operating characteristics curve (AUROC) were used for the model evaluation.

RESULTS

The developed model demonstrated classification performance with mean ± standard deviation of 0.912 ± 0.012, 0.924 ± 0.029, 0.901 ± 0.014, 0.898 ± 0.012, and 0.968 ± 0.004 for accuracy, sensitivity, specificity, precision, and AUROC, respectively.

CONCLUSION

The proposed DL-based NLP model may help in the early and efficient detection of patients with BM.

Machine Learning in Clinical Trials: A Primer with Applications to Neurology

We reviewed foundational concepts in artificial intelligence (AI) and machine learning (ML) and discussed ways in which these methodologies may be employed to enhance progress in clinical trials and research, with particular attention to applications in the design, conduct, and interpretation of clinical trials for neurologic diseases. We discussed ways in which ML may help to accelerate the pace of subject recruitment, provide realistic simulation of medical interventions, and enhance remote trial administration via novel digital biomarkers and therapeutics. Lastly, we provide a brief overview of the technical, administrative, and regulatory challenges that must be addressed as ML achieves greater integration into clinical trial workflows.

Artificial Intelligence Applied to clinical trials: opportunities and challenges

Background

Clinical Trials (CTs) remain the foundation of safe and effective drug development. Given the evolving data-driven and personalized medicine approach in healthcare, it is imperative for companies and regulators to utilize tailored Artificial Intelligence (AI) solutions that enable expeditious and streamlined clinical research. In this paper, we identified opportunities, challenges, and potential implications of AI in CTs.

Methods

Following an extensive search in relevant databases and websites, we gathered publications tackling the use of AI and Machine Learning (ML) in CTs from the past 5 years in the US and Europe, including Regulatory Authorities' documents.

Results

Documented applications of AI commonly concern the oncology field and are mostly being applied in the area of recruitment. Main opportunities discussed aim to create efficiencies across CT activities, including the ability to reduce sample sizes, improve enrollment and conduct faster, more optimized adaptive CTs. While AI is an area of enthusiastic development, the identified challenges are ethical in nature and relate to data availability, standards, and most importantly, lack of regulatory guidance hindering the acceptance of AI tools in drug development. However, future implications are significant and are anticipated to improve the probability of success, reduce trial burden and overall, speed up research and regulatory approval.

Conclusion

The use of AI in CTs is in its relative infancy; however, it is a fast-evolving field. As regulators provide more guidance on the acceptability of AI in specific areas, we anticipate the scope of use to broaden and the volume of implementation to increase rapidly.

Natural Language Processing for Automated Classification of Qualitative Data From Interviews of Patients With Cancer

OBJECTIVES

This study sought to explore the use of novel natural language processing (NLP) methods for classifying unstructured, qualitative textual data from interviews of patients with cancer to identify patient-reported symptoms and impacts on quality of life.

METHODS

We tested the ability of 4 NLP models to accurately classify text from interview transcripts as "symptom," "quality of life impact," and "other." Interview data sets from patients with hepatocellular carcinoma (HCC) (n = 25), biliary tract cancer (BTC) (n = 23), and gastric cancer (n = 24) were used. Models were cross-validated with transcript subsets designated for training, validation, and testing. Multiclass classification performance of the 4 models was evaluated at paragraph and sentence level using the HCC testing data set and analyzed by the one-versus-rest technique quantified by the receiver operating characteristic area under the curve (ROC AUC) score.

RESULTS

NLP models accurately classified multiclass text from patient interviews. The Bidirectional Encoder Representations from Transformers model generally outperformed all other models at paragraph and sentence level. The highest predictive performance of the Bidirectional Encoder Representations from Transformers model was observed using the HCC data set to train and BTC data set to test (mean ROC AUC, 0.940 [SD 0.028]), with similarly high predictive performance using balanced and imbalanced training data sets from BTC and gastric cancer populations.

CONCLUSIONS

NLP models were accurate in predicting multiclass classification of text from interviews of patients with cancer, with most surpassing 0.9 ROC AUC at paragraph level. NLP may be a useful tool for scaling up processing of patient interviews in clinical studies and, thus, could serve to facilitate patient input into drug development and improving patient care.

A comparative study of pre-trained language models for named entity recognition in clinical trial eligibility criteria from multiple corpora

Background

Clinical trial protocols are the foundation for advancing medical sciences, however, the extraction of accurate and meaningful information from the original clinical trials is very challenging due to the complex and unstructured texts of such documents. Named entity recognition (NER) is a fundamental and necessary step to process and standardize the unstructured text in clinical trials using Natural Language Processing (NLP) techniques.

Methods

In this study we fine-tuned pre-trained language models to support the NER task on clinical trial eligibility criteria. We systematically investigated four pre-trained contextual embedding models for the biomedical domain (i.e., BioBERT, BlueBERT, PubMedBERT, and SciBERT) and two models for the open domains (BERT and SpanBERT), for NER tasks using three existing clinical trial eligibility criteria corpora. In addition, we also investigated the feasibility of data augmentation approaches and evaluated their performance.

Results

Our evaluation results using tenfold cross-validation show that domain-specific transformer models achieved better performance than the general transformer models, with the best performance obtained by the PubMedBERT model (F1-scores of 0.715, 0.836, and 0.622 for the three corpora respectively). The data augmentation results show that it is feasible to leverage additional corpora to improve NER performance.

Conclusions

Findings from this study not only demonstrate the importance of contextual embeddings trained from domain-specific corpora, but also shed lights on the benefits of leveraging multiple data sources for the challenging NER task in clinical trial eligibility criteria text.

ELaPro, a LOINC-mapped core dataset for top laboratory procedures of eligibility screening for clinical trials

Background

Screening for eligible patients continues to pose a great challenge for many clinical trials. This has led to a rapidly growing interest in standardizing computable representations of eligibility criteria (EC) in order to develop tools that leverage data from electronic health record (EHR) systems. Although laboratory procedures (LP) represent a common entity of EC that is readily available and retrievable from EHR systems, there is a lack of interoperable data models for this entity of EC. A public, specialized data model that utilizes international, widely-adopted terminology for LP, e.g. Logical Observation Identifiers Names and Codes (LOINC®), is much needed to support automated screening tools.

Objective

The aim of this study is to establish a core dataset for LP most frequently requested to recruit patients for clinical trials using LOINC terminology. Employing such a core dataset could enhance the interface between study feasibility platforms and EHR systems and significantly improve automatic patient recruitment.

Methods

We used a semi-automated approach to analyze 10,516 screening forms from the Medical Data Models (MDM) portal’s data repository that are pre-annotated with Unified Medical Language System (UMLS). An automated semantic analysis based on concept frequency is followed by an extensive manual expert review performed by physicians to analyze complex recruitment-relevant concepts not amenable to automatic approach.

Results

Based on analysis of 138,225 EC from 10,516 screening forms, 55 laboratory procedures represented 77.87% of all UMLS laboratory concept occurrences identified in the selected EC forms. We identified 26,413 unique UMLS concepts from 118 UMLS semantic types and covered the vast majority of Medical Subject Headings (MeSH) disease domains.

Conclusions

Only a small set of common LP covers the majority of laboratory concepts in screening EC forms which supports the feasibility of establishing a focused core dataset for LP. We present ELaPro, a novel, LOINC-mapped, core dataset for the most frequent 55 LP requested in screening for clinical trials. ELaPro is available in multiple machine-readable data formats like CSV, ODM and HL7 FHIR. The extensive manual curation of this large number of free-text EC as well as the combining of UMLS and LOINC terminologies distinguishes this specialized dataset from previous relevant datasets in the literature.

Supplementary Information

The online version contains supplementary material available at 10.1186/s12874-022-01611-y.

How can natural language processing help model informed drug development?: a review

Objective

To summarize applications of natural language processing (NLP) in model informed drug development (MIDD) and identify potential areas of improvement.

Materials and Methods

Publications found on PubMed and Google Scholar, websites and GitHub repositories for NLP libraries and models. Publications describing applications of NLP in MIDD were reviewed. The applications were stratified into 3 stages: drug discovery, clinical trials, and pharmacovigilance. Key NLP functionalities used for these applications were assessed. Programming libraries and open-source resources for the implementation of NLP functionalities in MIDD were identified.

Results

NLP has been utilized to aid various processes in drug development lifecycle such as gene-disease mapping, biomarker discovery, patient-trial matching, adverse drug events detection, etc. These applications commonly use NLP functionalities of named entity recognition, word embeddings, entity resolution, assertion status detection, relation extraction, and topic modeling. The current state-of-the-art for implementing these functionalities in MIDD applications are transformer models that utilize transfer learning for enhanced performance. Various libraries in python, R, and Java like huggingface, sparkNLP, and KoRpus as well as open-source platforms such as DisGeNet, DeepEnroll, and Transmol have enabled convenient implementation of NLP models to MIDD applications.

Discussion

Challenges such as reproducibility, explainability, fairness, limited data, limited language-support, and security need to be overcome to ensure wider adoption of NLP in MIDD landscape. There are opportunities to improve the performance of existing models and expand the use of NLP in newer areas of MIDD.

Conclusions

This review provides an overview of the potential and pitfalls of current NLP approaches in MIDD.

Musculoskeletal care - at the confluence of data science, sensors, engineering, and computation

Data has always been integral to modern medicine in almost all aspects of patient care and the recent proliferation of data has opened up innumerable opportunities for all the stakeholders in trying to improve the quality of care and health outcomes including quality of life and rehabilitation. Greater usage and adoption of digital technologies have led to the convergence of health data in different forms – clinical, self-reported, electronic health records social media, etc. The application and utilization of patient data set continue to get broadened each day with greater availability and access. These are empowering newer cutting-edge solutions such as connected care and artificial intelligence, 3D printing and real-life mimicking prosthetics. The availability of data at micro and macro levels has the potential to act as a catalyst for personalized care based on behavioral, cultural, genetic, and psychological needs for patients with musculoskeletal disorders. Realistic algorithms coupled with biomarkers which can identify relevant interventions and alert the care providers regarding any deterioration. Although in the nascent stage currently, 3D printing, exoskeletons, and virtual rehabilitation hold tremendous potential of cost-effective, precise interventions for the patients.

Automated NLP Extraction of Clinical Rationale for Treatment Discontinuation in Breast Cancer

PURPOSE

Key oncology end points are not routinely encoded into electronic medical records (EMRs). We assessed whether natural language processing (NLP) can abstract treatment discontinuation rationale from unstructured EMR notes to estimate toxicity incidence and progression-free survival (PFS).

METHODS

We constructed a retrospective cohort of 6,115 patients with early-stage and 701 patients with metastatic breast cancer initiating care at Memorial Sloan Kettering Cancer Center from 2008 to 2019. Each cohort was divided into training (70%), validation (15%), and test (15%) subsets. Human abstractors identified the clinical rationale associated with treatment discontinuation events. Concatenated EMR notes were used to train high-dimensional logistic regression and convolutional neural network models. Kaplan-Meier analyses were used to compare toxicity incidence and PFS estimated by our NLP models to estimates generated by manual labeling and time-to-treatment discontinuation (TTD).

RESULTS

Our best high-dimensional logistic regression models identified toxicity events in early-stage patients with an area under the curve of the receiver-operator characteristic of 0.857 ± 0.014 (standard deviation) and progression events in metastatic patients with an area under the curve of 0.752 ± 0.027 (standard deviation). NLP-extracted toxicity incidence and PFS curves were not significantly different from manually extracted curves (P = .95 and P = .67, respectively). By contrast, TTD overestimated toxicity in early-stage patients (P < .001) and underestimated PFS in metastatic patients (P < .001). Additionally, we tested an extrapolation approach in which 20% of the metastatic cohort were labeled manually, and NLP algorithms were used to abstract the remaining 80%. This extrapolated outcomes approach resolved PFS differences between receptor subtypes (P < .001 for hormone receptor+/human epidermal growth factor receptor 2- v human epidermal growth factor receptor 2+ v triple-negative) that could not be resolved with TTD.

CONCLUSION

NLP models are capable of abstracting treatment discontinuation rationale with minimal manual labeling.

Automated classification of clinical trial eligibility criteria text based on ensemble learning and metric learning

BACKGROUND

Eligibility criteria are the primary strategy for screening the target participants of a clinical trial. Automated classification of clinical trial eligibility criteria text by using machine learning methods improves recruitment efficiency to reduce the cost of clinical research. However, existing methods suffer from poor classification performance due to the complexity and imbalance of eligibility criteria text data.

METHODS

An ensemble learning-based model with metric learning is proposed for eligibility criteria classification. The model integrates a set of pre-trained models including Bidirectional Encoder Representations from Transformers (BERT), A Robustly Optimized BERT Pretraining Approach (RoBERTa), XLNet, Pre-training Text Encoders as Discriminators Rather Than Generators (ELECTRA), and Enhanced Representation through Knowledge Integration (ERNIE). Focal Loss is used as a loss function to address the data imbalance problem. Metric learning is employed to train the embedding of each base model for feature distinguish. Soft Voting is applied to achieve final classification of the ensemble model. The dataset is from the standard evaluation task 3 of 5th China Health Information Processing Conference containing 38,341 eligibility criteria text in 44 categories.

RESULTS

Our ensemble method had an accuracy of 0.8497, a precision of 0.8229, and a recall of 0.8216 on the dataset. The macro F1-score was 0.8169, outperforming state-of-the-art baseline methods by 0.84% improvement on average. In addition, the performance improvement had a p-value of 2.152e-07 with a standard t-test, indicating that our model achieved a significant improvement.

CONCLUSIONS

A model for classifying eligibility criteria text of clinical trials based on multi-model ensemble learning and metric learning was proposed. The experiments demonstrated that the classification performance was improved by our ensemble model significantly. In addition, metric learning was able to improve word embedding representation and the focal loss reduced the impact of data imbalance to model performance.

Semantic categorization of Chinese eligibility criteria in clinical trials using machine learning methods

BACKGROUND

Semantic categorization analysis of clinical trials eligibility criteria based on natural language processing technology is crucial for the task of optimizing clinical trials design and building automated patient recruitment system. However, most of related researches focused on English eligibility criteria, and to the best of our knowledge, there are no researches studied the Chinese eligibility criteria. Thus in this study, we aimed to explore the semantic categories of Chinese eligibility criteria.

METHODS

We downloaded the clinical trials registration files from the website of Chinese Clinical Trial Registry (ChiCTR) and extracted both the Chinese eligibility criteria and corresponding English eligibility criteria. We represented the criteria sentences based on the Unified Medical Language System semantic types and conducted the hierarchical clustering algorithm for the induction of semantic categories. Furthermore, in order to explore the classification performance of Chinese eligibility criteria with our developed semantic categories, we implemented multiple classification algorithms, include four baseline machine learning algorithms (LR, NB, kNN, SVM), three deep learning algorithms (CNN, RNN, FastText) and two pre-trained language models (BERT, ERNIE).

RESULTS

We totally developed 44 types of semantic categories, summarized 8 topic groups, and investigated the average incidence and prevalence in 272 hepatocellular carcinoma related Chinese clinical trials. Compared with the previous proposed categories in English eligibility criteria, 13 novel categories are identified in Chinese eligibility criteria. The classification result shows that most of semantic categories performed quite well, the pre-trained language model ERNIE achieved best performance with macro-average F1 score of 0.7980 and micro-average F1 score of 0.8484.

CONCLUSION

As a pilot study of Chinese eligibility criteria analysis, we developed the 44 semantic categories by hierarchical clustering algorithms for the first times, and validated the classification capacity with multiple classification algorithms.

Evaluating eligibility criteria of oncology trials using real-world data and AI

There is a growing focus on making clinical trials more inclusive but the design of trial eligibility criteria remains challenging^1-3. Here we systematically evaluate the effect of different eligibility criteria on cancer trial populations and outcomes with real-world data using the computational framework of Trial Pathfinder. We apply Trial Pathfinder to emulate completed trials of advanced non-small-cell lung cancer using data from a nationwide database of electronic health records comprising 61,094 patients with advanced non-small-cell lung cancer. Our analyses reveal that many common criteria, including exclusions based on several laboratory values, had a minimal effect on the trial hazard ratios. When we used a data-driven approach to broaden restrictive criteria, the pool of eligible patients more than doubled on average and the hazard ratio of the overall survival decreased by an average of 0.05. This suggests that many patients who were not eligible under the original trial criteria could potentially benefit from the treatments. We further support our findings through analyses of other types of cancer and patient-safety data from diverse clinical trials. Our data-driven methodology for evaluating eligibility criteria can facilitate the design of more-inclusive trials while maintaining safeguards for patient safety.

[Artificial intelligence based Chinese clinical trials eligibility criteria classification]

Subject recruitment is a key component that affects the progress and results of clinical trials, and generally conducted with eligibility criteria (includes inclusion criteria and exclusion criteria). The semantic category analysis of eligibility criteria can help optimizing clinical trials design and building automated patient recruitment system. This study explored the automatic semantic categories classification of Chinese eligibility criteria based on artificial intelligence by academic shared task. We totally collected 38 341 annotated eligibility criteria sentences and predefined 44 semantic categories. A total of 75 teams participated in competition, with 27 teams having submitted system outputs. Based on the results, we found out that most teams adopted mixed models. The mainstream resolution was applying pre-trained language models capable of providing rich semantic representation, which were combined with neural network models and used to fine-tune the models with reference to classifier tasks, and finally improved classification performance could be obtained by ensemble modeling. The best-performing system achieved a macro F1 score of 0.81 by using a pre-trained language model, i.e. bidirectional encoder representations from transformers (BERT) and ensemble modeling. With the error analysis we found out that from the point of data processing steps the data pre-processing and post-processing were very important for classification, while from the point of data volume these categories with less data volume showed lower classification performance. Finally, we hope that this study could provide a valuable dataset and state-of-the-art result for the research of Chinese medical short text classification.

Clinical Natural Language Processing for Radiation Oncology: A Review and Practical Primer

Natural language processing (NLP), which aims to convert human language into expressions that can be analyzed by computers, is one of the most rapidly developing and widely used technologies in the field of artificial intelligence. Natural language processing algorithms convert unstructured free text data into structured data that can be extracted and analyzed at scale. In medicine, this unlocking of the rich, expressive data within clinical free text in electronic medical records will help untap the full potential of big data for research and clinical purposes. Recent major NLP algorithmic advances have significantly improved the performance of these algorithms, leading to a surge in academic and industry interest in developing tools to automate information extraction and phenotyping from clinical texts. Thus, these technologies are poised to transform medical research and alter clinical practices in the future. Radiation oncology stands to benefit from NLP algorithms if they are appropriately developed and deployed, as they may enable advances such as automated inclusion of radiation therapy details into cancer registries, discovery of novel insights about cancer care, and improved patient data curation and presentation at the point of care. However, challenges remain before the full value of NLP is realized, such as the plethora of jargon specific to radiation oncology, nonstandard nomenclature, a lack of publicly available labeled data for model development, and interoperability limitations between radiation oncology data silos. Successful development and implementation of high quality and high value NLP models for radiation oncology will require close collaboration between computer scientists and the radiation oncology community. Here, we present a primer on artificial intelligence algorithms in general and NLP algorithms in particular; provide guidance on how to assess the performance of such algorithms; review prior research on NLP algorithms for oncology; and describe future avenues for NLP in radiation oncology research and clinics.

Identifying Patient Phenotype Cohorts Using Prehospital Electronic Health Record Data

Objective: Emergency medical services (EMS) provide critical interventions for patients with acute illness and injury and are important in implementing prehospital emergency care research. Retrospective, manual patient record review, the current reference-standard for identifying patient cohorts, requires significant time and financial investment. We developed automated classification models to identify eligible patients for prehospital clinical trials using EMS clinical notes and compared model performance to manual review.Methods: With eligibility criteria for an ongoing prehospital study of chest pain patients, we used EMS clinical notes (n = 1208) to manually classify patients as eligible, ineligible, and indeterminate. We randomly split these same records into training and test sets to develop and evaluate machine-learning (ML) algorithms using natural language processing (NLP) for feature (variable) selection. We compared models to the manual classification to calculate sensitivity, specificity, accuracy, positive predictive value, and F1 measure. We measured clinical expert time to perform review for manual and automated methods.Results: ML models' sensitivity, specificity, accuracy, positive predictive value, and F1 measure ranged from 0.93 to 0.98. Compared to manual classification (N = 363 records), the automated method excluded 90.9% of records as ineligible and leaving only 33 records for manual review.Conclusions: Our ML derived approach demonstrates the feasibility of developing a high-performing, automated classification system using EMS clinical notes to streamline the identification of a specific cardiac patient cohort. This efficient approach can be leveraged to facilitate prehospital patient-trial matching, patient phenotyping (i.e. influenza-like illness), and create prehospital patient registries.

Towards deep phenotyping pregnancy: a systematic review on artificial intelligence and machine learning methods to improve pregnancy outcomes

Objective

Development of novel informatics methods focused on improving pregnancy outcomes remains an active area of research. The purpose of this study is to systematically review the ways that artificial intelligence (AI) and machine learning (ML), including deep learning (DL), methodologies can inform patient care during pregnancy and improve outcomes.

Materials and methods

We searched English articles on EMBASE, PubMed and SCOPUS. Search terms included ML, AI, pregnancy and informatics. We included research articles and book chapters, excluding conference papers, editorials and notes.

Results

We identified 127 distinct studies from our queries that were relevant to our topic and included in the review. We found that supervised learning methods were more popular (n = 69) than unsupervised methods (n = 9). Popular methods included support vector machines (n = 30), artificial neural networks (n = 22), regression analysis (n = 17) and random forests (n = 16). Methods such as DL are beginning to gain traction (n = 13). Common areas within the pregnancy domain where AI and ML methods were used the most include prenatal care (e.g. fetal anomalies, placental functioning) (n = 73); perinatal care, birth and delivery (n = 20); and preterm birth (n = 13). Efforts to translate AI into clinical care include clinical decision support systems (n = 24) and mobile health applications (n = 9).

Conclusions

Overall, we found that ML and AI methods are being employed to optimize pregnancy outcomes, including modern DL methods (n = 13). Future research should focus on less-studied pregnancy domain areas, including postnatal and postpartum care (n = 2). Also, more work on clinical adoption of AI methods and the ethical implications of such adoption is needed.

Evaluation of patient-level retrieval from electronic health record data for a cohort discovery task

OBJECTIVE

Growing numbers of academic medical centers offer patient cohort discovery tools to their researchers, yet the performance of systems for this use case is not well understood. The objective of this research was to assess patient-level information retrieval methods using electronic health records for different types of cohort definition retrieval.

MATERIALS AND METHODS

We developed a test collection consisting of about 100 000 patient records and 56 test topics that characterized patient cohort requests for various clinical studies. Automated information retrieval tasks using word-based approaches were performed, varying 4 different parameters for a total of 48 permutations, with performance measured using B-Pref. We subsequently created structured Boolean queries for the 56 topics for performance comparisons. In addition, we performed a more detailed analysis of 10 topics.

RESULTS

The best-performing word-based automated query parameter settings achieved a mean B-Pref of 0.167 across all 56 topics. The way a topic was structured (topic representation) had the largest impact on performance. Performance not only varied widely across topics, but there was also a large variance in sensitivity to parameter settings across the topics. Structured queries generally performed better than automated queries on measures of recall and precision but were still not able to recall all relevant patients found by the automated queries.

CONCLUSION

While word-based automated methods of cohort retrieval offer an attractive solution to the labor-intensive nature of this task currently used at many medical centers, we generally found suboptimal performance in those approaches, with better performance obtained from structured Boolean queries. Future work will focus on using the test collection to develop and evaluate new approaches to query structure, weighting algorithms, and application of semantic methods.

Secret groups and open forums: Defining online support communities from the perspective of people affected by cancer

Objective

A quarter of people diagnosed with cancer lack social support. Online cancer communities could allow people to connect and support one another. However, the current proliferation of online support communities constitutes a range of online environments with differing communication capacities and limitations. It is unclear what is perceived as online cancer community support and how different features can help or hinder supportive group processes. This study aimed to explore how perceived support is influenced by the different features and formats of online support environments.

Methods

In-depth qualitative interviews were conducted with 23 individuals affected by a range of cancer diagnoses, including both cancer survivors and family members. Data were analysed using deductive thematic analysis guided by a constructivist epistemological perspective.

Findings

Online supportive communities were defined and differentiated by two themes. Firstly, ‘Open forums’ were identified with thematic properties which facilitated a uniquely informative environment including ‘Safety in anonymity’, ‘Perceived reliability’ and ‘Exposure and detachment’. Secondly, ‘Secret groups’ were identified with thematic properties which enhanced an emotionally supportive environment including ‘Personalised interactions’, an overt ‘Peer hierarchy’, and ‘Crossing the virtual divide’.

Conclusions

Properties of groups can engender different degrees of interpersonal relations and different supportive interactions. In particular, support community designers may want to adapt key features such as anonymity, trustworthiness of websites, and the personalised nature of conversations to influence the development of supportive environments. In personalised peer-led groups, it may be prudent to provide guidance on how to reassert a positive environment if arguments break out online.

Data Mining of the Reviews from Online Private Doctors

Background: User-generated content shared in the online health communities (OHCs) is becoming a valuable resource for researchers to understand patients' decision-making behaviors in the management of their health. Many studies have focused on how to obtain useful information from online reviews in OHCs. Introduction: This study focuses on a telemedicine service called Online Private Doctor (OPD), which is offered by a leading Chinese physician review website (PRW). OPD reviews have not received much attention. By data mining the reviews, our goal is to determine what patients are talking about when they use the OPD service and whether they are satisfied with the service or not. Materials and Methods: We used a Python web crawler to collect 41,029 reviews and 84,510 short reviews (labels) of all 5,645 physicians who offered the OPD service on a PRW (haodf.com) in China. Mixed methods (i.e., a literature review, topic discovery, annotation, and a sentiment analysis) were used to determine the information that the OPD reviews are meant to express. Results: We discovered that the OPD reviews can be categorized into four subjects: competence (35.1%), communication (29.4%), treatment (26.0%), and convenience (9.5%). In terms of previously discovered topics, we found that competence, communication, and treatment have been discussed before, but convenience is an emerging subject. The sentiment analysis indicated that 93.67% of the reviews indicated positive emotions, and the area under the receiver operating characteristic (ROC) curve is 0.64. Furthermore, the labels indicated that only 0.72% (603/84,570) of reviews were negative toward the OPD service. The subjects of the labels were distributed according to competence (34.7%), communication (23.8%), treatment (33.5%), and convenience (8.0%). Discussion: The findings of our study suggest that patients who ever used OPD have been quite satisfied with the service. From their reviews, we discovered that OPD has its special characteristics and is convenient. However, it still has some shortcomings, for example, the quality of the phone connection. In terms of both the platform and the doctors, more efforts should be made to make the OPD better and more regulated. Conclusion: OPD is an emerging telemedicine service that still needs more time and space to evolve. For patients, it helps reduce problems such as scheduling and queuing. Therefore, it brings more convenience to people's daily lives. In the future, more attention should be paid to this service, as it is helpful in reducing the uneven distribution of medical resources.

Use of Natural Language Processing to Extract Clinical Cancer Phenotypes from Electronic Medical Records

Current models for correlating electronic medical records with -omics data largely ignore clinical text, which is an important source of phenotype information for patients with cancer. This data convergence has the potential to reveal new insights about cancer initiation, progression, metastasis, and response to treatment. Insights from this real-world data will catalyze clinical care, research, and regulatory activities. Natural language processing (NLP) methods are needed to extract these rich cancer phenotypes from clinical text. Here, we review the advances of NLP and information extraction methods relevant to oncology based on publications from PubMed as well as NLP and machine learning conference proceedings in the last 3 years. Given the interdisciplinary nature of the fields of oncology and information extraction, this analysis serves as a critical trail marker on the path to higher fidelity oncology phenotypes from real-world data.

Learning Eligibility in Cancer Clinical Trials Using Deep Neural Networks

Interventional cancer clinical trials are generally too restrictive, and some patients are often excluded on the basis of comorbidity, past or concomitant treatments, or the fact that they are over a certain age. The efficacy and safety of new treatments for patients with these characteristics are, therefore, not defined. In this work, we built a model to automatically predict whether short clinical statements were considered inclusion or exclusion criteria. We used protocols from cancer clinical trials that were available in public registries from the last 18 years to train word-embeddings, and we constructed a dataset of 6M short free-texts labeled as eligible or not eligible. A text classifier was trained using deep neural networks, with pre-trained word-embeddings as inputs, to predict whether or not short free-text statements describing clinical information were considered eligible. We additionally analyzed the semantic reasoning of the word-embedding representations obtained and were able to identify equivalent treatments for a type of tumor analogous with the drugs used to treat other tumors. We show that representation learning using deep neural networks can be successfully leveraged to extract the medical knowledge from clinical trial protocols for potentially assisting practitioners when prescribing treatments.

Using Self-Reported Patient Experiences to Understand Patient Burden: Learnings from Digital Patient Communities in Ankylosing Spondylitis

Introduction

Online communities contain a wealth of information containing unsolicited patient experiences that may go beyond what is captured by guided surveys or patient-reported outcome (PRO) instruments used in clinical settings. This study described patient experiences reported online to better understand the day-to-day disease burden of ankylosing spondylitis (AS).

Methods

Unguided, English-language patient narratives reported between January 2010 and May 2016 were collected from 52 online sources (e.g., general/health social networking sites, patient–physician Q&A sites, AS forums). Using natural language processing combined with manual curation, patient-reported experiences within narratives were evaluated and categorized into social, physical, emotional, cognitive, and role activity (SPEC-R) concepts to assess functional impairment. The same SPEC-R categorization was applied to 5 AS-specific PRO instruments to evaluate their coverage of concepts extracted from patient narratives.

Results

A total of 34,780 narratives from 3449 patients with AS were included. Physical aspects of AS (e.g., pain and mobility) were most commonly reported by patients (86.7%), followed by emotional (32.5%), cognitive (23.6%), role activity (8.7%) and social (5.1%). Some frequently discussed subconcepts were effectively captured by ≥ 2 PRO instruments, such as pain (65.3%), asthenia (19.9%), musculoskeletal impairment (19.9%), depression (9.9%), and anger/frustration (5.4%); others [e.g., anxiety (19.1%), mental impairment (3.2%), impulsivity (2.9%)] were not addressed by any of the PRO instruments.

Conclusion

These findings highlight the importance of analyzing patient experiences beyond clinical trial settings and physician reports; continuous assessment of existing PRO instruments in collaboration with patients may increase their utility in real-world settings.

Funding

Novartis Pharmaceuticals Corporation.

Electronic supplementary material

The online version of this article (10.1007/s12325-018-0669-1) contains supplementary material, which is available to authorized users.