Using Machine Learning and Natural Language Processing to Review and Classify the Medical Literature on Cancer Susceptibility Genes

Dysphagia in Parkinson's disease: A bibliometric and visualization analysis from 2002 to 2022

Background

Dysphagia, or difficulty swallowing, is a prevalent complication of Parkinson's disease (PD), which can significantly impair quality of life. Despite the numerous studies on dysphagia in PD published in various journals, there remains a dearth of bibliometric analysis within this domain. This study thus aims to examine the global patterns of research on dysphagia after PD over the past 20 years, employing a visual analysis.

Material and methods

This investigation aimed to gather pertinent publications concerning dysphagia in PD from the SCI-Expanded database of the Web of Science Core Collection (WoSCC), covering the period from 2002 to 2022. To dissect and visually represent the collated corpus, we harnessed the capacities of CiteSpace, VOSviewer and R software for meticulous bibliometric scrutiny.

Results

The bibliometric study encompassed a total of 692 publications. Within the scope of autocratic nations, the USA emerged as the leading country in the quantity of research outputs. The University of Florida stood out as the most prolific academic entity, with Troche MS being the foremost author, contributing to 21 publications. The journal "Dysphagia" featured as the prime venue for publication. Key trending terms identified over the last 20 years include "Parkinson's disease," "dysphagia," "oropharyngeal dysphagia," and "prevalence."

Conclusion

Bibliometric analysis on dysphagia in PD offers a detailed overview of the development of scholarly publications, enabling scholars to grasp the current state of research within their field. It also serves as a benchmark for shaping future research directions.

BIR: Biomedical Information Retrieval System for Cancer Treatment in Electronic Health Record Using Transformers

The rapid growth of electronic health records (EHRs) has led to unprecedented biomedical data. Clinician access to the latest patient information can improve the quality of healthcare. However, clinicians have difficulty finding information quickly and easily due to the sheer data mining volume. Biomedical information retrieval (BIR) systems can help clinicians find the information required by automatically searching EHRs and returning relevant results. However, traditional BIR systems cannot understand the complex relationships between EHR entities. Transformers are a new type of neural network that is very effective for natural language processing (NLP) tasks. As a result, transformers are well suited for tasks such as machine translation and text summarization. In this paper, we propose a new BIR system for EHRs that uses transformers for predicting cancer treatment from EHR. Our system can understand the complex relationships between the different entities in an EHR, which allows it to return more relevant results to clinicians. We evaluated our system on a dataset of EHRs and found that it outperformed state-of-the-art BIR systems on various tasks, including medical question answering and information extraction. Our results show that Transformers are a promising approach for BIR in EHRs, reaching an accuracy and an F1-score of 86.46%, and 0.8157, respectively. We believe that our system can help clinicians find the information they need more quickly and easily, leading to improved patient care.

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.

The use of artificial intelligence for automating or semi-automating biomedical literature analyses: a scoping review

OBJECTIVE

Evidence-based medicine (EBM) is a decision-making process based on the conscious and judicious use of the best available scientific evidence. However, the exponential increase in the amount of information currently available likely exceeds the capacity of human-only analysis. In this context, artificial intelligence (AI) and its branches such as machine learning (ML) can be used to facilitate human efforts in analyzing the literature to foster EBM. The present scoping review aimed to examine the use of AI in the automation of biomedical literature survey and analysis with a view to establishing the state-of-the-art and identifying knowledge gaps.

MATERIALS AND METHODS

Comprehensive searches of the main databases were performed for articles published up to June 2022 and studies were selected according to inclusion and exclusion criteria. Data were extracted from the included articles and the findings categorized.

RESULTS

The total number of records retrieved from the databases was 12,145, of which 273 were included in the review. Classification of the studies according to the use of AI in evaluating the biomedical literature revealed three main application groups, namely assembly of scientific evidence (n=127; 47%), mining the biomedical literature (n=112; 41%) and quality analysis (n=34; 12%). Most studies addressed the preparation of systematic reviews, while articles focusing on the development of guidelines and evidence synthesis were the least frequent. The biggest knowledge gap was identified within the quality analysis group, particularly regarding methods and tools that assess the strength of recommendation and consistency of evidence.

CONCLUSION

Our review shows that, despite significant progress in the automation of biomedical literature surveys and analyses in recent years, intense research is needed to fill knowledge gaps on more difficult aspects of ML, deep learning and natural language processing, and to consolidate the use of automation by end-users (biomedical researchers and healthcare professionals).

Penetrance of Gastric Adenocarcinoma Susceptibility Genes: A Systematic Review

BACKGROUND

Gastric adenocarcinoma (GAC) is the fifth most common cancer in the world, and the presence of germline pathogenic variants has been linked with approximately 5% of gastric cancer diagnoses. Multiple GAC susceptibility genes have been identified, but information regarding the risk associated with pathogenic variants in these genes remains obscure. We conducted a systematic review of existing studies reporting the penetrance of GAC susceptibility genes.

METHODS

A structured search query was devised to identify GAC-related papers indexed in MEDLINE/PubMed. A semi-automated natural language processing algorithm was applied to identify penetrance papers for inclusion. Original studies reporting the penetrance of GAC were included and the full-text articles were independently reviewed. Summary statistics, effect estimates, and precision parameters from these studies were compiled into a table using a predetermined format to ensure consistency.

RESULTS

Forty-five studies were identified reporting the penetrance of GAC among patients harboring mutations in 13 different genes: APC, ATM, BRCA1, BRCA2, CDH1, CHEK2, MLH1, MSH2, MSH6, PMS2, MUTYH-Monoallelic, NBN, and STK11.

CONCLUSION

Our systematic review highlights the importance of testing for germline pathogenic variants in patients before the development of GAC. Management of patients who harbor a pathogenic mutation is multifactorial, and clinicians should consider cancer risk for each applicable gene-cancer association throughout the screening and management process. The scarcity of studies we found investigating the risk of GAC among patients with pathogenic variants in GAC susceptibility genes highlights the need for more investigations that focus on producing robust risk estimates for gene-cancer associations.

Bibliometric and visual analysis of intestinal ischemia reperfusion from 2004 to 2022

Background

Intestinal ischemia/reperfusion (I/R) injury is a common tissue-organ damage occurring in surgical practice. This study aims to comprehensively review the collaboration and impact of countries, institutions, authors, subject areas, journals, keywords, and critical literature on intestinal I/R injury from a bibliometric perspective, and to assess the evolution of clustering of knowledge structures and identify hot trends and emerging topics.

Methods

Articles and reviews related to intestinal I/R were retrieved through subject search from Web of Science Core Collection. Bibliometric analyses were conducted on Excel 365, CiteSpace, VOSviewer, and Bibliometrix (R-Tool of R-Studio).

Results

A total of 1069 articles and reviews were included from 2004 to 2022. The number of articles on intestinal I/R injury gradually plateaued, but the number of citations increased. These publications were mainly from 985 institutions in 46 countries, led by China and the United States. Liu Kx published the most papers, while Chiu Cj had the largest number of co-citations. Analysis of the journals with the most outputs showed that most journals focused on surgical sciences, cell biology, and immunology. Macroscopic sketch and microscopic characterization of the entire knowledge domain were achieved through co-citation analysis. The roles of cell death, exosomes, intestinal flora, and anesthetics in intestinal I/R injury are the current and developing research focuses. The keywords "dexmedetomidine", "proliferation", and "ferroptosis" may also become new trends and focus of future research.

Conclusion

This study comprehensively reviews the research on intestinal I/R injury using bibliometric and visualization methods, and will help scholars better understand the dynamic evolution of intestinal I/R injury and provide directions for future research.

Applications of Model-Based Meta-Analysis in Drug Development

Model-based meta-analysis (MBMA) is a quantitative approach that leverages published summary data along with internal data and can be applied to inform key drug development decisions, including the benefit-risk assessment of a treatment under investigation. These risk-benefit assessments may involve determining an optimal dose compared against historic external comparators of a particular disease indication. MBMA can provide a flexible framework for interpreting aggregated data from historic reference studies and therefore should be a standard tool for the model-informed drug development (MIDD) framework.In addition to pairwise and network meta-analyses, MBMA provides further contributions in the quantitative approaches with its ability to incorporate longitudinal data and the pharmacologic concept of dose-response relationship, as well as to combine individual- and summary-level data and routinely incorporate covariates in the analysis.A common application of MBMA is the selection of optimal dose and dosing regimen of the internal investigational molecule to evaluate external benchmarking and to support comparator selection. Two case studies provided examples in applications of MBMA in biologics (durvalumab + tremelimumab for safety) and small molecule (fenebrutinib for efficacy) to support drug development decision-making in two different but well-studied disease areas, i.e., oncology and rheumatoid arthritis, respectively.Important to the future directions of MBMA include additional recognition and engagement from drug development stakeholders for the MBMA approach, stronger collaboration between pharmacometrics and statistics, expanded data access, and the use of machine learning for database building. Timely, cost-effective, and successful application of MBMA should be part of providing an integrated view of MIDD.

Machine Learning Approach to Facilitate Knowledge Synthesis at the Intersection of Liver Cancer, Epidemiology, and Health Disparities Research

PURPOSE

Liver cancer is a global challenge, and disparities exist across multiple domains and throughout the disease continuum. However, liver cancer's global epidemiology and etiology are shifting, and the literature is rapidly evolving, presenting a challenge to the synthesis of knowledge needed to identify areas of research needs and to develop research agendas focusing on disparities. Machine learning (ML) techniques can be used to semiautomate the literature review process and improve efficiency. In this study, we detail our approach and provide practical benchmarks for the development of a ML approach to classify literature and extract data at the intersection of three fields: liver cancer, health disparities, and epidemiology.

METHODS

We performed a six-phase process including: training (I), validating (II), confirming (III), and performing error analysis (IV) for a ML classifier. We then developed an extraction model (V) and applied it (VI) to the liver cancer literature identified through PubMed. We present precision, recall, F1, and accuracy metrics for the classifier and extraction models as appropriate for each phase of the process. We also provide the results for the application of our extraction model.

RESULTS

With limited training data, we achieved a high degree of accuracy for both our classifier and for the extraction model for liver cancer disparities research literature performed using epidemiologic methods. The disparities concept was the most challenging to accurately classify, and concepts that appeared infrequently in our data set were the most difficult to extract.

CONCLUSION

We provide a roadmap for using ML to classify and extract comprehensive information on multidisciplinary literature. Our technique can be adapted and modified for other cancers or diseases where disparities persist.

Natural Language Processing to Identify Digital Learning Tools in Postgraduate Family Medicine: Protocol for a Scoping Review

Background

The COVID-19 pandemic has highlighted the growing need for digital learning tools in postgraduate family medicine training. Family medicine departments must understand and recognize the use and effectiveness of digital tools in order to integrate them into curricula and develop effective learning tools that fill gaps and meet the learning needs of trainees.

Objective

This scoping review will aim to explore and organize the breadth of knowledge regarding digital learning tools in family medicine training.

Methods

This scoping review follows the 6 stages of the methodological framework outlined first by Arksey and O’Malley, then refined by Levac et al, including a search of published academic literature in 6 databases (MEDLINE, ERIC, Education Source, Embase, Scopus, and Web of Science) and gray literature. Following title and abstract and full text screening, characteristics and main findings of the included studies and resources will be tabulated and summarized. Thematic analysis and natural language processing (NLP) will be conducted in parallel using a 9-step approach to identify common themes and synthesize the literature. Additionally, NLP will be employed for bibliometric and scientometric analysis of the identified literature.

Results

The search strategy has been developed and launched. As of October 2021, we have completed stages 1, 2, and 3 of the scoping review. We identified 132 studies for inclusion through the academic literature search and 127 relevant studies in the gray literature search. Further refinement of the eligibility criteria and data extraction has been ongoing since September 2021.

Conclusions

In this scoping review, we will identify and consolidate information and evidence related to the use and effectiveness of existing digital learning tools in postgraduate family medicine training. Our findings will improve the understanding of the current landscape of digital learning tools, which will be of great value to educators and trainees interested in using existing tools, innovators looking to design digital learning tools that meet current needs, and researchers involved in the study of digital tools.

Trial Registration

OSF Registries osf.io/wju4k; https://osf.io/wju4k

International Registered Report Identifier (IRRID)

DERR1-10.2196/34575

Research Landscape of Artificial Intelligence and e-Learning: A Bibliometric Research

While an increasing number of organizations have introduced artificial intelligence as an important facilitating tool for learning online, the application of artificial intelligence in e-learning has become a hot topic for research in recent years. Over the past few decades, the importance of online learning has also been a concern in many fields, such as technological education, STEAM, AR/VR apps, online learning, amongst others. To effectively explore research trends in this area, the current state of online learning should be understood. Systematic bibliometric analysis can address this problem by providing information on publishing trends and their relevance in various topics. In this study, the literary application of artificial intelligence combined with online learning from 2010 to 2021 was analyzed. In total, 64 articles were collected to analyze the most productive countries, universities, authors, journals and publications in the field of artificial intelligence combined with online learning using VOSviewer through WOS data collection. In addition, the mapping of co-citation and co-occurrence was explored by analyzing a knowledge map. The main objective of this study is to provide an overview of the trends and pathways in artificial intelligence and online learning to help researchers understand global trends and future research directions.

Twenty Years' Development of Teacher Identity Research: A Bibliometric Analysis

This study aims to demonstrate a detailed knowledge map of teacher identity research via a 20-year data set from the Web of Science (WoS) database. A bibliometric analysis was employed for analyzing the articles published between 2001 and 2021 to show the status of teacher identity research in the past 20 years, research topics on teacher identity, and future research directions. Using the keyword "teacher identity" and filtering data by selecting articles and early access in teaching and education, 848 articles were retrieved. Through production, content, and citation analysis with the help of a bibliometric tool, this study found that teacher identity remained a popular research theme in the academic field over the past 20 years, and its booming production involved many authors, institutions, and sources, and countries. Furthermore, teachers' "beliefs," "emotions," "professional development," and "context" impacting the construction and reconstruction of teacher identity were the popular topics in teacher identity research, and fundamental issues, including "identity," "teacher identity," "professional identity," "development," "teacher development," "beliefs," and "intersectionality" of teacher identity keep good topics in future research.

Application of Artificial Intelligence to Overcome Clinical Information Overload in Urologic Cancer

OBJECTIVE

To describe the use of artificial intelligence (AI) in medical literature and trial data extraction, and its applications in uro-oncology. This bridging review, which consolidates information from the diverse applications of AI, highlights how AI users can investigate more sophisticated queries than with traditional methods, leading to synthesis of raw data and complex outputs into more actionable and personalized results, particularly in the field of uro-oncology.

METHODS

Literature and clinical trial searches were performed in PubMed, Dimensions, Embase and Google (1999-2020). The searches focused on the use of AI and its various forms to facilitate literature searches, clinical guidelines development, and clinical trial data extraction in uro-oncology. To illustrate how AI can be applied toaddress questions about optimizing therapeutic decision making and individualizing treatment regimens, the Dimensions-linked information platform was searched for "prostate cancer" keywords (76 publications were identified; 48 were included).

RESULTS

AI offers the promise of transforming raw data and complex outputs into actionable insights. Literature and clinical trial searches can be automated, enabling clinicians to develop and analyze publications expeditiously on complex issues such as therapeutic sequencing and to obtain updates on documents that evolve at the pace and scope of the landscape. An AI-based platform inclusive of 12 trial databases and >100 scientific literature sources enabled the creation of an interactive visualization.

CONCLUSION

As the literature and clinical trial landscape continues to grow in complexity and with increasing speed, the ability to pull the right information at the right time from different search engines and resources while excluding social media bias becomes more challenging. This review demonstrates that by applying natural language processing and machine learning algorithms, validated and optimized AI leads to a speedier, more personalized, efficient and focused search compared with traditional methods.

Penetrance of male breast cancer susceptibility genes: a systematic review

PURPOSE

Several male breast cancer (MBC) susceptibility genes have been identified, but the MBC risk for individuals with a pathogenic variant in each of these genes (i.e., penetrance) remains unclear. We conducted a systematic review of studies reporting the penetrance of MBC susceptibility genes to better summarize current estimates of penetrance.

METHODS

A search query was developed to identify MBC-related papers indexed in PubMed/MEDLINE. A validated natural language processing method was applied to identify papers reporting penetrance estimates. These penetrance studies' bibliographies were reviewed to ensure comprehensiveness. We accessed the potential ascertainment bias for each enrolled study.

RESULTS

Fifteen penetrance studies were identified from 12,182 abstracts, covering five purported MBC susceptibility genes: ATM, BRCA1, BRCA2, CHEK2, and PALB2. Cohort (n = 6, 40%) and case-control (n = 5, 33%) studies were the two most common study designs, followed by family-based (n = 3, 20%), and a kin-cohort study (n = 1, 7%). Seven of the 15 studies (47%) adjusted for ascertainment adequately and therefore the MBC risks reported by these seven studies can be considered applicable to the general population. Based on these seven studies, we found pathogenic variants in ATM, BRCA2, CHEK2 c.1100delC, and PALB2 show an increased risk for MBC. The association between BRCA1 and MBC was not statistically significant.

CONCLUSION

This work supports the conclusion that pathogenic variants in ATM, BRCA2, CHEK2 c.1100delC, and PALB2 increase the risk of MBC, whereas pathogenic variants in BRCA1 may not be associated with increased MBC risk.

Search Behavior Regarding Cancer Susceptibility Genes Using a Clinical Decision Support Tool for Gene-Specific Penetrance: Content Analysis

BACKGROUND

Genetic testing for germline cancer susceptibility genes is widely available. The Ask2Me.org (All Syndromes Known to Man Evaluator) tool is a clinical decision support tool that provides evidence-based risk predictions for individuals with pathogenic variants in cancer susceptibility genes.

OBJECTIVE

The aim of this study was to understand the search behavior of the Ask2Me.org tool users, identify the patterns of queries entered, and discuss how to further improve the tool.

METHODS

We analyzed the Ask2Me.org user-generated queries collected between December 12, 2018, and October 8, 2019. The gene frequencies of the user-generated queries were compared with previously published panel testing data to assess the correspondence between usage and prevalence of pathogenic variants. The frequencies of prior cancer in the user-generated queries were compared with the most recent US population-based cancer incidence.

RESULTS

A total of 10,085 search queries were evaluated. The average age submitted in the queries was 48.8 (SD 16.5) years, and 84.1% (8478/10,085) of the submitted queries were for females. BRCA2 (1671/10,085, 16.6%), BRCA1 (1627/10,085, 16.1%), CHEK2 (994/10,085, 9.9%), ATM (662/10,085, 6.6%), and APC (492/10,085, 4.9%) were the top 5 genes searched by users. There was a strong linear correlation between genes queried by users and the frequency of pathogenic variants reported in published panel testing data (r=0.95, r2=0.90, P<.001). Over half of the queries (5343/10,085, 53.0%) included a prior personal history of cancer. The frequencies of prior cancers in the queries on females were strongly correlated with US cancer incidences (r=0.97, r2=0.95, P<.001), while the same correlation was weaker among the queries on males (r=0.69, r2=0.47, P=.02).

CONCLUSIONS

The patients entered in the Ask2Me.org tool are a representative cohort of patients with pathogenic variants in cancer susceptibility genes in the United States. While a majority of the queries were on breast cancer susceptibility genes, users also queried susceptibility genes with lower prevalence, which may represent a transformation from single gene testing to multigene panel testing. Owing to these changing tides, more efforts are needed to improve evidence-based clinical decision support tools to better aid clinicians and their practice.

Extracting Concepts for Precision Oncology from the Biomedical Literature

This paper describes an initial dataset and automatic natural language processing (NLP) method for extracting concepts related to precision oncology from biomedical research articles. We extract five concept types: Cancer, Mutation, Population, Treatment, Outcome. A corpus of 250 biomedical abstracts were annotated with these concepts following standard double-annotation procedures. We then experiment with BERT-based models for concept extraction. The best-performing model achieved a precision of 63.8%, a recall of 71.9%, and an F1 of 67.1. Finally, we propose additional directions for research for improving extraction performance and utilizing the NLP system in downstream precision oncology applications.

Disease Spectrum of Breast Cancer Susceptibility Genes

Background

Pathogenic variants in cancer susceptibility genes can increase the risk of a spectrum of diseases, which clinicians must manage for their patients. We evaluated the disease spectrum of breast cancer susceptibility genes (BCSGs) with the aim of developing a comprehensive resource of gene-disease associations for clinicians.

Methods

Twelve genes (ATM, BARD1, BRCA1, BRCA2, CDH1, CHEK2, NF1, PALB2, PTEN, RECQL, STK11, and TP53), all of which have been conclusively established as BCSGs by the Clinical Genome Resource (ClinGen) and/or the NCCN guidelines, were investigated. The potential gene-disease associations for these 12 genes were verified and evaluated based on six genetic resources (ClinGen, NCCN, OMIM, Genetics Home Reference, GeneCards, and Gene-NCBI) and an additional literature review using a semiautomated natural language processing (NLP) abstract classification procedure.

Results

Forty-two diseases were found to be associated with one or more of the 12 BCSGs for a total of 86 gene-disease associations, of which 90% (78/86) were verified by ClinGen and/or NCCN. Four gene-disease associations could not be verified by either ClinGen or NCCN but were verified by at least three of the other four genetic resources. Four gene-disease associations were verified by the NLP procedure alone.

Conclusion

This study is unique in that it systematically investigates the reported disease spectrum of BCSGs by surveying multiple genetic resources and the literature with the aim of developing a single consolidated, comprehensive resource for clinicians. This innovative approach provides a general guide for evaluating gene-disease associations for BCSGs, potentially improving the clinical management of at-risk individuals.

Disease spectrum of gastric cancer susceptibility genes

Pathogenic variants in germline cancer susceptibility genes can increase the risk of a large number of diseases. Our study aims to assess the disease spectrum of gastric cancer susceptibility genes and to develop a comprehensive resource of gene-disease associations for clinicians. Twenty-seven potential germline gastric cancer susceptibility genes were identified from three review articles and from six commonly used genetic information resources. The diseases associated with each gene were evaluated via a semi-structured review of six genetic resources and an additional literature review using a natural language processing (NLP)-based procedure. Out of 27 candidate genes, 13 were identified as gastric cancer susceptibility genes (APC, ATM, BMPR1A, CDH1, CHEK2, EPCAM, MLH1, MSH2, MSH6, MUTYH-Biallelic, PALB2, SMAD4, and STK11). A total of 145 gene-disease associations (with 45 unique diseases) were found to be associated with these 13 genes. Other gastrointestinal cancers were prominent among identified associations, with 11 of 13 gastric cancer susceptibility genes also associated with colorectal cancer, eight genes associated with pancreatic cancer, and seven genes associated with small intestine cancer. Gastric cancer susceptibility genes are frequently associated with other diseases as well as gastric cancer, with potential implications for how carriers of these genes are screened and managed. Unfortunately, commonly used genetic resources provide heterogeneous information with regard to these genes and their associated diseases, highlighting the importance of developing guides for clinicians that integrate data across available resources and the medical literature.

Non-medullary Thyroid Cancer Susceptibility Genes: Evidence and Disease Spectrum

BACKGROUND

The prevalence of non-medullary thyroid cancer (NMTC) is increasing worldwide. Although most NMTCs grow slowly, conventional therapies are less effective in advanced tumors. Approximately 5-15% of NMTCs have a significant germline genetic component. Awareness of the NMTC susceptibility genes may lead to earlier diagnosis and better cancer prevention.

OBJECTIVE

The aim of this study was to provide the current panorama of susceptibility genes associated with NMTC and the spectrum of diseases associated with these genes.

METHODS

Twenty-five candidate genes were identified by searching for relevant studies in PubMed. Each candidate gene was carefully checked using six authoritative genetic resources: ClinGen, National Comprehensive Cancer Network guidelines, Online Mendelian Inheritance in Man, Genetics Home Reference, GeneCards, and Gene-NCBI, and a validated natural language processing (NLP)-based literature review protocol was used to further assess gene-disease associations where there was ambiguity.

RESULTS

Among 25 candidate genes, 10 (APC, DICER1, FOXE1, HABP2, NKX2-1, PRKAR1A, PTEN, SDHB, SDHD, and SRGAP1) were verified among the six genetic resources. Two additional genes, CHEK2 and SEC23B, were verified using the NLP protocol. Seventy-nine diseases were found to be associated with these 12 NMTC susceptibility genes. The following diseases were associated with more than one NMTC susceptibility gene: colorectal cancer, breast cancer, gastric cancer, kidney cancer, gastrointestinal stromal tumor, paraganglioma, pheochromocytoma, and benign skin conditions.

CONCLUSION

Twelve genes predisposing to NMTC and their associated disease spectra were identified and verified. Clinicians should be aware that patients with certain pathogenic variants may require more aggressive surveillance beyond their thyroid cancer risk.

Artificial Intelligence Clinical Evidence Engine for Automatic Identification, Prioritization, and Extraction of Relevant Clinical Oncology Research

PURPOSE

We developed a system to automate analysis of the clinical oncology scientific literature from bibliographic databases and match articles to specific patient cohorts to answer specific questions regarding the efficacy of a treatment. The approach attempts to replicate a clinician's mental processes when reviewing published literature in the context of a patient case. We describe the system and evaluate its performance.

METHODS

We developed separate ground truth data sets for each of the tasks described in the paper. The first ground truth was used to measure the natural language processing (NLP) accuracy from approximately 1,300 papers covering approximately 3,100 statements and approximately 25 concepts; performance was evaluated using a standard F1 score. The ground truth for the expert classifier model was generated by dividing papers cited in clinical guidelines into a training set and a test set in an 80:20 ratio, and performance was evaluated for accuracy, sensitivity, and specificity.

RESULTS

The NLP models were able to identify individual attributes with a 0.7-0.9 F1 score, depending on the attribute of interest. The expert classifier machine learning model was able to classify the individual records with a 0.93 accuracy (95% CI, 0.9 to 0.96, P < .0001), and sensitivity and specificity of 0.95 and 0.91, respectively. Using a decision boundary of 0.5 for the positive (expert) label, the classifier demonstrated an F1 score of 0.92.

CONCLUSION

The system identified and extracted evidence from the oncology literature with a high degree of accuracy, sensitivity, and specificity. This tool enables timely access to the most relevant biomedical literature, providing critical support to evidence-based practice in areas of rapidly evolving science.

Predictive article recommendation using natural language processing and machine learning to support evidence updates in domain-specific knowledge graphs

Objectives

Describe an augmented intelligence approach to facilitate the update of evidence for associations in knowledge graphs.

Methods

New publications are filtered through multiple machine learning study classifiers, and filtered publications are combined with articles already included as evidence in the knowledge graph. The corpus is then subjected to named entity recognition, semantic dictionary mapping, term vector space modeling, pairwise similarity, and focal entity match to identify highly related publications. Subject matter experts review recommended articles to assess inclusion in the knowledge graph; discrepancies are resolved by consensus.

Results

Study classifiers achieved F-scores from 0.88 to 0.94, and similarity thresholds for each study type were determined by experimentation. Our approach reduces human literature review load by 99%, and over the past 12 months, 41% of recommendations were accepted to update the knowledge graph.

Conclusion

Integrated search and recommendation exploiting current evidence in a knowledge graph is useful for reducing human cognition load.

Penetrance of Colorectal Cancer Among Mismatch Repair Gene Mutation Carriers: A Meta-Analysis

Background

Lynch syndrome, the most common colorectal cancer (CRC) syndrome, is caused by germline mismatch repair (MMR) genes. Precise estimates of age-specific risks are crucial for sound counseling of individuals managing a genetic predisposition to cancer, but published risk estimates vary. The objective of this work is to provide gene-, sex-, and age-specific risk estimates of CRC for MMR mutation carriers that comprehensively reflect the best available data.

Methods

We conducted a meta-analysis to combine risk information from multiple studies on Lynch syndrome-associated CRC. We used a likelihood-based approach to integrate reported measures of CRC risk and deconvolved aggregated information to estimate gene- and sex-specific risk.

Results

Our comprehensive search identified 10 studies (8 on MLH1, 9 on MSH2, and 3 on MSH6). We estimated the cumulative risk of CRC by age and sex in heterozygous mutation carriers. At age 70 years, for male and female carriers, respectively, risks for MLH1 were 43.9% (95% confidence interval [CI] = 39.6% to 46.6%) and 37.3% (95% CI = 32.2% to 40.2%), for MSH2 were 53.9% (95% CI = 49.0% to 56.3%) and 38.6% (95% CI = 34.1% to 42.0%), and for MSH6 were 12.0% (95% CI = 2.4% to 24.6%) and 12.3% (95% CI = 3.5% to 23.2%).

Conclusions

Our results provide up-to-date and comprehensive age-specific CRC risk estimates for counseling and risk prediction tools. These will have a direct clinical impact by improving prevention and management strategies for both individuals who are MMR mutation carriers and those considering testing.

Natural language processing to facilitate breast cancer research and management

The medical literature has been growing exponentially, and its size has become a barrier for physicians to locate and extract clinically useful information. As a promising solution, natural language processing (NLP), especially machine learning (ML)-based NLP is a technology that potentially provides a promising solution. ML-based NLP is based on training a computational algorithm with a large number of annotated examples to allow the computer to "learn" and "predict" the meaning of human language. Although NLP has been widely applied in industry and business, most physicians still are not aware of the huge potential of this technology in medicine, and the implementation of NLP in breast cancer research and management is fairly limited. With a real-world successful project of identifying penetrance papers for breast and other cancer susceptibility genes, this review illustrates how to train and evaluate an NLP-based medical abstract classifier, incorporate it into a semiautomatic meta-analysis procedure, and validate the effectiveness of this procedure. Other implementations of NLP technology in breast cancer research, such as parsing pathology reports and mining electronic healthcare records, are also discussed. We hope this review will help breast cancer physicians and researchers to recognize, understand, and apply this technology to meet their own clinical or research needs.