Electronic health records include information on patients' status and medical history, which could cover the history of diseases and disorders that could be hereditary. One important use of family history information is in precision health, where the goal is to keep the population healthy with preventative measures. Natural Language Processing (NLP) and machine learning techniques can assist with identifying information that could assist health professionals in identifying health risks before a condition is developed in their later years, saving lives and reducing healthcare costs.
We survey the literature on the techniques from the NLP field that have been developed to utilise digital health records to identify risks of familial diseases. We highlight that rule-based methods are heavily investigated and are still actively used for family history extraction. Still, more recent efforts have been put into building neural models based on large-scale pre-trained language models. In addition to the areas where NLP has successfully been utilised, we also identify the areas where more research is needed to unlock the value of patients' records regarding data collection, task formulation and downstream applications.
A Dataset and Resources for Identifying Patient Health Literacy Information from Clinical Notes
National Library of Medicine(国家医学图书馆);Massachusetts Institute of Technology(麻省理工学院);Yonsei University College of Medicine(延世大学医学院);Beth Israel Deaconess Medical Center(贝斯以色列医疗中心);NYC Health + Hospitals - Lincoln(纽约市卫生局-林肯医院)
Extracting Social Determinants of Health from Pediatric Patient Notes Using Large Language Models: Novel Corpus and Methods
University of Washington(华盛顿大学);George Mason University(乔治梅森大学);Dana-Farber Cancer Institute(达纳-法伯癌症研究所);Boston Children's Hospital(波士顿儿童医院);Harvard Medical School(哈佛医学院)
Mining Social Determinants of Health for Heart Failure Patient 30-Day Readmission via Large Language Model
Department of Computer Science, Emory University(计算机科学系,埃默里大学);Nell Hodgson Woodruff School of Nursing, Emory University(Nell Hodgson Woodruff护理学院,埃默里大学)
Identifying physical health comorbidities in a cohort of individuals with severe mental illness: An application of SemEHR
NIHR Biomedical Research Centre at South London and Maudsley NHS Foundation Trust and King’s College London(英国国立卫生研究院生物医学研究中心(位于南伦敦和莫兹利 NHS 基金会信托及伦敦国王学院));University of Edinburgh(爱丁堡大学);University College London(伦敦大学学院)
Identifying Mentions of Pain in Mental Health Records Text: A Natural Language Processing Approach
Institute of Psychiatry, Psychology and Neurosciences, King’s College London(伦敦国王学院精神病学、心理学与神经科学研究所);Health Data Research UK(英国健康数据研究中心);South London and Maudsley Biomedical Research Centre(南伦敦和莫兹利生物医学研究中心);The South London and Maudsley NHS Foundation Trust(南伦敦和莫兹利国民保健信托基金会)
Frame Semantic Patterns for Identifying Underreporting of Notifiable Events in Healthcare: The Case of Gender-Based Violence
Federal University of Juiz de Fora(联邦大学-巴西吉尔兹德福拉);FrameNet Brasil(FrameNet巴西);University of Gothenburg(哥德堡大学);Vital Strategies Brasil(Vital Strategies巴西);Federal University of Minas Gerais(巴西矿务联邦大学);Brazilian National Council for Scientific and Technological Development – CNPq(巴西科学和技术发展国家委员会–CNPq)
Identifying Depressive Symptoms from Tweets: Figurative Language Enabled Multitask Learning Framework
LHNCBC, U.S. National Library of Medicine(美国国家医学图书馆 LHNCBC);Indian Institute of Technology Gandhinagar(印度理工学院甘地讷格尔分校);Wright State University(莱特州立大学);University of South Carolina(南卡罗来纳大学)
An NLP Solution to Foster the Use of Information in Electronic Health Records for Efficiency in Decision-Making in Hospital Care
Centro Hospitalar Universitário de São João(圣若昂大学医院中心);Faculdade de Medicina da Universidade do Porto(波尔图大学医学院);Priberam;Instituto de Saúde Pública da Universidade do Porto(波尔图大学公共卫生研究所)
How Much User Context Do We Need? Privacy by Design in Mental Health NLP Application
University of Marburg(马尔堡大学);Technical University of Darmstadt(达姆施塔特工业大学);Georgia Institute of Technology(佐治亚理工学院);Manipal Institute of Technology(马尼帕尔理工学院)