scholarly journals Overview of the 2019 n2c2/OHNLP Track on Family History Extraction (Preprint)

2020 ◽  
Author(s):  
Feichen Shen ◽  
Sijia Liu ◽  
Sunyang Fu ◽  
Yanshan Wang ◽  
Samuel Henry ◽  
...  
Keyword(s):  
South Carolina ◽  
Family History ◽  
Mayo Clinic ◽  
Family Members ◽  
Relation Extraction ◽  
Shared Task ◽  
Clinical Observations ◽  
Clinical Narrative ◽  
Entity Identification ◽  
Institute Of Technology

BACKGROUND As a risk factor for many diseases, family history captures both shared genetic variations and living environments among family members. Though there are several systems focusing on family history extraction (FHE) using natural language processing (NLP) techniques, the evaluation protocol of such systems has not been standardized. OBJECTIVE The n2c2/OHNLP 2019 FHE Task aims to encourage the community efforts on a standard evaluation and system development on FHE from synthetic clinical narratives. METHODS We organized the first BioCreative/OHNLP FHE shared task in 2018. We continued the shared task in 2019 in collaboration with n2c2 and OHNLP consortium, and organized the 2019 n2c2/OHNLP FHE track. The shared task composes of two subtasks. Subtask 1 focuses on identifying family member entities and clinical observations (diseases), and Subtask 2 expects the association of the living status, side of the family and clinical observations to family members to be extracted. Subtask 2 is an end-to-end task which is based on the result of Subtask 1. We manually curated the first de-identified clinical narrative from family history sections of clinical notes at Mayo Clinic Rochester, the content of which are highly relevant to patients’ family history. RESULTS 17 teams from all over the world have participated in the n2c2/OHNLP FHE shared task, where 38 runs were submitted for subtask 1 and 21 runs were submitted for subtask 2. For subtask 1, the top three runs were generated by Harbin Institute of Technology, ezDI, Inc, and The Medical University of South Carolina with F1 scores of 0.8745, 0.8225, and 0.8130, respectively. For subtask 2, the top three runs were from Harbin Institute of Technology, ezDI, Inc, and University of Florida with F1 scores of 0.681, 0.6586, and 0.6544, respectively. The workshop was held in conjunction with the AMIA 2019 Fall Symposium. Conclusions: A wide variety of methods were used by different teams in both tasks, such as BERT, CNN, Bi-LSTM, CRF, SVM, and rule-based strategies. System performances show that relation extraction from family history is a more challenging task when compared to entity identification task. CONCLUSIONS We summarize the 2019 n2c2/OHNLP FHE shared task in this overview. In this task, we have developed a corpus using de-identified family history data stored in Mayo Clinic. The corpus we prepared along with the shared task have encouraged participants internationally to develop FHE systems for understanding clinical narratives. We compared the performance of valid systems on two subtasks: entity identification and relation extraction. The optimal F1 score for subtask 1 and subtask 2 is 0.8745 and 0.6810 respectively. We also observed that most of the typical errors made by the submitted systems are related to co-reference resolution. The corpus could be viewed as valuable resources for more researchers to improve systems for family history analysis. CLINICALTRIAL

scholarly journals Family History Extraction Using Deep Biaffine Attention (Preprint)

2020 ◽  
Author(s):  
Kecheng Zhan ◽  
Weihua Peng ◽  
Ying Xiong ◽  
Huhao Fu ◽  
Qingcai Chen ◽  
...  
Keyword(s):  
Family History ◽  
Information Extraction ◽  
Short Term Memory ◽  
Family Members ◽  
Relation Extraction ◽  
Disease Diagnosis ◽  
Entity Recognition ◽  
Shared Task ◽  
Family History Information ◽  
Clinical Text

BACKGROUND Family history (FH) information, including family members, side of family of family members, living status of family members, observations of family members, etc., plays a significant role in disease diagnosis and treatment. Family member information extraction aims to extract FH information from semi-structured/unstructured text in electronic health records (EHRs), which is a challenging task regarding named entity recognition (NER) and relation extraction (RE), where NE refers to family members, living status and observations, and relation refers to relations between family members and living status, and relations between family members and observations. OBJECTIVE This study aims to explore the ways to effectively extract family history information from clinical text. METHODS Inspired by dependency parsing, we design a novel graph-based schema to represent FH information and introduced deep biaffine attention to extract FH information in clinical text. In the deep biaffine attention model, we use CNN-BiLSTM (Convolutional Neural Network-Bidirectional Long Short Term Memory network) and BERT (Bidirectional Encoder Representation from Transformers) to encode input sentences, and deployed biaffine classifier to extract FH information. In addition, we also develop a post-processing module to adjust results. A system based on the proposed method was developed for the 2019 n2c2/OHNLP shared task track on FH information extraction, which includes two subtasks on entity recognition and relation extraction respectively. RESULTS We conduct experiments on the corpus provided by the 2019 n2c2/OHNLP shared task track on FH information extraction. Our system achieved the highest F1-scores of 0.8823 on subtask 1 and 0.7048 on subtask 2, respectively, new benchmark results on the 2019 n2c2/OHNLP corpus. CONCLUSIONS This study designed a novel Schema to represent FH information using graph and applied deep biaffine attention to extract FH information. Experimental results show the effectiveness of deep biaffine attention on FH information extraction.

scholarly journals Family history information extraction via deep joint learning

2019 ◽  
Vol 19 (S10) ◽  
Author(s):  
Xue Shi ◽  
Dehuan Jiang ◽  
Yuanhang Huang ◽  
Xiaolong Wang ◽  
Qingcai Chen ◽  
...  
Keyword(s):  
Family History ◽  
Language Processing ◽  
Family Members ◽  
Decision Making Process ◽  
Family History Information ◽  
Health Records ◽  
Joint Learning ◽  
Clinical Text ◽  
History Information ◽  
Entity Identification

Abstract Background Family history (FH) information, including family members, side of family of family members (i.e., maternal or paternal), living status of family members, observations (diseases) of family members, etc., is very important in the decision-making process of disorder diagnosis and treatment. However FH information cannot be used directly by computers as it is always embedded in unstructured text in electronic health records (EHRs). In order to extract FH information form clinical text, there is a need of natural language processing (NLP). In the BioCreative/OHNLP2018 challenge, there is a task regarding FH extraction (i.e., task1), including two subtasks: (1) entity identification, identifying family members and their observations (diseases) mentioned in clinical text; (2) family history extraction, extracting side of family of family members, living status of family members, and observations of family members. For this task, we propose a system based on deep joint learning methods to extract FH information. Our system achieves the highest F1- scores of 0.8901 on subtask1 and 0.6359 on subtask2, respectively.

scholarly journals A Hybrid Model for Entity Identification and Relation Extraction of Family History Information (Preprint)

2020 ◽  
Author(s):  
Youngjun Kim ◽  
Paul M Heider ◽  
Isabel R H Lally ◽  
Stéphane M Meystre
Keyword(s):  
Family History ◽  
Information Extraction ◽  
Relation Extraction ◽  
Free Text ◽  
Data Sets ◽  
Family History Information ◽  
Clinical Notes ◽  
History Information ◽  
End To End ◽  
Entity Identification

BACKGROUND Family history information is important to assess the risk of inherited medical conditions. Natural language processing has the potential to extract this information from unstructured free-text notes to improve patient care and decision-making. We describe the end-to-end information extraction system the Medical University of South Carolina team developed when participating in the 2019 n2c2/OHNLP shared task. OBJECTIVE This task involves identifying mentions of family members and observations in electronic health record text notes, and recognizing the relations between family members, observations, and living status. Our system aims to achieve a high level of performance by integrating heuristics and advanced information extraction methods. Our efforts also include improving the performance of two subtasks by exploiting additional labeled data and clinical text-based embedding models. METHODS We present a hybrid method that combines machine learning and rule-based approaches. We implemented an end-to-end system with multiple information extraction and attribute classification components. For entity identification, we trained bidirectional long short-term memory deep learning models. These models incorporated static word embeddings and context-dependent embeddings. We created a voting ensemble that combined the predictions of all individual models. For relation extraction, we trained two relation extraction models. The first model determined the living status of each family member. The second model identified observations associated with each family member. We implemented online gradient descent models to extract related entity pairs. As part of post-challenge efforts, we used the BioCreative/OHNLP 2018 corpus and trained new models with the union of these two data sets. We also pre-trained language models using clinical notes from the MIMIC-III clinical database. RESULTS The voting ensemble achieved better performance than individual classifiers. In the entity identification task, the best performing system reached a precision of 78.90% and a recall of 83.84%. Our NLP system for entity identification and relation extraction ranked 3rd and 4th respectively in the challenge. Our end-to-end pipeline system substantially benefited from the combination of the two data sets. Compared to our official submission, the revised system yielded significantly better performance (p < 0.05) with F1-scores of 86.02% and 72.48% for entity identification and relation extraction, respectively. CONCLUSIONS We demonstrated that a hybrid model could be used to successfully extract family history information recorded in unstructured free-text notes. In this study, our approach of entity identification as a sequence labeling problem produced satisfactory results. Our post-challenge efforts significantly improved performance by leveraging additional labeled data and using word vector representations learned from large collections of clinical notes.

MULTIPLE ENDOCRINE NEOPLASIA IN PRACTICE OF PRIMARY CARE AND FAMILY PHYISICIANS

2020 ◽  
pp. 11-15
Author(s):  
V. I Pozhar ◽  
O. V. Doroshenko ◽  
M. I. Shevchuk
Keyword(s):  
Family History ◽  
Genetic Analysis ◽  
Multiple Endocrine Neoplasia ◽  
Ganglion Cells ◽  
Family Members ◽  
Clinical Manifestations ◽  
Neurofibromatosis Type ◽  
Endocrine Tumors ◽  
Endocrine Neoplasia ◽  
Cutaneous Lichen Amyloidosis

Multiple endocrine neoplasia is characterized with a predisposition to tumors involving two or more endocrine glands. The four main forms of the disease are inherited as an autosomal dominant syndrome or may occur sporadically. In addition to these four forms, six other syndromes are associated with the presence of multiple endocrine and other neoplasms of the organs: hyperparathyroidism − jaw tumors, Carney complex, von Hippel−Lindau disease, neurofibromatosis type 1, Cowden syndrome and McCune − Albright syndrome. The diagnosis of multiple endocrine neoplasia syndrome can be established in humans by one of the three available criteria: clinical features, family history, genetic analysis. Mutation analysis during these syndromes is useful in clinical practice to confirm the clinical diagnosis; identifying family members who tolerate the mutation and need to be screened, and identifying family members who do not tolerate the mutation. Syndrome of multiple endocrine neoplasia (Wermer syndrome) is characterized by the presence of a triad of tumors, including tumors of the parathyroid glands, pheochromocytoma and tumors of the parathyroid gland. It occurs less frequently in combination with Hirschsprung's disease, caused by the absence of vegetative ganglion cells in the intestine terminal parts, that leads to colonic enlargement, severe constipation and obstruction. This syndrome may be associated with cutaneous lichen amyloidosis, the clinical manifestations of which are pruritus and lichenoid lesions, usually located in the upper back. A clinical case of MEN2 syndrome in a 52−year−old patient is presented. It is noted that for such patients, in addition to timely syndromic rather than component diagnosis of this endocrine multipathology, the spread of neoplastic process in medullary thyroid cancer to its capsule and surrounding tissues, as well as the presence of metastases in peripheral lymph nodes are important. As a rule, such patients cannot be timely cured. Key words: multiple endocrine neoplasia, endocrine tumors, genetic analysis, family history.

FAMILY TENSION AS A CAUSE OF COLIC IN INFANTS

PEDIATRICS ◽  
1956 ◽  
Vol 18 (5) ◽  
pp. 835-836
Author(s):  
John C. Cobb
Keyword(s):  
Family History ◽  
Allergic Disease ◽  
Family Members ◽  
Clinical Impression ◽  
Family Histories ◽  
The Family

A study of colic in infancy was undertaken as part of the Yale Rooming-In Project. The longitudinal records of 98 infants who were study subjects were analyzed with respect to incidence, duration, and severity of colic. Forty-eight of the infants were classified as fussy or colicky and 50 as contented. Because I had formed the clinical impression that allergy was an important contributing factor in the causation of colic, careful family histories were taken for all of these infants with particular attention to allergic disease in any member of either parent's family. An adequate family history was obtained in 95 of these infants. These data were analyzed both according to the incidence of allergic disease and according to the severity of allergic disease in family members. Among the relatives of the 45 "fussy" or "colicky" infants 7.3 per cent had severe allergy, 17.7 pen cent had mild allergy and 74 per cent had little or no allergy. Among the relatives of the 50 contented infants 7.6 per cent had severe allergy, 14.7 per cent had mild allergy and 77 per cent had no allergy. The family histories included a total of 957 relatives. The 45 families of the babies who were fussy or colicky were divided as follows as to amount of allergy among the relatives. In 7 families there was much allergy, in 30 families there was some allergy and in 8 families there was little or no allergy. The [See Table I in Source PDF] families of the 50 contented infants were divided as follows, in 7 families there was much allergy, in 33 there was some allergy and in 10 there was little on no allergy.

Family Therapy in Cases of Interminable Grief for the Loss of a Child

1989 ◽  
Vol 19 (3) ◽  
pp. 187-202 ◽  
Author(s):  
Elliott J. Rosen
Keyword(s):  
Family Therapy ◽  
Family History ◽  
Clinical Assessment ◽  
Family Members ◽  
Treatment Method ◽  
Grief Work ◽  
Death Of A Child ◽  
Loss Of A Child ◽  
The Individual

This paper presents a treatment method in cases where grieving for the death of a child extends beyond normal parameters. The symptoms of interminable grief are likely to continue unless there is direct, and often dramatic intervention. Guidelines for clinical assessment are presented, with particular emphasis upon the investigation of family history in which an early, unresolved death may have occurred. This approach integrates grief work with the individual into a family therapy framework and reflects the notion that grieving, even if identified in one person, is a family affair. Criteria for the inclusion of family members in treatment are considered, the stresses upon the therapist are addressed, a course of treatment is outlined, and two representative cases are presented.

scholarly journals Glaucoma Screening in Family Members of Glaucoma Patients at a Tertiary Eye Hospital in Eastern Region of Nepal

2021 ◽  
Vol 13 (2) ◽  
pp. 128-136
Author(s):  
Ravi Dhar Bhandari ◽  
Bandana Khanal ◽  
Manish Poudel ◽  
Mohan Krishna Shrestha ◽  
Suman Shamsher Thapa
Keyword(s):  
Family History ◽  
Early Detection ◽  
Open Angle Glaucoma ◽  
Family Members ◽  
Angle Closure Glaucoma ◽  
Angle Closure ◽  
Eastern Region ◽  
Open Angle ◽  
Cross Sectional ◽  
First Degree Relatives

Introduction: The second most common cause of blindness in the world is glaucoma. Family history plays an important role in early detection and management of patients with glaucoma. The main objective of this study was to determine the prevalence of glaucoma in first degree relatives of Primary open angle glaucoma (POAG) and Primary angle closure glaucoma (PACG) patients. Glaucoma awareness among the first degree relatives was also assessed.    Materials and methods: A  cross sectional hospital based study was designed to examine and diagnose glaucoma among first degree relatives of patients with POAG and PACG, attending the outpatient department at Ramlal Golchha Eye Hospital in the Eastern region of Nepal from June 2016 to May 2017. A comprehensive eye examination was conducted by a glaucoma specialist at the hospital. All subjects underwent vision screening, refraction, slit lamp biomicroscopy, intraocular pressure (IOP) measurement, gonioscopy and a dilated fundus examination. All glaucoma suspects and those diagnosed with glaucoma were enrolled for visual field examination.Results:  Two hundred and twenty-seven first degree relatives of 72 patients were invited for the examination. Out of 227 individuals, 131 (males 67.94%, females 32.06%) agreed to participate in the study. A total of 23 (17.56%) individuals were diagnosed with glaucoma, 10 (43.47%) as POAG and 13 (56.52%) as PACG. Fourteen percent of parents, 22% of siblings and 9% of off-springs had open angle glaucoma. Among 13 PACG participants, 26.08% of parents, 26.08% of siblings and 4.34% of off-springs had angle closure glaucoma. Awareness among first degree relatives diagnosed with glaucoma was 21.74%.  Conclusion:  The prevalence of glaucoma among first degree relatives of glaucoma patients was higher than individuals without family history of glaucoma. Promoting awareness on glaucoma and the timely screening of family members can lead to early detection and prevention of blindness from the disease.  

632 Family History of Children Diagnosed with Obstructive Sleep Apnea

SLEEP ◽  
2021 ◽  
Vol 44 (Supplement_2) ◽  
pp. A248-A248
Author(s):  
Kristi Porterfield-Pruss ◽  
Denise Willis ◽  
Beverly Spray ◽  
Supriya Jambhekar
Keyword(s):  
Family History ◽  
Family Members ◽  
Biological Father ◽  
Medical Problems ◽  
Obstructive Sleep ◽  
Familial Association ◽  
History Of ◽  
The Mean ◽  
Relationship Of ◽  
The Relationship

Abstract Introduction Limited evidence suggests a familial association of OSA. It is not known how often children who require positive airway pressure (PAP) devices have a family member with OSA or that requires PAP. It is felt that PAP adherence in children is affected by PAP adherence in parents. We wanted to explore the relationship of OSA in children requiring PAP to OSA in immediate family members as well as the association of obesity and adherence between children and family members. Methods Caregivers of children who utilize PAP devices at home were invited to complete an electronic questionnaire regarding family history of OSA. Descriptive statistics were utilized to summarize results. Results The study was completed by 75 participants. The majority of children were male (64%, 48/75), black (47%, 35/75) and non-Hispanic (88%, 66/75). The mean age was 11.8 years (median 13) and mean BMI was 32.8 (median 29.8). The mean AHI on the diagnostic polysomnogram was 28.4 events per hour (median 15.3). Mean adherence to PAP &gt; 4 hours per night was 56.5 (Median 68.2). Most, 87% (65/75), have other underlying medical problems. Twenty-four percent (18/75) have a biological father with OSA of whom 61% (11/18) are considered moderately/extremely obese. Of mothers, 13% (10/75) have OSA and 70% (7/10) are obese. Overall, 29% (22/75) had either a paternal (11%, 8/75) or maternal (19%, 14/75) grandfather with OSA of which 36% (8/22) are obese. For grandmothers, 31% (23/75) have OSA and 22% (5/23) are obese with more being paternal (19%, 14/75) compared to maternal (12%, 9/75). Of the 73 total family members reported to have OSA, 86% (63/73) use PAP and most (65%, 41/63) use it for &gt; 4 hours every night. Few participants had siblings with OSA. Conclusion There were more fathers with OSA than mothers, but mothers were reported to be obese more often. Grandparents were reported to have OSA but were reported to be obese less often than parents. Maternal grandparents with OSA were reported to be obese more than paternal grandparents. The majority of family members with OSA who use CPAP report nightly use. Support (if any):

Breaking News of Cancer Diagnosis: A Qualitative Study on the Experiences and Emotional Needs of Patients With Cancer in a Multiethnic Asian Setting

2020 ◽  
pp. JOP.20.00002
Author(s):  
Li-Ping Wong ◽  
Yek-Ching Kong ◽  
Nanthini Thevi Bhoo-Pathy ◽  
Shridevi Subramaniam ◽  
Ros Suzanna Bustamam ◽  
...  
Keyword(s):  
Family History ◽  
Emotional Distress ◽  
Cancer Diagnosis ◽  
Family Members ◽  
Bad News ◽  
Emotional Impact ◽  
Negative Experience ◽  
Supportive Cancer Care ◽  
Patients With Cancer ◽  
Asian Patients

PURPOSE: The breaking of news of a cancer diagnosis is an important milestone in a patient’s cancer journey. We explored the emotional experiences of patients with cancer during the breaking of news of a cancer diagnosis and the arising needs in a multiethnic Asian setting with limited supportive cancer care services. METHODS: Twenty focus group discussions were conducted with 102 Asian patients with cancer from diverse sociodemographic backgrounds. Thematic analysis was performed. RESULTS: While most participants, especially younger patients with young children, experienced intense emotional distress upon receiving a cancer diagnosis, those with a family history of cancer were relatively calm and resigned. Nonetheless, the prior negative experience with cancer in the family made affected participants with a family history less eager to seek cancer treatment and less hopeful for a cure. Although a majority viewed the presence of family members during the breaking of bad news as important, a minority opted to face it alone to lessen the emotional impact on their family members. Difficulties disclosing the news of a cancer diagnosis to loved ones also emerged as an important need. Sensitive and empathetic patient-physician communication during the breaking of news of a cancer diagnosis was stressed as paramount. CONCLUSION: A patient-centered communication approach needs to be developed to reduce the emotional distress to patients and their families after the breaking of bad news of a cancer diagnosis. This is expected to positively affect the patients’ subsequent coping skills and attitudes toward cancer, which may improve adherence to cancer therapy.

Sign in / Sign up

Export Citation Format

Share Document