Natural Language Processing Rules Research Articles

Social Determinants of Health Documentation in Structured and Unstructured Clinical Data of Patients With Diabetes: Comparative Analysis.

Electronic health records (EHRs) have yet to fully capture social determinants of health (SDOH) due to challenges such as nonexistent or inconsistent data capture tools across clinics, lack of time, and the burden of extra steps for the clinician. However, patient clinical notes (unstructured data) may be a better source of patient-related SDOH information. It is unclear how accurately EHR data reflect patients' lived experience of SDOH. The manual process of retrieving SDOH information from clinical notes is time-consuming and not feasible. We leveraged two high-throughput tools to identify SDOH mappings to structured and unstructured patient data: PatientExploreR and Electronic Medical Record Search Engine (EMERSE). We included adult patients (≥18 years of age) receiving primary care for their diabetes at the University of California, San Francisco (UCSF), from January 1, 2018, to December 31, 2019. We used expert raters to develop a corpus using SDOH in the compendium as a knowledge base as targets for the natural language processing (NLP) text string mapping to find string stems, roots, and syntactic similarities in the clinical notes of patients with diabetes. We applied advanced built-in EMERSE NLP query parsers implemented with JavaCC. We included 4283 adult patients receiving primary care for diabetes at UCSF. Our study revealed that SDOH may be more significant in the lives of patients with diabetes than is evident from structured data recorded on EHRs. With the application of EMERSE NLP rules, we uncovered additional information from patient clinical notes on problems related to social connectionsisolation, employment, financial insecurity, housing insecurity, food insecurity, education, and stress. We discovered more patient information related to SDOH in unstructured data than in structured data. The application of this technique and further investment in similar user-friendly tools and infrastructure to extract SDOH information from unstructured data may help to identify the range of social conditions that influence patients' disease experiences and inform clinical decision-making.

On semi-automated extraction of causal networks from raw text

A rule-based framework, named SCANER (Semi-automated CAusal Network Extraction from Raw text) is presented. SCANER converts raw text into causal networks using a set of natural language processing rules. The raw textual data that contains useful information for informing future decisions and developing strategies in various critical domains must be converted into useful, understandable models. However, building such models manually from raw text is a labor-intensive and time-consuming process and needs to be automated. The automated extraction of causality from raw text, however, has its own set of challenges due to the linguistic complexity and ambiguity of the texts. It can also be argued that for complicated scenarios and critical domains subject matter experts cannot rely solely on such automatically generated models without sound reasoning to support them. This implies the need for a semi-automated human-in-the-loop approach. This research, therefore, is focused on combining the strengths of both manual and automated approaches and on developing a framework for a rule-based semi-automated approach to generate causal networks from raw text. SCANER is evaluated on three collections of raw text from political, food insecurity, and medical domains using F-Score as the evaluation metric. The ground truth for the causal links is generated after incorporating feedback from a group of three human judges. A comparative analysis with Eidos, an open-source causality extraction system, demonstrates the advantages of SCANER in generating dense and accurate causal networks from the raw text.

Literature Review of Qualitative Data with Natural Language Processing

Qualitative research techniques are frequently employed by scholars in the field of social sciences when investigating communities and their communication media. The proliferation of computer-mediated communications has resulted in a substantial volume of textual content. However, the process of coding this vast amount of information necessitates significant time and effort. This article examines the potential for automating specific elements of content analysis through the utilization of natural language processing (NLP) systems, which analyze text in human languages, with a focus on extracting theoretical evidence. In this study, we present a case analysis utilizing NLP to examine the effectiveness of NLP rules in qualitative analysis. Our findings indicate that the NLP rules demonstrated strong performance across multiple codes. The utilization of a NLP system in its current developmental stage has the potential to significantly minimize the text volume, which has to be evaluated using the human coder. This reduction could potentially result in a substantial increase in coding speed, potentially by a factor of ten or more. The research is considered groundbreaking as it pioneers the application of advanced NLP approach to evaluate qualitative data, making it one of the earliest studies in this domain.

Real-world treatment response in Japanese patients with cancer using unstructured data from electronic health records

PurposeWe generated methods for evaluating clinical outcomes including treatment response in oncology using the unstructured data from electronic health records (EHR) in Japanese language.MethodsThis retrospective analysis used medical record database and administrative data of University of Miyazaki Hospital in Japan of patients with lung/breast cancer. Treatment response (objective response [OR], stable disease [SD] or progressive disease [PD]) was adjudicated by two evaluators using clinicians’ progress notes, radiology reports and pathological reports of 15 patients with lung cancer (training data set). For assessing key terms to describe treatment response, natural language processing (NLP) rules were created from the texts identified by the evaluators and broken down by morphological analysis. The NLP rules were applied for assessing data of other 70 lung cancer and 30 breast cancer patients, who were not adjudicated, to examine if any difference in using key terms exist between these patients.ResultsA total of 2,039 records in progress notes, 131 in radiology reports and 60 in pathological reports of 15 patients, were adjudicated. Progress notes were the most common primary source data for treatment assessment (60.7%), wherein, the most common key terms with high sensitivity and specificity to describe OR were “reduction/shrink”, for SD were “(no) remarkable change/(no) aggravation)” and for PD were “(limited) effect” and “enlargement/grow”. These key terms were also found in other larger cohorts of 70 patients with lung cancer and 30 patients with breast cancer.ConclusionThis study demonstrated that assessing response to anticancer therapy using Japanese EHRs is feasible by interpreting progress notes, radiology reports and Japanese key terms using NLP.

Development of a generalizable natural language processing pipeline to extract physician-reported pain from clinical reports: Generated using publicly-available datasets and tested on institutional clinical reports for cancer patients with bone metastases

Objective:The majority of cancer patients suffer from severe pain at the advanced stage of their illness. In most cases, cancer pain is underestimated by clinical staff and is not properly managed until it reaches a critical stage. Therefore, detecting and addressing cancer pain early can potentially improve the quality of life of cancer patients.The objective of this research project was to develop a generalizable Natural Language Processing (NLP) pipeline to find and classify physician-reported pain in the radiation oncology consultation notes of cancer patients with bone metastases. Materials and Methods:The texts of 1249 publicly-available hospital discharge notes in the i2b2 database were used as a training and validation set. The MetaMap and NegEx algorithms were implemented for medical terms extraction. Sets of NLP rules were developed to score pain terms in each note. By averaging pain scores, each note was assigned to one of the three verbally-declared pain (VDP) labels, including no pain, pain, and no mention of pain. Without further training, the generalizability of our pipeline in scoring individual pain terms was tested independently using 30 hospital discharge notes from the MIMIC-III database and 30 consultation notes of cancer patients with bone metastasis from our institution’s radiation oncology electronic health record. Finally, 150 notes from our institution were used to assess the pipeline’s performance at assigning VDP. Results:Our NLP pipeline successfully detected and quantified pain in the i2b2 summary notes with 93% overall precision and 92% overall recall. Testing on the MIMIC-III database achieved precision and recall of 91% and 86% respectively. The pipeline successfully detected pain with 89% precision and 82% recall on our institutional radiation oncology corpus. Finally, our pipeline assigned a VDP to each note in our institutional corpus with 84% and 82% precision and recall, respectively. Conclusion:Our NLP pipeline enables the detection and classification of physician-reported pain in our radiation oncology corpus. This portable and ready-to-use pipeline can be used to automatically extract and classify physician-reported pain from clinical notes where the pain is not otherwise documented through structured data entry.

Aspects Based Opinion Mining for Teacher and Course Evaluation

Teacher and course evaluation by students at the end of each term is an important task in almost every academic institution world wide. It helps in assessing faculty performance and suitability of the course in any academic program. The data collected from evaluation comprises of two parts|Likert Scale and open-ended feedback. Computationally, the Likert Scale form can be handled easily as it is numerical in nature but to handle open-ended feedback is a challenging task. Presently, in most of the organizations, it is processed manually, which is error-prone, tedious and full of human biases. To solve this problem, this paper proposes a two-step strategy based on Machine Learning and Natural Language Processing (NLP) techniques. The first step is to extract overall topic of the feedback text using supervised machine learning followed by exploitation of NLP rules to find out specific aspect about which the feedback is given along with orientation of the opinion either positive, negative or neutral. Using, this two-step strategy combining with NLP, machine learning techniques and data from past seven years of real feedback at a public sector university in Pakistan, we are able to achieve a recall and precision of 83.89% and 84% on topic identification i.e. to classify a feedback in teacher and course category. The system is able to extract different aspects of teacher and course with a precision of 83% and recall of 80%, whereas overall sentiment classification accuracy is 90%.

A Novel Framework to Automatically Generate IFML Models From Plain Text Requirements

User Interfaces (UI’s) are highly important in this era of web and mobile applications. Therefore, an efficient and accurate development of UI’s is desirable in early Software Development Life Cycle (SDLC) phases. To achieve this, Object Management Group (OMG) introduced Interaction Flow Modeling Language (IFML) standard in 2013. IFML provides the modeling of manifold UI’s for different applications like mobile, web and desktop. Although IFML is based on Model Driven Engineering (MDE) principle, the development of user interface models from initial requirements is still complex and time consuming task. Particularly, it requires domain expertise to understand several IFML concepts like domain model, view container etc. for the proper modeling of user interfaces. Consequently, there is a strong need of an approach to automate the development of IFML models from initial plain text requirements. This article presents a novel framework to automatically generate IFML models from textual requirements by utilizing the features of Natural Language Processing (NLP). Particularly, a set of NLP rules are developed to extract important IFML elements like View Components, Events etc. from textual requirements. Furthermore, a comprehensive algorithm is developed for the systematic execution of NLP rules in order to generate both IFML Domain and Core models. As a part of research, a sophisticated $T$ ext to IF ML ( T2IF ) tool is developed. The feasibility of proposed framework is demonstrated through movie manager and online bookstore case studies. The evaluation results prove that the proposed framework is capable of generating IFML models from textual requirements with high accuracy.

Identifying named entities from PubMed for enriching semantic categories.

BackgroundControlled vocabularies such as the Unified Medical Language System (UMLS®) and Medical Subject Headings (MeSH®) are widely used for biomedical natural language processing (NLP) tasks. However, the standard terminology in such collections suffers from low usage in biomedical literature, e.g. only 13% of UMLS terms appear in MEDLINE®.ResultsWe here propose an efficient and effective method for extracting noun phrases for biomedical semantic categories. The proposed approach utilizes simple linguistic patterns to select candidate noun phrases based on headwords, and a machine learning classifier is used to filter out noisy phrases. For experiments, three NLP rules were tested and manually evaluated by three annotators. Our approaches showed over 93% precision on average for the headwords, “gene”, “protein”, “disease”, “cell” and “cells”.ConclusionsAlthough biomedical terms in knowledge-rich resources may define semantic categories, variations of the controlled terms in literature are still difficult to identify. The method proposed here is an effort to narrow the gap between controlled vocabularies and the entities used in text. Our extraction method cannot completely eliminate manual evaluation, however a simple and automated solution with high precision performance provides a convenient way for enriching semantic categories by incorporating terms obtained from the literature.Electronic supplementary materialThe online version of this article (doi:10.1186/s12859-015-0487-2) contains supplementary material, which is available to authorized users.

Machine learning and rule-based automated coding of qualitative data

Large volumes of textual data pose considerable challenges for manual qualitative analysis. We explore semi-automatic coding of textual data by leveraging Natural Language Processing (NLP). We compare the performance of human-developed NLP rules to those inferred by machine learning (ML) algorithms. The results suggest that NLP with ML may be useful to support researchers coding qualitative data.