Intentional injury and violent death after intimate partner violence. A retrospective matched-cohort study.

The incidence of intimate partner violence (IPV) varies according to IPV definitions and data collection approaches. The criminal Justice system assesses IPV through a review of the evidence gathered by the police and the court hearings. We aimed to determine the association between IPV, as identified in criminal Justice disposition records, and subsequent healthcare-identified intentional injury inflicted by others, including violent death. We conducted a retrospective population-based matched-cohort study using linked multisectoral databases. Female adult Manitoba residents identified as victims of IPV in provincial prosecution and disposition records 2004 to 2016 (n = 20,469) were matched to three non-victims (n = 61,407) of similar age, relationship status and place of residence at the date of the IPV incident. Outcomes were first healthcare use for intentional injury and violent death, assessed in Emergency Department visits, hospitalizations and Vital Statistics deaths records. Conditional Cox Regression was used to obtain Hazard Ratios (HR) with 95% confidence intervals (CI). The risk of intentional injury was 8.5 per 1000 women among non-victims of IPV and 55.8 per 1000 women among IPV victims. The Hazard Ratios associated with IPV were 3.8 (95% CI: 3.4, 4.3) for intentional injury and 4.6 (95% CI: 2.3, 9.2) for violent death, after adjustment. IPV victims experienced half the risk of subsequent intentional injury if the accused received a probation sentence. Our findings suggest that Justice involvement represents an opportunity for intersectoral collaborative prevention of subsequent intentional injury among IPV victims.

Identifying Risk Factors Associated With Lower Back Pain in Electronic Medical Record Free Text: Deep Learning Approach Using Clinical Note Annotations.

Background: Lower back pain is a common weakening condition that affects a large population. It is a leading cause of disability and lost productivity, and the associated medical costs and lost wages place a substantial burden on individuals and society. Recent advances in artificial intelligence and natural language processing have opened new opportunities for the identification and management of risk factors for lower back pain. In this paper, we propose and train a deep learning model on a data set of clinical notes that have been annotated with relevant risk factors, and we evaluate the model's performance in identifying risk factors in new clinical notes. Objective: The primary objective is to develop a novel deep learning approach to detect risk factors for underlying disease in patients presenting with lower back pain in clinical encounter notes. The secondary objective is to propose solutions to potential challenges of using deep learning and natural language processing techniques for identifying risk factors in electronic medical record free text and make practical recommendations for future research in this area. Methods: We manually annotated clinical notes for the presence of six risk factors for severe underlying disease in patients presenting with lower back pain. Data were highly imbalanced, with only 12% (n=296) of the annotated notes having at least one risk factor. To address imbalanced data, a combination of semantic textual similarity and regular expressions was used to further capture notes for annotation. Further analysis was conducted to study the impact of downsampling, binary formulation of multi-label classification, and unsupervised pretraining on classification performance. Results: Of 2749 labeled clinical notes, 347 exhibited at least one risk factor, while 2402 exhibited none. The initial analysis shows that downsampling the training set to equalize the ratio of clinical notes with and without risk factors improved the macro-area under the receiver operating characteristic curve (AUROC) by 2%. The Bidirectional Encoder Representations from Transformers (BERT) model improved the macro-AUROC by 15% over the traditional machine learning baseline. In experiment 2, the proposed BERT-convolutional neural network (CNN) model for longer texts improved (4% macro-AUROC) over the BERT baseline, and the multitask models are more stable for minority classes. In experiment 3, domain adaptation of BERTCNN using masked language modeling improved the macro-AUROC by 2%. Conclusions: Primary care clinical notes are likely to require manipulation to perform meaningful free-text analysis. The application of BERT models for multi-label classification on downsampled annotated clinical notes is useful in detecting risk factors suggesting an indication for imaging for patients with lower back pain.

De-identification of free text data containing personal health information: a scoping review of reviews.

Introduction: Using data in research often requires that the data first be de-identified, particularly in the case of health data, which often include Personal Identifiable Information (PII) and/or Personal Health Identifying Information (PHII). There are established procedures for de-identifying structured data, but de-identifying clinical notes, electronic health records, and other records that include free text data is more complex. Several different ways to achieve this are documented in the literature. This scoping review identifies categories of de-identification methods that can be used for free text data. Methods: We adopted an established scoping review methodology to examine review articles published up to May 9, 2022, in Ovid MEDLINE; Ovid Embase; Scopus; the ACM Digital Library; IEEE Explore; and Compendex. Our research question was: What methods are used to de-identify free text data? Two independent reviewers conducted title and abstract screening and full-text article screening using the online review management tool Covidence. Results: The initial literature search retrieved 3,312 articles, most of which focused primarily on structured data. Eighteen publications describing methods of de-identification of free text data met the inclusion criteria for our review. The majority of the included articles focused on removing categories of personal health information identified by the Health Insurance Portability and Accountability Act (HIPAA). The de-identification methods they described combined rule-based methods or machine learning with other strategies such as deep learning. Conclusion: Our review identifies and categorises de-identification methods for free text data as rule-based methods, machine learning, deep learning and a combination of these and other approaches. Most of the articles we found in our search refer to de-identification methods that target some or all categories of PHII. Our review also highlights how de-identification systems for free text data have evolved over time and points to hybrid approaches as the most promising approach for the future.

A scoping review of preprocessing methods for unstructured text data to assess data quality.

Introduction: Unstructured text data (UTD) are increasingly found in many databases that were never intended to be used for research, including electronic medical record (EMR) databases. Data quality can impact the usefulness of UTD for research. UTD are typically prepared for analysis (i.e., preprocessed) and analyzed using natural language processing (NLP) techniques. Different NLP methods are used to preprocess UTD and may affect data quality. Objective: Our objective was to systematically document current research and practices about NLP preprocessing methods to describe or improve the quality of UTD, including UTD found in EMR databases. Methods: A scoping review was undertaken of peer-reviewed studies published between December 2002 and January 2021. Scopus, Web of Science, ProQuest, and EBSCOhost were searched for literature relevant to the study objective. Information extracted from the studies included article characteristics (i.e., year of publication, journal discipline), data characteristics, types of preprocessing methods, and data quality topics. Study data were presented using a narrative synthesis. Results: A total of 41 articles were included in the scoping review; over 50% were published between 2016 and 2021. Almost 20% of the articles were published in health science journals. Common preprocessing methods included removal of extraneous text elements such as stop words, punctuation, and numbers, word tokenization, and parts of speech tagging. Data quality topics for articles about EMR data included misspelled words, security (i.e., de-identification), word variability, sources of noise, quality of annotations, and ambiguity of abbreviations. Conclusions: Multiple NLP techniques have been proposed to preprocess UTD, with some differences in techniques applied to EMR data. There are similarities in the data quality dimensions used to characterize structured data and UTD. While a few general-purpose measures of data quality that do not require external data; most of these focus on the measurement of noise.

Pan-Canadian Electronic Medical Record Diagnostic and Unstructured Text Data for Capturing PTSD: Retrospective Observational Study.

BACKGROUND: The availability of electronic medical record (EMR) free-text data for research varies. However, access to short diagnostic text fields is more widely available. OBJECTIVE: This study assesses agreement between free-text and short diagnostic text data from primary care EMR for identification of posttraumatic stress disorder (PTSD). METHODS: This retrospective cross-sectional study used EMR data from a pan-Canadian repository representing 1574 primary care providers at 265 clinics using 11 EMR vendors. Medical record review using free text and short diagnostic text fields of the EMR produced reference standards for PTSD. Agreement was assessed with sensitivity, specificity, positive predictive value, negative predictive value, and accuracy. RESULTS: Our reference set contained 327 patients with free text and short diagnostic text. Among these patients, agreement between free text and short diagnostic text had an accuracy of 93.6% (CI 90.4%-96.0%). In a single Canadian province, case definitions 1 and 4 had a sensitivity of 82.6% (CI 74.4%-89.0%) and specificity of 99.5% (CI 97.4%-100%). However, when the reference set was expanded to a pan-Canada reference (n=12,104 patients), case definition 4 had the strongest agreement (sensitivity: 91.1%, CI 90.1%-91.9%; specificity: 99.1%, CI 98.9%-99.3%). CONCLUSIONS: Inclusion of free-text encounter notes during medical record review did not lead to improved capture of PTSD cases, nor did it lead to significant changes in case definition agreement. Within this pan-Canadian database, jurisdictional differences in diagnostic codes and EMR structure suggested the need to supplement diagnostic codes with natural language processing to capture PTSD. When unavailable, short diagnostic text can supplement free-text data for reference set creation and case validation. Application of the PTSD case definition can inform PTSD prevalence and characteristics.

Relaxation of social distancing restrictions: Model estimated impact on COVID-19 epidemic in Manitoba, Canada.

OBJECTIVES: The unprecedented worldwide social distancing response to COVID-19 resulted in a quick reversal of escalating case numbers. Recently, local governments globally have begun to relax social distancing regulations. Using the situation in Manitoba, Canada as an example, we estimated the impact that social distancing relaxation may have on the pandemic. METHODS: We fit a mathematical model to empirically estimated numbers of people infected, recovered, and died from COVID-19 in Manitoba. We then explored the impact of social distancing relaxation on: (a) time until near elimination of COVID-19 (< one case per million), (b) time until peak prevalence, (c) proportion of the population infected within one year, (d) peak prevalence, and (e) deaths within one year. RESULTS: Assuming a closed population, near elimination of COVID-19 in Manitoba could have been achieved in 4-6 months (by July or August) if there were no relaxation of social distancing. Relaxing to 15% of pre-COVID effective contacts may extend the local epidemic for more than two years (median 2.1). Relaxation to 50% of pre-COVID effective contacts may result in a peak prevalence of 31-38% of the population, within 3-4 months of initial relaxation. CONCLUSION: Slight relaxation of social distancing may immensely impact the pandemic duration and expected peak prevalence. Only holding the course with respect to social distancing may have resulted in near elimination before Fall of 2020; relaxing social distancing to 15% of pre-COVID-19 contacts will flatten the epidemic curve but greatly extend the duration of the pandemic.