Challenges of Developing a Natural Language Processing Method With Electronic Health Records to Identify Persons With Chronic Mobility Disability

Toward Reliable Symptom Coding in Electronic Health Records for Symptom Assessment and Research: Identification and Categorization of International Classification of Diseases, Ninth Revision, Clinical Modification Symptom Codes

To date, symptom documentation has mostly relied on clinical notes in electronic health records or patient-reported outcomes using disease-specific symptom inventories. To provide a common and precise language for symptom recording, assessment, and research, a comprehensive list of symptom codes is needed. The International Classification of Diseases, Ninth Revision or its clinical modification ( International Classification of Diseases, Ninth Revision, Clinical Modification ) has a range of codes designated for symptoms, but it does not contain codes for all possible symptoms, and not all codes in that range are symptom related. This study aimed to identify and categorize the first list of International Classification of Diseases, Ninth Revision, Clinical Modification symptom codes for a general population and demonstrate their use to characterize symptoms of patients with type 2 diabetes mellitus in the Cerner database. A list of potential symptom codes was automatically extracted from the Unified Medical Language System Metathesaurus. Two clinical experts in symptom science and diabetes manually reviewed this list to identify and categorize codes as symptoms. A total of 1888 International Classification of Diseases, Ninth Revision, Clinical Modification symptom codes were identified and categorized into 65 categories. The symptom characterization using the newly obtained symptom codes and categories was found to be more reasonable than that using the previous symptom codes and categories on the same Cerner diabetes cohort.

Delirium and Healthcare Utilization in Patients Undergoing Hematopoietic Stem Cell Transplantation

Delirium, a common neuropsychiatric syndrome among hospitalized patients, has been associated with significant morbidity and mortality in patients undergoing hematopoietic stem cell transplantation (HSCT). Although delirium is often reversible with prompt diagnosis and appropriate management, timely screening of hospitalized patients, including HSCT recipients at risk for delirium, is lacking. The association between delirium symptoms and healthcare utilization among HSCT recipients is also limited. We conducted a retrospective analysis of 502 hospitalized patients admitted for allogeneic or autologous HSCT at 2 tertiary care hospitals between April 2016 and April 2021. We used Natural Language Processing (NLP) to identify patients with delirium symptoms, as defined by an NLP-assisted chart review of the electronic health record (EHR). We used multivariable regression models to examine the associations between delirium symptoms, clinical outcomes, and healthcare utilization, adjusting for patient-, disease-, and transplantation-related factors. Overall, 44.4% (124 of 279) of patients undergoing allogeneic HSCT and 39.0% (87 of 223) of those undergoing autologous HSCT were identified as having delirium symptoms during their index hospitalization. Two-thirds (139 of 211) of the patients with delirium symptoms were prescribed treatment with antipsychotic medications. Among allogeneic HSCT recipients, delirium symptoms were associated with longer hospital length of stay (β = 7.960; P < .001), fewer days alive and out of the hospital (β = -23.669; P < .001), and more intensive care unit admissions (odds ratio, 2.854; P = .002). In autologous HSCT recipients, delirium symptoms were associated with longer hospital length of stay (β = 2.204; P < .001). NLP-assisted EHR review is a feasible approach to identifying hospitalized patients, including HSCT recipients at risk for delirium. Because delirium symptoms are negatively associated with health care utilization during and after HSCT, our findings underscore the need to efficiently identify patients hospitalized for HSCT who are at risk of delirium to improve their outcomes. © 2023 American Society for Transplantation and Cellular Therapy. Published by Elsevier Inc.

The use of natural language processing in palliative care research: A scoping review

BACKGROUND

Natural language processing has been increasingly used in palliative care research over the last 5 years for its versatility and accuracy.

AIM

To evaluate and characterize natural language processing use in palliative care research, including the most commonly used natural language processing software and computational methods, data sources, trends in natural language processing use over time, and palliative care topics addressed.

DESIGN

A scoping review using the framework by Arksey and O'Malley and the updated recommendations proposed by Levac et al. was conducted.

SOURCES

PubMed, Web of Science, Embase, Scopus, and IEEE Xplore databases were searched for palliative care studies that utilized natural language processing tools. Data on study characteristics and natural language processing instruments used were collected and relevant palliative care topics were identified.

RESULTS

197 relevant references were identified. Of these, 82 were included after full-text review. Studies were published in 48 different journals from 2007 to 2022. The average sample size was 21,541 (median 435). Thirty-two different natural language processing software and 33 machine-learning methods were identified. Nine main sources for data processing and 15 main palliative care topics across the included studies were identified. The most frequent topic was mortality and prognosis prediction. We also identified a trend where natural language processing was frequently used in analyzing clinical serious illness conversations extracted from audio recordings.

CONCLUSIONS

We found 82 papers on palliative care using natural language processing methods for a wide-range of topics and sources of data that could expand the use of this methodology. We encourage researchers to consider incorporating this cutting-edge research methodology in future studies to improve published palliative care data.

Gross motor function prediction using natural language processing in cerebral palsy

AIM

To predict ambulatory status and Gross Motor Function Classification System (GMFCS) levels in patients with cerebral palsy (CP) by applying natural language processing (NLP) to electronic health record (EHR) clinical notes.

METHOD

Individuals aged 8 to 26 years with a diagnosis of CP in the EHR between January 2009 and November 2020 (~12 years of data) were included in a cross-sectional retrospective cohort of 2483 patients. The cohort was divided into train-test and validation groups. Positive predictive value, sensitivity, specificity, and area under the receiver operating curve (AUC) were calculated for prediction of ambulatory status and GMFCS levels.

RESULTS

The median age was 15 years (interquartile range 10-20 years) for the total cohort, with 56% being male and 75% White. The validation group resulted in 70% sensitivity, 88% specificity, 81% positive predictive value, and 0.89 AUC for predicting ambulatory status. NLP applied to the EHR differentiated between GMFCS levels I-II and III (15% sensitivity, 96% specificity, 46% positive predictive value, and 0.71 AUC); and IV and V (81% sensitivity, 51% specificity, 70% positive predictive value, and 0.75 AUC).

INTERPRETATION

NLP applied to the EHR demonstrated excellent differentiation between ambulatory and non-ambulatory status, and good differentiation between GMFCS levels I-II and III, and IV and V. Clinical use of NLP may help to individualize functional characterization and management.

WHAT THIS PAPER ADDS

Natural language processing (NLP) applied to the electronic health record (EHR) can predict ambulatory status in children with cerebral palsy (CP). NLP provides good prediction of Gross Motor Function Classification System level in children with CP using the EHR. NLP methods described could be integrated in an EHR system to provide real-time information.

Clinical Informatics Approaches to Understand and Address Cancer Disparities

OBJECTIVES

Disparities in cancer incidence and outcomes across race, ethnicity, gender, socioeconomic status, and geography are well-documented, but their etiologies are often poorly understood and multifactorial. Clinical informatics can provide tools to better understand and address these disparities by enabling high-throughput analysis of multiple types of data. Here, we review recent efforts in clinical informatics to study and measure disparities in cancer.

METHODS

We carried out a narrative review of clinical informatics studies related to cancer disparities and bias published from 2018-2021, with a focus on domains such as real-world data (RWD) analysis, natural language processing (NLP), radiomics, genomics, proteomics, metabolomics, and metagenomics.

RESULTS

Clinical informatics studies that investigated cancer disparities across race, ethnicity, gender, and age were identified. Most cancer disparities work within clinical informatics used RWD analysis, NLP, radiomics, and genomics. Emerging applications of clinical informatics to understand cancer disparities, including proteomics, metabolomics, and metagenomics, were less well represented in the literature but are promising future research avenues. Algorithmic bias was identified as an important consideration when developing and implementing cancer clinical informatics techniques, and efforts to address this bias were reviewed.

CONCLUSIONS

In recent years, clinical informatics has been used to probe a range of data sources to understand cancer disparities across different populations. As informatics tools become integrated into clinical decision-making, attention will need to be paid to ensure that algorithmic bias does not amplify existing disparities. In our increasingly interconnected medical systems, clinical informatics is poised to untap the full potential of multi-platform health data to address cancer disparities.

The Use of Natural Language Processing to Assess Social Support in Patients With Advanced Cancer

BACKGROUND

Data examining associations among social support, survival, and healthcare utilization are lacking in patients with advanced cancer.

METHODS

We conducted a cross-sectional secondary analysis using data from a prospective longitudinal cohort study of 966 hospitalized patients with advanced cancer at Massachusetts General Hospital from 2014 through 2017. We used NLP to identify extent of patients' social support (limited versus adequate as defined by NLP-aided review of the Electronic Health Record (EHR)). Two independent coders achieved a Kappa of 0.90 (95% CI: 0.84-1.00) using NLP. Using multivariable regression models, we examined associations of social support with: 1) OS; 2) death or readmission within 90 days of hospital discharge; 3) time to readmission within 90 days; and 4) hospital length of stay (LOS).

RESULTS

Patients' median age was 65 (range: 21-92) years, and a plurality had gastrointestinal (GI) cancer (34.3%) followed by lung cancer (19.5%). 6.2% (60/966) of patients had limited social support. In multivariable analyses, limited social support was not significantly associated with OS (HR = 1.13, P = 0.390), death or readmission (OR = 1.18, P = 0.578), time to readmission (HR = 0.92, P = 0.698), or LOS (β = -0.22, P = 0.726). We identified a potential interaction suggesting cancer type (GI cancer versus other) may be an effect modifier of the relationship between social support and OS (interaction term P = 0.053). In separate unadjusted analyses, limited social support was associated with lower OS (HR = 2.10, P = 0.008) in patients with GI cancer but not other cancer types (HR = 1.00, P = 0.991).

CONCLUSION

We used NLP to assess the extent of social support in patients with advanced cancer. We did not identify significant associations of social support with OS or healthcare utilization but found cancer type may be an effect modifier of the relationship between social support and OS. These findings underscore the potential utility of NLP for evaluating social support in patients with advanced cancer.

A roadmap to reduce information inequities in disability with digital health and natural language processing

People with disabilities disproportionately experience negative health outcomes. Purposeful analysis of information on all aspects of the experience of disability across individuals and populations can guide interventions to reduce health inequities in care and outcomes. Such an analysis requires more holistic information on individual function, precursors and predictors, and environmental and personal factors than is systematically collected in current practice. We identify 3 key information barriers to more equitable information: (1) a lack of information on contextual factors that affect a person's experience of function; (2) underemphasis of the patient's voice, perspective, and goals in the electronic health record; and (3) a lack of standardized locations in the electronic health record to record observations of function and context. Through analysis of rehabilitation data, we have identified ways to mitigate these barriers through the development of digital health technologies to better capture and analyze information about the experience of function. We propose 3 directions for future research on using digital health technologies, particularly natural language processing (NLP), to facilitate capturing a more holistic picture of a patient's unique experience: (1) analyzing existing information on function in free text documentation; (2) developing new NLP-driven methods to collect information on contextual factors; and (3) collecting and analyzing patient-reported descriptions of personal perceptions and goals. Multidisciplinary collaboration between rehabilitation experts and data scientists to advance these research directions will yield practical technologies to help reduce inequities and improve care for all populations.

Natural Language Processing for Computer-Assisted Chart Review to Assess Documentation of Substance use and Psychopathology in Heart Failure Patients Awaiting Cardiac Resynchronization Therapy

CONTEXT

Advanced heart failure (HF) patients often experience distressing psychological symptoms, frequently meeting diagnostic criteria for psychological disorders, including anxiety, depression, and substance use disorder. Patients with device-based HF therapies have added risk for psychological disorders, with consequences for their physiological functioning, including adverse cardiac outcomes.

OBJECTIVES

This study used natural language processing (NLP) for computer-assisted chart review to assess documentation of mental health and substance use in HF patients awaiting cardiac resynchronization therapy (CRT), a device-based HF therapy.

METHODS

We applied NLP to clinical notes from electronic health records (EHR) of 965 consecutive patients, with 9821 total clinical notes, at two academic medical centers between 2004 and 2015. We developed and validated a keyword library capturing terms related to mental health and substance use, while balancing specificity and sensitivity.

RESULTS

Mean age was 71.6 years (SD = 11.8), 78% male, and 87% non-Hispanic White. Of the 544 patients (56.4%) with documentation of mental health history, 9.7% had their mental health assessed and 6.6% had a plan documented. Of the 773 patients (80.1%) with documentation of substance use history, 10 (1.0%) had an assessment, and 3 (0.3%) had a plan.

CONCLUSION

Despite clinical recommendations and standards of care, clinicians are under documenting assessments and plans prior to CRT. Future research should develop an algorithm to prompt clinicians to document this content. Such quality improvement efforts may ensure adherence to standards of care and clinical guidelines.

Perinatal Health Risks And Outcomes Among US Women With Self-Reported Disability, 2011-19

Women with disabilities experience elevated risk for adverse pregnancy outcomes. Most studies have inferred disabilities from diagnosis codes, likely undercounting disabilities. We analyzed data, including self-reported disability status, from the National Survey of Family Growth for the period 2011-19. We compared respondents with and without disabilities on these characteristics: smoking during pregnancy, delayed prenatal care, preterm birth, and low birthweight. A total of 19.5 percent of respondents who had given birth reported a disability, which is a much higher prevalence than estimates reported in US studies using diagnosis codes. Respondents with disabilities were twice as likely as those without disabilities to have smoked during pregnancy (19.0 percent versus 8.9 percent). They also had 24 percent and 29 percent higher risk for preterm birth and low birthweight, respectively. Our findings suggest that studies using diagnosis codes may represent only a small proportion of pregnancies among people with disabilities. Measurement and analysis of self-reported disability would facilitate better understanding of the full extent of disability-related disparities, per the Affordable Care Act.

Implications of Physical Access Barriers for Breast Cancer Diagnosis and Treatment in Women with Mobility Disability

Objective

More than 30 years since enactment of the Americans with Disabilities Act, people with disability continue to face physical access barriers, notably inaccessible medical diagnostic equipment, in clinical settings. Access barriers affect breast cancer screening and treatment for women with disability.

Methods

We used standard diagnosis codes and natural language processing to screen electronic health records (EHRs) in a digital data repository from a large healthcare delivery system for patients with pre-existing mobility disability diagnosed with breast cancer between 2005-2017. We reviewed EHRs of 20 patients, using conventional content analysis to examine breast cancer diagnosis and treatment experiences.

Results

Clinicians noted challenges positioning patients for routine procedures including manual breast exam, screening mammography, and breast biopsies. Given challenges accommodating disability for adjuvant therapies, mastectomy was favored over breast-conserving options despite early stages of diagnosis. Notations contained little information about proactive problem-solving for arranging accommodations.

Conclusions

Notations described physical access barriers for breast cancer detection and treatment, with limited planning for mitigating barriers. Despite 2017 promulgation of federal Standards for Accessible Medical Diagnostic Equipment, implementing these standards requires further rulemaking.

Natural Language Processing to Identify Advance Care Planning Documentation in a Multisite Pragmatic Clinical Trial

CONTEXT

Large multisite clinical trials studying decision-making when facing serious illness require an efficient method for abstraction of advance care planning (ACP) documentation from clinical text documents. However, the current gold standard method of manual chart review is time-consuming and unreliable.

OBJECTIVES

To evaluate the ability to use natural language processing (NLP) to identify ACP documention in clinical notes from patients participating in a multisite trial.

METHODS

Patients with advanced cancer followed in three disease-focused oncology clinics at Duke Health, Mayo Clinic, and Northwell Health were identified using administrative data. All outpatient and inpatient notes from patients meeting inclusion criteria were extracted from electronic health records (EHRs) between March 2018 and March 2019. NLP text identification software with semi-automated chart review was applied to identify documentation of four ACP domains: (1) conversations about goals of care, (2) limitation of life-sustaining treatment, (3) involvement of palliative care, and (4) discussion of hospice. The performance of NLP was compared to gold standard manual chart review.

RESULTS

435 unique patients with 79,797 notes were included in the study. In our validation data set, NLP achieved F1 scores ranging from 0.84 to 0.97 across domains compared to gold standard manual chart review. NLP identified ACP documentation in a fraction of the time required by manual chart review of EHRs (1-5 minutes per patient for NLP, vs. 30-120 minutes for manual abstraction).

CONCLUSION

NLP is more efficient and as accurate as manual chart review for identifying ACP documentation in studies with large patient cohorts.

Analysis of depression in social media texts through the Patient Health Questionnaire-9 and natural language processing

Objective

Although depression in modern people is emerging as a major social problem, it shows a low rate of use of mental health services. The purpose of this study was to classify sentences written by social media users based on the nine symptoms of depression in the Patient Health Questionnaire-9, using natural language processing to assess naturally users’ depression based on their results.

Methods

First, train two sentence classifiers: the Y/N sentence classifier, which categorizes whether a user’s sentence is related to depression, and the 0–9 sentence classifier, which further categorizes the user sentence based on the depression symptomology of the Patient Health Questionnaire-9. Then the depression classifier, which is a logistic regression model, was generated to classify the sentence writer’s depression. These trained sentence classifiers and the depression classifier were used to analyze the social media textual data of users and establish their depression.

Results

Our experimental results showed that the proposed depression classifier showed 68.3% average accuracy, which was better than the baseline depression classifier that used only the Y/N sentence classifier and had 53.3% average accuracy.

Conclusions

This study is significant in that it demonstrates the possibility of determining depression from only social media users’ textual data.

Linking Free Text Documentation of Functioning and Disability to the ICF With Natural Language Processing

Background: Invaluable information on patient functioning and the complex interactions that define it is recorded in free text portions of the Electronic Health Record (EHR). Leveraging this information to improve clinical decision-making and conduct research requires natural language processing (NLP) technologies to identify and organize the information recorded in clinical documentation.

Methods: We used natural language processing methods to analyze information about patient functioning recorded in two collections of clinical documents pertaining to claims for federal disability benefits from the U.S. Social Security Administration (SSA). We grounded our analysis in the International Classification of Functioning, Disability, and Health (ICF), and used the Activities and Participation domain of the ICF to classify information about functioning in three key areas: mobility, self-care, and domestic life. After annotating functional status information in our datasets through expert clinical review, we trained machine learning-based NLP models to automatically assign ICF categories to mentions of functional activity.

Results: We found that rich and diverse information on patient functioning was documented in the free text records. Annotation of 289 documents for Mobility information yielded 2,455 mentions of Mobility activities and 3,176 specific actions corresponding to 13 ICF-based categories. Annotation of 329 documents for Self-Care and Domestic Life information yielded 3,990 activity mentions and 4,665 specific actions corresponding to 16 ICF-based categories. NLP systems for automated ICF coding achieved over 80% macro-averaged F-measure on both datasets, indicating strong performance across all ICF categories used.

Conclusions: Natural language processing can help to navigate the tradeoff between flexible and expressive clinical documentation of functioning and standardizable data for comparability and learning. The ICF has practical limitations for classifying functional status information in clinical documentation but presents a valuable framework for organizing the information recorded in health records about patient functioning. This study advances the development of robust, ICF-based NLP technologies to analyze information on patient functioning and has significant implications for NLP-powered analysis of functional status information in disability benefits management, clinical care, and research.

Association of Social Support With Overall Survival and Healthcare Utilization in Patients With Aggressive Hematologic Malignancies

BACKGROUND

Social support plays a crucial role for patients with aggressive hematologic malignancies as they navigate their illness course. The aim of this study was to examine associations of social support with overall survival (OS) and healthcare utilization in this population.

METHODS

A cross-sectional secondary analysis was conducted using data from a prospective longitudinal cohort study of 251 hospitalized patients with aggressive hematologic malignancies at Massachusetts General Hospital from 2014 through 2017. Natural Language Processing (NLP) was used to identify the extent of patients' social support (limited vs adequate as defined by NLP-aided chart review of the electronic health record). Multivariable regression models were used to examine associations of social support with (1) OS, (2) death or readmission within 90 days of discharge from index hospitalization, (3) time to readmission within 90 days, and (4) index hospitalization length of stay.

RESULTS

Patients had a median age of 64 years (range, 19-93 years), and most were White (89.6%), male (68.9%), and married (65.3%). A plurality of patients had leukemia (42.2%) followed by lymphoma (37.9%) and myelodysplastic syndrome/myeloproliferative neoplasm (19.9%). Using NLP, we identified that 8.8% (n=22) of patients had limited social support. In multivariable analyses, limited social support was associated with worse OS (hazard ratio, 2.00; P=.042) and a higher likelihood of death or readmission within 90 days of discharge (odds ratio, 3.11; P=.043), but not with time to readmission within 90 days or with index hospitalization length of stay.

CONCLUSIONS

In this cohort of hospitalized patients with aggressive hematologic malignancies, we found associations of limited social support with lower OS and a higher likelihood of death or readmission within 90 days of hospital discharge. These findings underscore the utility of NLP for evaluating the extent of social support and the need for larger studies evaluating social support in patients with aggressive hematologic malignancies.

Deep learning-based natural language processing in ophthalmology: applications, challenges and future directions

PURPOSE OF REVIEW

Artificial intelligence (AI) is the fourth industrial revolution in mankind's history. Natural language processing (NLP) is a type of AI that transforms human language, to one that computers can interpret and process. NLP is still in the formative stages of development in healthcare, with promising applications and potential challenges in its applications. This review provides an overview of AI-based NLP, its applications in healthcare and ophthalmology, next-generation use case, as well as potential challenges in deployment.

RECENT FINDINGS

The integration of AI-based NLP systems into existing clinical care shows considerable promise in disease screening, risk stratification, and treatment monitoring, amongst others. Stakeholder collaboration, greater public acceptance, and advancing technologies will continue to shape the NLP landscape in healthcare and ophthalmology.

SUMMARY

Healthcare has always endeavored to be patient centric and personalized. For AI-based NLP systems to become an eventual reality in larger-scale applications, it is pertinent for key stakeholders to collaborate and address potential challenges in application. Ultimately, these would enable more equitable and generalizable use of NLP systems for the betterment of healthcare and society.

Viewpoint: An Information Extraction Framework for Disability Determination Using a Mental Functioning Use-Case (Preprint)

Natural language processing (NLP) in health care enables transformation of complex narrative information into high value products such as clinical decision support and adverse event monitoring in real time via the electronic health record (EHR). However, information technologies for mental health have consistently lagged because of the complexity of measuring and modeling mental health and illness. The use of NLP to support management of mental health conditions is a viable topic that has not been explored in depth. This paper provides a framework for the advanced application of NLP methods to identify, extract, and organize information on mental health and functioning to inform the decision-making process applied to assessing mental health. We present a use-case related to work disability, guided by the disability determination process of the US Social Security Administration (SSA). From this perspective, the following questions must be addressed about each problem that leads to a disability benefits claim: When did the problem occur and how long has it existed? How severe is it? Does it affect the person’s ability to work? and What is the source of the evidence about the problem? Our framework includes 4 dimensions of medical information that are central to assessing disability—temporal sequence and duration, severity, context, and information source. We describe key aspects of each dimension and promising approaches for application in mental functioning. For example, to address temporality, a complete functional timeline must be created with all relevant aspects of functioning such as intermittence, persistence, and recurrence. Severity of mental health symptoms can be successfully identified and extracted on a 4-level ordinal scale from absent to severe. Some NLP work has been reported on the extraction of context for specific cases of wheelchair use in clinical settings. We discuss the links between the task of information source assessment and work on source attribution, coreference resolution, event extraction, and rule-based methods. Gaps were identified in NLP applications that directly applied to the framework and in existing relevant annotated data sets. We highlighted NLP methods with the potential for advanced application in the field of mental functioning. Findings of this work will inform the development of instruments for supporting SSA adjudicators in their disability determination process. The 4 dimensions of medical information may have relevance for a broad array of individuals and organizations responsible for assessing mental health function and ability. Further, our framework with 4 specific dimensions presents significant opportunity for the application of NLP in the realm of mental health and functioning beyond the SSA setting, and it may support the development of robust tools and methods for decision-making related to clinical care, program implementation, and other outcomes.

Perspectives of Patients with Pre-existing Mobility Disability on the Process of Diagnosing Their Cancer

BACKGROUND

Mobility disability is the most common disability among adult Americans, estimated at 13.7% of the US population. Cancer prevalence is higher among people with mobility disability compared with the general population, yet people with disability experience disparities in cancer screening and treatment.

OBJECTIVE

We explored experiences of patients with mobility disability with the process of cancer diagnosis.

DESIGN

Open-ended individual interviews, which reached data saturation. Interviews were transcribed verbatim for conventional content analysis.

PARTICIPANTS

We interviewed 20 participants with pre-existing mobility disability that required the use of an assistive device or assistance with performance of activities of daily living and who were subsequently diagnosed with cancer (excluding melanoma).

KEY RESULTS

Concerns coalesced around five broad categories: inaccessibility of medical diagnostic equipment affecting the process of cancer diagnosis, attitudes of clinical staff about accommodating disability, dismissal of cancer signs/symptoms as emotional responses to chronic health conditions, misattributing cancer signs/symptoms to underlying disability, and attitudes about pursuing legal action for substandard care. Participants provided examples of how erroneous assumptions and potentially biased attitudes among clinicians interfered with the process of their cancer diagnosis, sometimes contributing to an insufficient workup and diagnostic delays.

CONCLUSIONS

Physical and attitudinal barriers affect the process of cancer diagnosis in people with mobility disability. Though people with mobility disability may be clinically complex, clinicians should be aware of the risks of diagnostic overshadowing (i.e., the misattribution of cancer signs/symptoms to underlying disability) and other erroneous assumptions that may affect timeliness of cancer diagnosis and quality of care. Further efforts, including educating clinicians about challenges in caring for persons with disability, should be considered to improve the process of cancer diagnosis for this population.

TRIAL REGISTRATION

N/A.

Automated Coding of Under-Studied Medical Concept Domains: Linking Physical Activity Reports to the International Classification of Functioning, Disability, and Health

Linking clinical narratives to standardized vocabularies and coding systems is a key component of unlocking the information in medical text for analysis. However, many domains of medical concepts, such as functional outcomes and social determinants of health, lack well-developed terminologies that can support effective coding of medical text. We present a framework for developing natural language processing (NLP) technologies for automated coding of medical information in under-studied domains, and demonstrate its applicability through a case study on physical mobility function. Mobility function is a component of many health measures, from post-acute care and surgical outcomes to chronic frailty and disability, and is represented as one domain of human activity in the International Classification of Functioning, Disability, and Health (ICF). However, mobility and other types of functional activity remain under-studied in the medical informatics literature, and neither the ICF nor commonly-used medical terminologies capture functional status terminology in practice. We investigated two data-driven paradigms, classification and candidate selection, to link narrative observations of mobility status to standardized ICF codes, using a dataset of clinical narratives from physical therapy encounters. Recent advances in language modeling and word embedding were used as features for established machine learning models and a novel deep learning approach, achieving a macro-averaged F-1 score of 84% on linking mobility activity reports to ICF codes. Both classification and candidate selection approaches present distinct strengths for automated coding in under-studied domains, and we highlight that the combination of (i) a small annotated data set; (ii) expert definitions of codes of interest; and (iii) a representative text corpus is sufficient to produce high-performing automated coding systems. This research has implications for continued development of language technologies to analyze functional status information, and the ongoing growth of NLP tools for a variety of specialized applications in clinical care and research.

Exploring Cancer Treatment Experiences for Patients With Preexisting Mobility Disability

OBJECTIVE

We explored the process of cancer care for patients with preexisting mobility disability, focusing on treatment decisions and experiences.

DESIGN

We recruited 20 participants with preexisting mobility disability, requiring use of an assistive device or assistance with activities of daily living, subsequently diagnosed with cancer (excluding skin cancers). We conducted open-ended individual interviews, which reached data saturation and were transcribed verbatim for conventional content analysis.

RESULTS

Concerns coalesced around 4 themes: disability-related healthcare experiences affect cancer treatment decisions; concerns about cancer treatment worsening functional impairments; access barriers; and limited provider awareness and biases about treating people with disability. Residual fear from previous medical interventions and concerns about exacerbating functional impairments influenced cancer treatment preferences. Participants also raised concerns that their underlying disability may be used to justify less aggressive treatment. Nevertheless, cancer treatment did exacerbate mobility difficulties for some participants. Inaccessible hospital rooms, lack of accessible medical equipment, and attitudinal barriers complicated treatments.

CONCLUSIONS

People with preexisting mobility disability experience barriers to cancer treatment, compromising quality of care and potentially outcomes. Further training and proactive planning for accommodating disability during cancer treatment and rehabilitation are warranted.

TO CLAIM CME CREDITS

Complete the self-assessment activity and evaluation online at http://www.physiatry.org/JournalCME.

CME OBJECTIVES

Upon completion of the article, the reader should be able to: (1) Recognize inadequate accommodations that compromise the diagnosis and treatment of a new cancer in patients with preexisting disability; (2) Recommend involving rehabilitation specialists in the process of care and clinical decision making from the time of cancer diagnosis for patients with preexisting disability newly diagnosed with malignancy; and (3) In the setting of accessibility barriers, facilitate efforts to accommodate patients with preexisting disability to improve quality of care in diagnosing and treating cancer.

LEVEL

Advanced.

ACCREDITATION

The Association of Academic Physiatrists is accredited by the Accreditation Council for Continuing Medical Education to provide continuing medical education for physicians.The Association of Academic Physiatrists designates this Journal-based CME activity for a maximum of 1.0 AMA PRA Category 1 Credit(s)™. Physicians should only claim credit commensurate with the extent of their participation in the activity.

Exploring the Process of Cancer Care for Patients With Pre-Existing Mobility Disability

PURPOSE

Approximately 13% of the US population report mobility disability. People with mobility disability experience healthcare disparities, including lower rates of cancer screening and substandard cancer care compared with nondisabled people. We explored clinicians' reports of aspects of diagnosing and treating three common cancer types among persons with pre-existing mobility disability.

METHODS

We used standard diagnosis codes and natural language processing to screen electronic health records (EHR) in the Research Patient Data Repository for patients with pre-existing chronic mobility impairment who were newly diagnosed with one of three common cancers (colorectal, prostate, and non-Hodgkin lymphoma) between 2005 and 2017. We eliminated numerous cases whose EHRs lacked essential information. We reviewed EHRs of 27 cases, using conventional content analysis to identify themes concerning their cancer diagnoses and treatments.

RESULTS

Clinicians' notations coalesced around four major themes: (1) patients' health risks raise concerns about diagnostic processes; (2) cancer signs or symptoms can be erroneously attributed to the patient's underlying disabling condition, delaying diagnosis; (3) disability complicates cancer treatment decisions; and (4) problems with equipment accessibility and disability accommodations impede cancer diagnoses.

DISCUSSION

Clinicians view patients with pre-existing mobility disability as often clinically complex, presenting challenges for diagnosing and treating their cancer. Nonetheless, these patients may experience substandard care because of disability-related problems. Given the growing population of people with mobility disability, further efforts to improve care quality and timeliness of diagnosis are warranted.

Automated Categorization of Systemic Disease and Duration From Electronic Medical Record System Data Using Finite-State Machine Modeling: Prospective Validation Study

BACKGROUND

One of the major challenges in the health care sector is that approximately 80% of generated data remains unstructured and unused. Since it is difficult to handle unstructured data from electronic medical record systems, it tends to be neglected for analyses in most hospitals and medical centers. Therefore, there is a need to analyze unstructured big data in health care systems so that we can optimally utilize and unearth all unexploited information from it.

OBJECTIVE

In this study, we aimed to extract a list of diseases and associated keywords along with the corresponding time durations from an indigenously developed electronic medical record system and describe the possibility of analytics from the acquired datasets.

METHODS

We propose a novel, finite-state machine to sequentially detect and cluster disease names from patients' medical history. We defined 3 states in the finite-state machine and transition matrix, which depend on the identified keyword. In addition, we also defined a state-change action matrix, which is essentially an action associated with each transition. The dataset used in this study was obtained from an indigenously developed electronic medical record system called eyeSmart that was implemented across a large, multitier ophthalmology network in India. The dataset included patients' past medical history and contained records of 10,000 distinct patients.

RESULTS

We extracted disease names and associated keywords by using the finite-state machine with an accuracy of 95%, sensitivity of 94.9%, and positive predictive value of 100%. For the extraction of the duration of disease, the machine's accuracy was 93%, sensitivity was 92.9%, and the positive predictive value was 100%.

CONCLUSIONS

We demonstrated that the finite-state machine we developed in this study can be used to accurately identify disease names, associated keywords, and time durations from a large cohort of patient records obtained using an electronic medical record system.

Exploring attitudes about developing cancer among patients with pre-existing mobility disability

OBJECTIVE

Mobility disability affects approximately 13.7% of the United States population, representing the most common disability type. People with mobility disability experience disparities in cancer screening and higher prevalence of some cancers compared to the general population. We sought to explore the attitudes of people with pre-existing mobility disability about their cancer diagnosis.

METHODS

We conducted open-ended individual interviews with 20 participants who had pre-existing mobility disability requiring use of an assistive device or assistance with performance of activities of daily living (ADLs), subsequently diagnosed with cancer (excluding skin cancers). Interviews reached data saturation and were transcribed verbatim for conventional content analysis.

RESULTS

Concerns coalesced around three major themes: sense of control over health conditions, seeking support, and recommendations for other people with disability seeking cancer care. Some participants described feeling a loss of control over their cancer diagnosis that they did not have regarding disability, while others suggested that disability presented greater challenges than their cancer diagnosis. Participants described seeking various forms of support, including emotional support (e.g., from friends and family), informational support (e.g., recommendations for seeking care), instrumental support (e.g., ADLs), and appraisal (e.g., self-reflection of personal qualities for fighting cancer). They provided recommendations, highlighting importance of self-advocacy and being attuned to changes in health status.

CONCLUSIONS

We found that people with pre-existing mobility disability and cancer express complex attitudes towards their cancer diagnosis. Findings may inform efforts to improve quality of relevant supports to meet the psychosocial needs of this population.

Can disability accommodation needs stored in electronic health records help providers prepare for patient visits? A qualitative study

Background

Embedding patient accommodation need in the electronic health record (EHR) has been proposed as one means to improve health care delivery to patients with disabilities. Accommodation need is not a standard field in commercial EHR software. However, some medical practices ask about accommodation need and store it in the EHR. Little is known about how the information is used, or barriers to its use. This exploratory-descriptive study examines whether and how information about patients’ disability-related accommodation needs stored in patient records is used in a primary health care center to plan for care.

Methods

Four focus groups (n = 35) were conducted with staff of a Federally Qualified Health Center that asks four accommodation questions at intake for the EHR. Respondents were asked how they learned about patient accommodation need, whether and how they used the information in the EHR, barriers to its use, and recommendations for where accommodation information should reside. A brief semi-structured interview was conducted with patients who had indicated an accommodation need (n = 12) to learn their experience at their most recent appointment. The qualitative data were coded using structural coding and themes extracted.

Results

Five themes were identified from the focus groups: (1) staff often do not know accommodation needs before the patient’s arrival; (2) electronic patient information systems offer helpful information, but their structure creates challenges and information gaps; (3) accommodations for a patient’s disability occur, but are developed at the time of visit; (4) provider knowledge of a regular patient is often the basis for accommodation preparation; and (5) staff recognize benefits to advance knowledge of accommodation needs and are supportive of methods to enable it. Most patients did not recall indicating accommodation need on the intake form. However, they expected to be accommodated based upon the medical practice’s knowledge of them.

Conclusions

Patient accommodation information in the EHR can be useful for visit planning. However, the structure must enable transfer of information between scheduling and direct care and be updatable as needs change. Flexibility to record a variety of needs, visibility to differentiate accommodation need from other alerts, and staff education about needs were recommended.