Association of Weight Loss in Ambulatory Care Settings With First Diagnosis of Lung Cancer in the US.

Importance: Lung cancer, the US's leading cause of cancer death, is often diagnosed following presentation to health care settings with symptoms, and many patients present with late-stage disease. Objective: To investigate the association between weight loss and subsequent diagnosis of incident lung cancer in an ambulatory care population and to assess whether recorded weight change had higher odds of lung cancer diagnosis than objective measurements. Design, Setting, and Participants: This case-control study included patients visiting a US academic medical center between January 1, 2012, and December 31, 2019. Data were derived from US ambulatory care electronic health records from the University of Washington Medical Center linked to the local Surveillance, Epidemiology, and End Results cancer registry. Cases were identified from patients who had a primary lung cancer diagnosis between 2012 and 2019; controls were matched on age, sex, smoking status, and presenting to the same type of ambulatory clinic as cases. Data were analyzed from March 2022 through January 2023. Exposure: Continuous and categorical weight change were assessed. Main Outcomes and Measures: Odds ratios estimating the likelihood of a diagnosis of lung cancer were calculated using univariable and multivariable conditional logistic regression. Results: A total of 625 patients aged 40 years or older with a first primary lung cancer diagnosis and 4606 matched controls were included (1915 [36.6%] ages 60 to 69 years; 418 [8.0%] Asian, 389 [7.4%] Black, 4092 [78.2%] White). In unadjusted analyses, participants with weight loss of 1% to 3% (odds ratio [OR], 1.12; 95% CI, 0.88-1.41), 3% to 5% (OR, 1.36; 95% CI, 0.99-1.88), or 5% to 10% (OR, 1.23; 95% CI, 0.82-1.85) over a 2-year period did not have statistically significantly increased risk of lung cancer diagnosis compared with those who maintained a steady weight. However, participants with weight loss of 10% to 50% had more than twice the odds of a lung cancer diagnosis (OR, 2.27; 95% CI, 1.27-4.05). Most categories of weight loss showed significant associations with an increased risk of lung cancer diagnosis for at least 6 months prior to diagnosis. Patients who had weight loss both recorded in clinicians' notes and measured had higher odds of lung cancer compared with patients who had only recorded (OR, 1.26; odds; 95% CI, 1.04-1.52) or measured (OR, 8.53; 95% CI, 6.99-10.40) weight loss. Conclusions and Relevance: In this case-control study, weight loss in the prior 6 months was associated with incident lung cancer diagnosis and was present whether weight loss was recorded as a symptom by the clinician or based on changes in routinely measured weight, demonstrating a potential opportunity for early diagnosis. The association between measured and recorded weight loss by clinicians presents novel results for the US.

From benchmark to bedside: transfer learning from social media to patient-provider text messages for suicide risk prediction.

OBJECTIVE: Compared to natural language processing research investigating suicide risk prediction with social media (SM) data, research utilizing data from clinical settings are scarce. However, the utility of models trained on SM data in text from clinical settings remains unclear. In addition, commonly used performance metrics do not directly translate to operational value in a real-world deployment. The objectives of this study were to evaluate the utility of SM-derived training data for suicide risk prediction in a clinical setting and to develop a metric of the clinical utility of automated triage of patient messages for suicide risk. MATERIALS AND METHODS: Using clinical data, we developed a Bidirectional Encoder Representations from Transformers-based suicide risk detection model to identify messages indicating potential suicide risk. We used both annotated and unlabeled suicide-related SM posts for multi-stage transfer learning, leveraging customized contemporary learning rate schedules. We also developed a novel metric estimating predictive models' potential to reduce follow-up delays with patients in distress and used it to assess model utility. RESULTS: Multi-stage transfer learning from SM data outperformed baseline approaches by traditional classification performance metrics, improving performance from 0.734 to a best F1 score of 0.797. Using this approach for automated triage could reduce response times by 15 minutes per urgent message. DISCUSSION: Despite differences in data characteristics and distribution, publicly available SM data benefit clinical suicide risk prediction when used in conjunction with contemporary transfer learning techniques. Estimates of time saved due to automated triage indicate the potential for the practical impact of such models when deployed as part of established suicide prevention interventions. CONCLUSIONS: This work demonstrates a pathway for leveraging publicly available SM data toward improving risk assessment, paving the way for better clinical care and improved clinical outcomes.

Symptoms and signs of lung cancer prior to diagnosis: case-control study using electronic health records from ambulatory care within a large US-based tertiary care centre.

OBJECTIVE: Lung cancer is the most common cause of cancer-related death in the USA. While most patients are diagnosed following symptomatic presentation, no studies have compared symptoms and physical examination signs at or prior to diagnosis from electronic health records (EHRs) in the USA. We aimed to identify symptoms and signs in patients prior to diagnosis in EHR data. DESIGN: Case-control study. SETTING: Ambulatory care clinics at a large tertiary care academic health centre in the USA. PARTICIPANTS, OUTCOMES: We studied 698 primary lung cancer cases in adults diagnosed between 1 January 2012 and 31 December 2019, and 6841 controls matched by age, sex, smoking status and type of clinic. Coded and free-text data from the EHR were extracted from 2 years prior to diagnosis date for cases and index date for controls. Univariate and multivariable conditional logistic regression were used to identify symptoms and signs associated with lung cancer at time of diagnosis, and 1, 3, 6 and 12 months before the diagnosis/index dates. RESULTS: Eleven symptoms and signs recorded during the study period were associated with a significantly higher chance of being a lung cancer case in multivariable analyses. Of these, seven were significantly associated with lung cancer 6 months prior to diagnosis: haemoptysis (OR 3.2, 95% CI 1.9 to 5.3), cough (OR 3.1, 95% CI 2.4 to 4.0), chest crackles or wheeze (OR 3.1, 95% CI 2.3 to 4.1), bone pain (OR 2.7, 95% CI 2.1 to 3.6), back pain (OR 2.5, 95% CI 1.9 to 3.2), weight loss (OR 2.1, 95% CI 1.5 to 2.8) and fatigue (OR 1.6, 95% CI 1.3 to 2.1). CONCLUSIONS: Patients diagnosed with lung cancer appear to have symptoms and signs recorded in the EHR that distinguish them from similar matched patients in ambulatory care, often 6 months or more before diagnosis. These findings suggest opportunities to improve the diagnostic process for lung cancer.

Deep Representations of First-person Pronouns for Prediction of Depression Symptom Severity.

Prior work has shown that analyzing the use of first-person singular pronouns can provide insight into individuals' mental status, especially depression symptom severity. These findings were generated by counting frequencies of first-person singular pronouns in text data. However, counting doesn't capture how these pronouns are used. Recent advances in neural language modeling have leveraged methods generating contextual embeddings. In this study, we sought to utilize the embeddings of first-person pronouns obtained from contextualized language representation models to capture ways these pronouns are used, to analyze mental status. De-identified text messages sent during online psychotherapy with weekly assessment of depression severity were used for evaluation. Results indicate the advantage of contextualized first-person pronoun embeddings over standard classification token embeddings and frequency-based pronoun analysis results in predicting depression symptom severity. This suggests contextual representations of first-person pronouns can enhance the predictive utility of language used by people with depression symptoms.

How Timely Is Diagnosis of Lung Cancer? Cohort Study of Individuals with Lung Cancer Presenting in Ambulatory Care in the United States.

The diagnosis of lung cancer in ambulatory settings is often challenging due to non-specific clinical presentation, but there are currently no clinical quality measures (CQMs) in the United States used to identify areas for practice improvement in diagnosis. We describe the pre-diagnostic time intervals among a retrospective cohort of 711 patients identified with primary lung cancer from 2012-2019 from ambulatory care clinics in Seattle, Washington USA. Electronic health record data were extracted for two years prior to diagnosis, and Natural Language Processing (NLP) applied to identify symptoms/signs from free text clinical fields. Time points were defined for initial symptomatic presentation, chest imaging, specialist consultation, diagnostic confirmation, and treatment initiation. Median and interquartile ranges (IQR) were calculated for intervals spanning these time points. The mean age of the cohort was 67.3 years, 54.1% had Stage III or IV disease and the majority were diagnosed after clinical presentation (94.5%) rather than screening (5.5%). Median intervals from first recorded symptoms/signs to diagnosis was 570 days (IQR 273-691), from chest CT or chest X-ray imaging to diagnosis 43 days (IQR 11-240), specialist consultation to diagnosis 72 days (IQR 13-456), and from diagnosis to treatment initiation 7 days (IQR 0-36). Symptoms/signs associated with lung cancer can be identified over a year prior to diagnosis using NLP, highlighting the need for CQMs to improve timeliness of diagnosis.

Identifying opportunities for informatics-supported suicide prevention: the case of Caring Contacts.

Suicide is the tenth leading cause of death in the United States. Caring Contacts (CC) is a suicide prevention intervention involving care teams sending brief messages expressing unconditional care to patients at risk of suicide. Despite solid evidence for its effectiveness, CC has not been broadly adopted by healthcare organizations. Technology has the potential to facilitate CC if barriers to adoption were better understood. This qualitative study assessed the needs of organizational stakeholders for a CC informatics tool through interviews that investigated barriers to adoption, workflow challenges, and participant-suggested design opportunities. We identified contextual barriers related to environment, intervention parameters, and technology use. Workflow challenges included time-consuming simple tasks, risk assessment and management, the cognitive demands of authoring follow-up messages, accessing and aggregating information across systems, and team communication. To address these needs, we propose design considerations that focus on automation, cognitive support, and data and workflow integration. Future work will incorporate these findings to design informatics tools supporting broader adoption of Caring Contacts.

Neuropsychological test validation of speech markers of cognitive impairment in the Framingham Cognitive Aging Cohort.

AIM: Although clinicians primarily diagnose dementia based on a combination of metrics such as medical history and formal neuropsychological tests, recent work using linguistic analysis of narrative speech to identify dementia has shown promising results. We aim to build upon research by Thomas JA & Burkardt HA et al. (J Alzheimers Dis. 2020;76:905-22) and Alhanai et al. (arXiv:1710.07551v1. 2020) on the Framingham Heart Study (FHS) Cognitive Aging Cohort by 1) demonstrating the predictive capability of linguistic analysis in differentiating cognitively normal from cognitively impaired participants and 2) comparing the performance of the original linguistic features with the performance of expanded features. METHODS: Data were derived from a subset of the FHS Cognitive Aging Cohort. We analyzed a sub-selection of 98 participants, which provided 127 unique audio files and clinical observations (n = 127, female = 47%, cognitively impaired = 43%). We built on previous work which extracted original linguistic features from transcribed audio files by extracting expanded features. We used both feature sets to train logistic regression classifiers to distinguish cognitively normal from cognitively impaired participants and compared the predictive power of the original and expanded linguistic feature sets, and participants' Mini-Mental State Examination (MMSE) scores. RESULTS: Based on the area under the receiver-operator characteristic curve (AUC) of the models, both the original (AUC = 0.882) and expanded (AUC = 0.883) feature sets outperformed MMSE (AUC = 0.870) in classifying cognitively impaired and cognitively normal participants. Although the original and expanded feature sets had similar AUC, the expanded feature set showed better positive and negative predictive value [expanded: positive predictive value (PPV) = 0.738, negative predictive value (NPV) = 0.889; original: PPV = 0.701, NPV = 0.869]. CONCLUSIONS: Linguistic analysis has been shown to be a potentially powerful tool for clinical use in classifying cognitive impairment. This study expands the work of several others, but further studies into the plausibility of speech analysis in clinical use are vital to ensure the validity of speech analysis for clinical classification of cognitive impairment.

Behavioral Activation and Depression Symptomatology: Longitudinal Assessment of Linguistic Indicators in Text-Based Therapy Sessions.

BACKGROUND: Behavioral activation (BA) is rooted in the behavioral theory of depression, which states that increased exposure to meaningful, rewarding activities is a critical factor in the treatment of depression. Assessing constructs relevant to BA currently requires the administration of standardized instruments, such as the Behavioral Activation for Depression Scale (BADS), which places a burden on patients and providers, among other potential limitations. Previous work has shown that depressed and nondepressed individuals may use language differently and that automated tools can detect these differences. The increasing use of online, chat-based mental health counseling presents an unparalleled resource for automated longitudinal linguistic analysis of patients with depression, with the potential to illuminate the role of reward exposure in recovery. OBJECTIVE: This work investigated how linguistic indicators of planning and participation in enjoyable activities identified in online, text-based counseling sessions relate to depression symptomatology over time. METHODS: Using distributional semantics methods applied to a large corpus of text-based online therapy sessions, we devised a set of novel BA-related categories for the Linguistic Inquiry and Word Count (LIWC) software package. We then analyzed the language used by 10,000 patients in online therapy chat logs for indicators of activation and other depression-related markers using LIWC. RESULTS: Despite their conceptual and operational differences, both previously established LIWC markers of depression and our novel linguistic indicators of activation were strongly associated with depression scores (Patient Health Questionnaire [PHQ]-9) and longitudinal patient trajectories. Emotional tone; pronoun rates; words related to sadness, health, and biology; and BA-related LIWC categories appear to be complementary, explaining more of the variance in the PHQ score together than they do independently. CONCLUSIONS: This study enables further work in automated diagnosis and assessment of depression, the refinement of BA psychotherapeutic strategies, and the development of predictive models for decision support.

StayHome: A FHIR-Native Mobile COVID-19 Symptom Tracker and Public Health Reporting Tool.

As the COVID-19 pandemic continues to unfold and states experience the impacts of reopened economies, it is critical to efficiently manage new outbreaks through widespread testing and monitoring of both new and possible cases. Existing labor-intensive public health workflows may benefit from information collection directly from individuals through patient-reported outcomes (PROs) systems. Our objective was to develop a reusable, mobile-friendly application for collecting PROs and experiences to support COVID-19 symptom self-monitoring and data sharing with appropriate public health agencies, using Fast Healthcare Interoperability Resources (FHIR) for interoperability. We conducted a needs assessment and designed and developed StayHome, a mobile PRO administration tool. FHIR serves as the primary data model and driver of business logic. Keycloak, AWS, Docker, and other technologies were used for deployment. Several FHIR modules were used to create a novel "FHIR-native" application design. By leveraging FHIR to shape not only the interface strategy but also the information architecture of the application, StayHome enables the consistent standards-based representation of data and reduces the barrier to integration with public health information systems. FHIR supported rapid application development by providing a domain-appropriate data model and tooling. FHIR modules and implementation guides were referenced in design and implementation. However, there are gaps in the FHIR specification which must be recognized and addressed appropriately. StayHome is live and accessible to the public at https://stayhome.app. The code and resources required to build and deploy the application are available from https://github.com/uwcirg/stayhome-project.

Assessing the Utility of Language and Voice Biomarkers to Predict Cognitive Impairment in the Framingham Heart Study Cognitive Aging Cohort Data.

BACKGROUND: There is a need for fast, accessible, low-cost, and accurate diagnostic methods for early detection of cognitive decline. Dementia diagnoses are usually made years after symptom onset, missing a window of opportunity for early intervention. OBJECTIVE: To evaluate the use of recorded voice features as proxies for cognitive function by using neuropsychological test measures and existing dementia diagnoses. METHODS: This study analyzed 170 audio recordings, transcripts, and paired neuropsychological test results from 135 participants selected from the Framingham Heart Study (FHS), which includes 97 recordings of cognitively normal participants and 73 recordings of cognitively impaired participants. Acoustic and linguistic features of the voice samples were correlated with cognitive performance measures to verify their association. RESULTS: Language and voice features, when combined with demographic variables, performed with an AUC of 0.942 (95% CI 0.929-0.983) in predicting cognitive status. Features with good predictive power included the acoustic features mean spectral slope in the 500-1500 Hz band, variation in the F2 bandwidth, and variation in the Mel-Frequency Cepstral Coefficient (MFCC) 1; the demographic features employment, education, and age; and the text features of number of words, number of compound words, number of unique nouns, and number of proper names. CONCLUSION: Several linguistic and acoustic biomarkers show correlations and predictive power with regard to neuropsychological testing results and cognitive impairment diagnoses, including dementia. This initial study paves the way for a follow-up comprehensive study incorporating the entire FHS cohort.

Predicting Adverse Drug-Drug Interactions with Neural Embedding of Semantic Predications

The identification of drug-drug interactions (DDIs) is important for patient safety; yet, compared to other pharmacovigilance work, a limited amount of research has been conducted in this space. Recent work has successfully applied a method of deriving distributed vector representations from structured biomedical knowledge, known as Embedding of Semantic Predications (ESP), to the problem of predicting individual drug side effects. In the current paper we extend this work by applying ESP to the problem of predicting polypharmacy side-effects for particular drug combinations, building on a recent reconceptualization of this problem as a network of drug nodes connected by side effect edges. We evaluate ESP embeddings derived from the resulting graph on a side-effect prediction task against a previously reported graph convolutional neural network approach, using the same data and evaluation methods. We demonstrate that ESP models perform better, while being faster to train, more re-usable, and significantly simpler.