RESUMO
Importance: The ways in which we access, acquire, and use data in clinical trials have evolved very little over time, resulting in a fragmented and inefficient system that limits the amount and quality of evidence that can be generated. Observations: Clinical trial design has advanced steadily over several decades. Yet the infrastructure for clinical trial data collection remains expensive and labor intensive and limits the amount of evidence that can be collected to inform whether and how interventions work for different patient populations. Meanwhile, there is increasing demand for evidence from randomized clinical trials to inform regulatory decisions, payment decisions, and clinical care. Although substantial public and industry investment in advancing electronic health record interoperability, data standardization, and the technology systems used for data capture have resulted in significant progress on various aspects of data generation, there is now a need to combine the results of these efforts and apply them more directly to the clinical trial data infrastructure. Conclusions and Relevance: We describe a vision for a modernized infrastructure that is centered around 2 related concepts. First, allowing the collection and rigorous evaluation of multiple data sources and types and, second, enabling the possibility to reuse health data for multiple purposes. We address the need for multidisciplinary collaboration and suggest ways to measure progress toward this goal.
RESUMO
Rheumatoid arthritis (RA) management lean toward achieving remission or low-disease activity. In this study, we conducted single-cell RNA sequencing (scRNAseq) of peripheral blood mononuclear cells (PBMCs) from 36 individuals (18 RA patients and 18 matched controls, accounting for age, sex, race, and ethnicity), to identify disease-relevant cell subsets and cell type-specific signatures associated with disease activity. Our analysis revealed 18 distinct PBMC subsets, including an IFITM3 overexpressing Interferon-activated (IFN-activated) monocyte subset. We observed an increase in CD4+ T effector memory cells in patients with moderate to high disease activity (DAS28-CRP ≥ 3.2), and a decrease in non-classical monocytes in patients with low disease activity or remission (DAS28-CRP < 3.2). Pseudobulk analysis by cell type identified 168 differentially expressed genes between RA and matched controls, with a downregulation of pro-inflammatory genes in the gamma-delta T cells subset, alteration of genes associated with RA predisposition in the IFN-activated subset, and non-classical monocytes. Additionally, we identified a gene signature associated with moderate-high disease activity, characterized by upregulation of pro-inflammatory genes such as TNF, JUN, EGR1, IFIT2, MAFB, G0S2, and downregulation of genes including HLA-DQB1, HLA-DRB5, TNFSF13B. Notably, cell-cell communication analysis revealed an upregulation of signaling pathways, including VISTA, in both moderate-high and remission-low disease activity contexts. Our findings provide valuable insights into the systemic cellular and molecular mechanisms underlying RA disease activity.
RESUMO
Artificial intelligence (AI) has the potential to transform every facet of cardiovascular practice and research. The exponential rise in technology powered by AI is defining new frontiers in cardiovascular care, with innovations that span novel diagnostic modalities, new digital native biomarkers of disease, and high-performing tools evaluating care quality and prognosticating clinical outcomes. These digital innovations promise expanded access to cardiovascular screening and monitoring, especially among those without access to high-quality, specialized care historically. Moreover, AI is propelling biological and clinical discoveries that will make future cardiovascular care more personalized, precise, and effective. The review brings together these diverse AI innovations, highlighting developments in multimodal cardiovascular AI across clinical practice and biomedical discovery, and envisioning this new future backed by contemporary science and emerging discoveries. Finally, we define the critical path and the safeguards essential to realizing this AI-enabled future that helps achieve optimal cardiovascular health and outcomes for all.
Assuntos
Inteligência Artificial , Doenças Cardiovasculares , Humanos , Doenças Cardiovasculares/terapia , Doenças Cardiovasculares/diagnóstico , Cardiologia/métodos , Cardiologia/tendênciasRESUMO
OBJECTIVE: Although supervised machine learning is popular for information extraction from clinical notes, creating large annotated datasets requires extensive domain expertise and is time-consuming. Meanwhile, large language models (LLMs) have demonstrated promising transfer learning capability. In this study, we explored whether recent LLMs could reduce the need for large-scale data annotations. MATERIALS AND METHODS: We curated a dataset of 769 breast cancer pathology reports, manually labeled with 12 categories, to compare zero-shot classification capability of the following LLMs: GPT-4, GPT-3.5, Starling, and ClinicalCamel, with task-specific supervised classification performance of 3 models: random forests, long short-term memory networks with attention (LSTM-Att), and the UCSF-BERT model. RESULTS: Across all 12 tasks, the GPT-4 model performed either significantly better than or as well as the best supervised model, LSTM-Att (average macro F1-score of 0.86 vs 0.75), with advantage on tasks with high label imbalance. Other LLMs demonstrated poor performance. Frequent GPT-4 error categories included incorrect inferences from multiple samples and from history, and complex task design, and several LSTM-Att errors were related to poor generalization to the test set. DISCUSSION: On tasks where large annotated datasets cannot be easily collected, LLMs can reduce the burden of data labeling. However, if the use of LLMs is prohibitive, the use of simpler models with large annotated datasets can provide comparable results. CONCLUSIONS: GPT-4 demonstrated the potential to speed up the execution of clinical NLP studies by reducing the need for large annotated datasets. This may increase the utilization of NLP-based variables and outcomes in clinical studies.
RESUMO
Importance: The introduction of large language models (LLMs), such as Generative Pre-trained Transformer 4 (GPT-4; OpenAI), has generated significant interest in health care, yet studies evaluating their performance in a clinical setting are lacking. Determination of clinical acuity, a measure of a patient's illness severity and level of required medical attention, is one of the foundational elements of medical reasoning in emergency medicine. Objective: To determine whether an LLM can accurately assess clinical acuity in the emergency department (ED). Design, Setting, and Participants: This cross-sectional study identified all adult ED visits from January 1, 2012, to January 17, 2023, at the University of California, San Francisco, with a documented Emergency Severity Index (ESI) acuity level (immediate, emergent, urgent, less urgent, or nonurgent) and with a corresponding ED physician note. A sample of 10â¯000 pairs of ED visits with nonequivalent ESI scores, balanced for each of the 10 possible pairs of 5 ESI scores, was selected at random. Exposure: The potential of the LLM to classify acuity levels of patients in the ED based on the ESI across 10â¯000 patient pairs. Using deidentified clinical text, the LLM was queried to identify the patient with a higher-acuity presentation within each pair based on the patients' clinical history. An earlier LLM was queried to allow comparison with this model. Main Outcomes and Measures: Accuracy score was calculated to evaluate the performance of both LLMs across the 10â¯000-pair sample. A 500-pair subsample was manually classified by a physician reviewer to compare performance between the LLMs and human classification. Results: From a total of 251â¯401 adult ED visits, a balanced sample of 10â¯000 patient pairs was created wherein each pair comprised patients with disparate ESI acuity scores. Across this sample, the LLM correctly inferred the patient with higher acuity for 8940 of 10â¯000 pairs (accuracy, 0.89 [95% CI, 0.89-0.90]). Performance of the comparator LLM (accuracy, 0.84 [95% CI, 0.83-0.84]) was below that of its successor. Among the 500-pair subsample that was also manually classified, LLM performance (accuracy, 0.88 [95% CI, 0.86-0.91]) was comparable with that of the physician reviewer (accuracy, 0.86 [95% CI, 0.83-0.89]). Conclusions and Relevance: In this cross-sectional study of 10â¯000 pairs of ED visits, the LLM accurately identified the patient with higher acuity when given pairs of presenting histories extracted from patients' first ED documentation. These findings suggest that the integration of an LLM into ED workflows could enhance triage processes while maintaining triage quality and warrants further investigation.
Assuntos
Serviço Hospitalar de Emergência , Gravidade do Paciente , Humanos , Serviço Hospitalar de Emergência/estatística & dados numéricos , Estudos Transversais , Adulto , Masculino , Feminino , Pessoa de Meia-Idade , Índice de Gravidade de Doença , São FranciscoRESUMO
Importance: Large language models (LLMs) possess a range of capabilities which may be applied to the clinical domain, including text summarization. As ambient artificial intelligence scribes and other LLM-based tools begin to be deployed within healthcare settings, rigorous evaluations of the accuracy of these technologies are urgently needed. Objective: To investigate the performance of GPT-4 and GPT-3.5-turbo in generating Emergency Department (ED) discharge summaries and evaluate the prevalence and type of errors across each section of the discharge summary. Design: Cross-sectional study. Setting: University of California, San Francisco ED. Participants: We identified all adult ED visits from 2012 to 2023 with an ED clinician note. We randomly selected a sample of 100 ED visits for GPT-summarization. Exposure: We investigate the potential of two state-of-the-art LLMs, GPT-4 and GPT-3.5-turbo, to summarize the full ED clinician note into a discharge summary. Main Outcomes and Measures: GPT-3.5-turbo and GPT-4-generated discharge summaries were evaluated by two independent Emergency Medicine physician reviewers across three evaluation criteria: 1) Inaccuracy of GPT-summarized information; 2) Hallucination of information; 3) Omission of relevant clinical information. On identifying each error, reviewers were additionally asked to provide a brief explanation for their reasoning, which was manually classified into subgroups of errors. Results: From 202,059 eligible ED visits, we randomly sampled 100 for GPT-generated summarization and then expert-driven evaluation. In total, 33% of summaries generated by GPT-4 and 10% of those generated by GPT-3.5-turbo were entirely error-free across all evaluated domains. Summaries generated by GPT-4 were mostly accurate, with inaccuracies found in only 10% of cases, however, 42% of the summaries exhibited hallucinations and 47% omitted clinically relevant information. Inaccuracies and hallucinations were most commonly found in the Plan sections of GPT-generated summaries, while clinical omissions were concentrated in text describing patients' Physical Examination findings or History of Presenting Complaint. Conclusions and Relevance: In this cross-sectional study of 100 ED encounters, we found that LLMs could generate accurate discharge summaries, but were liable to hallucination and omission of clinically relevant information. A comprehensive understanding of the location and type of errors found in GPT-generated clinical text is important to facilitate clinician review of such content and prevent patient harm.
RESUMO
Detecting epistatic drivers of human phenotypes is a considerable challenge. Traditional approaches use regression to sequentially test multiplicative interaction terms involving pairs of genetic variants. For higher-order interactions and genome-wide large-scale data, this strategy is computationally intractable. Moreover, multiplicative terms used in regression modeling may not capture the form of biological interactions. Building on the Predictability, Computability, Stability (PCS) framework, we introduce the epiTree pipeline to extract higher-order interactions from genomic data using tree-based models. The epiTree pipeline first selects a set of variants derived from tissue-specific estimates of gene expression. Next, it uses iterative random forests (iRF) to search training data for candidate Boolean interactions (pairwise and higher-order). We derive significance tests for interactions, based on a stabilized likelihood ratio test, by simulating Boolean tree-structured null (no epistasis) and alternative (epistasis) distributions on hold-out test data. Finally, our pipeline computes PCS epistasis p-values that probabilisticly quantify improvement in prediction accuracy via bootstrap sampling on the test set. We validate the epiTree pipeline in two case studies using data from the UK Biobank: predicting red hair and multiple sclerosis (MS). In the case of predicting red hair, epiTree recovers known epistatic interactions surrounding MC1R and novel interactions, representing non-linearities not captured by logistic regression models. In the case of predicting MS, a more complex phenotype than red hair, epiTree rankings prioritize novel interactions surrounding HLA-DRB1, a variant previously associated with MS in several populations. Taken together, these results highlight the potential for epiTree rankings to help reduce the design space for follow up experiments.
Assuntos
Epistasia Genética , Estudo de Associação Genômica Ampla , Humanos , Estudo de Associação Genômica Ampla/métodos , Fenótipo , Herança Multifatorial/genética , Modelos Logísticos , Polimorfismo de Nucleotídeo ÚnicoRESUMO
With the rapid growth of interest in and use of large language models (LLMs) across various industries, we are facing some crucial and profound ethical concerns, especially in the medical field. The unique technical architecture and purported emergent abilities of LLMs differentiate them substantially from other artificial intelligence (AI) models and natural language processing techniques used, necessitating a nuanced understanding of LLM ethics. In this Viewpoint, we highlight ethical concerns stemming from the perspectives of users, developers, and regulators, notably focusing on data privacy and rights of use, data provenance, intellectual property contamination, and broad applications and plasticity of LLMs. A comprehensive framework and mitigating strategies will be imperative for the responsible integration of LLMs into medical practice, ensuring alignment with ethical principles and safeguarding against potential societal risks.
Assuntos
Inteligência Artificial , Processamento de Linguagem Natural , Humanos , Inteligência Artificial/ética , Propriedade IntelectualRESUMO
BACKGROUND: The Mayo endoscopic subscore (MES) is an important quantitative measure of disease activity in ulcerative colitis. Colonoscopy reports in routine clinical care usually characterize ulcerative colitis disease activity using free text description, limiting their utility for clinical research and quality improvement. We sought to develop algorithms to classify colonoscopy reports according to their MES. METHODS: We annotated 500 colonoscopy reports from 2 health systems. We trained and evaluated 4 classes of algorithms. Our primary outcome was accuracy in identifying scorable reports (binary) and assigning an MES (ordinal). Secondary outcomes included learning efficiency, generalizability, and fairness. RESULTS: Automated machine learning models achieved 98% and 97% accuracy on the binary and ordinal prediction tasks, outperforming other models. Binary models trained on the University of California, San Francisco data alone maintained accuracy (96%) on validation data from Zuckerberg San Francisco General. When using 80% of the training data, models remained accurate for the binary task (97% [n = 320]) but lost accuracy on the ordinal task (67% [n = 194]). We found no evidence of bias by gender (Pâ =â .65) or area deprivation index (Pâ =â .80). CONCLUSIONS: We derived a highly accurate pair of models capable of classifying reports by their MES and recognizing when to abstain from prediction. Our models were generalizable on outside institution validation. There was no evidence of algorithmic bias. Our methods have the potential to enable retrospective studies of treatment effectiveness, prospective identification of patients meeting study criteria, and quality improvement efforts in inflammatory bowel diseases.
Our accurate pair of models automatically classify colonoscopy reports by Mayo endoscopic subscore and abstain from prediction appropriately. Our methods can enable large-scale electronic health record studies of treatment effectiveness, prospective identification of patients for clinical trials, and quality improvement efforts in ulcerative colitis.
RESUMO
OBJECTIVES: Vedolizumab (VDZ) and ustekinumab (UST) are second-line treatments in pediatric patients with ulcerative colitis (UC) refractory to antitumor necrosis factor (anti-TNF) therapy. Pediatric studies comparing the effectiveness of these medications are lacking. Using a registry from ImproveCareNow (ICN), a global research network in pediatric inflammatory bowel disease, we compared the effectiveness of UST and VDZ in anti-TNF refractory UC. METHODS: We performed a propensity-score weighted regression analysis to compare corticosteroid-free clinical remission (CFCR) at 6 months from starting second-line therapy. Sensitivity analyses tested the robustness of our findings to different ways of handling missing outcome data. Secondary analyses evaluated alternative proxies of response and infection risk. RESULTS: Our cohort included 262 patients on VDZ and 74 patients on UST. At baseline, the two groups differed on their mean pediatric UC activity index (PUCAI) (p = 0.03) but were otherwise similar. At Month 6, 28.3% of patients on VDZ and 25.8% of those on UST achieved CFCR (p = 0.76). Our primary model showed no difference in CFCR (odds ratio: 0.81; 95% confidence interval [CI]: 0.41-1.59) (p = 0.54). The time to biologic discontinuation was similar in both groups (hazard ratio: 1.26; 95% CI: 0.76-2.08) (p = 0.36), with the reference group being VDZ, and we found no differences in clinical response, growth parameters, hospitalizations, surgeries, infections, or malignancy risk. Sensitivity analyses supported these findings of similar effectiveness. CONCLUSIONS: UST and VDZ are similarly effective for inducing clinical remission in anti-TNF refractory UC in pediatric patients. Providers should consider safety, tolerability, cost, and comorbidities when deciding between these therapies.
Assuntos
Anticorpos Monoclonais Humanizados , Colite Ulcerativa , Fármacos Gastrointestinais , Ustekinumab , Humanos , Colite Ulcerativa/tratamento farmacológico , Ustekinumab/uso terapêutico , Feminino , Masculino , Criança , Anticorpos Monoclonais Humanizados/uso terapêutico , Adolescente , Fármacos Gastrointestinais/uso terapêutico , Resultado do Tratamento , Fator de Necrose Tumoral alfa/antagonistas & inibidores , Indução de Remissão/métodos , Pontuação de Propensão , Sistema de RegistrosRESUMO
Outpatient clinical notes are a rich source of information regarding drug safety. However, data in these notes are currently underutilized for pharmacovigilance due to methodological limitations in text mining. Large language models (LLMs) like Bidirectional Encoder Representations from Transformers (BERT) have shown progress in a range of natural language processing tasks but have not yet been evaluated on adverse event (AE) detection. We adapted a new clinical LLM, University of California - San Francisco (UCSF)-BERT, to identify serious AEs (SAEs) occurring after treatment with a non-steroid immunosuppressant for inflammatory bowel disease (IBD). We compared this model to other language models that have previously been applied to AE detection. We annotated 928 outpatient IBD notes corresponding to 928 individual patients with IBD for all SAE-associated hospitalizations occurring after treatment with a non-steroid immunosuppressant. These notes contained 703 SAEs in total, the most common of which was failure of intended efficacy. Out of eight candidate models, UCSF-BERT achieved the highest numerical performance on identifying drug-SAE pairs from this corpus (accuracy 88-92%, macro F1 61-68%), with 5-10% greater accuracy than previously published models. UCSF-BERT was significantly superior at identifying hospitalization events emergent to medication use (P < 0.01). LLMs like UCSF-BERT achieve numerically superior accuracy on the challenging task of SAE detection from clinical notes compared with prior methods. Future work is needed to adapt this methodology to improve model performance and evaluation using multicenter data and newer architectures like Generative pre-trained transformer (GPT). Our findings support the potential value of using large language models to enhance pharmacovigilance.
Assuntos
Algoritmos , Imunossupressores , Doenças Inflamatórias Intestinais , Processamento de Linguagem Natural , Farmacovigilância , Humanos , Projetos Piloto , Doenças Inflamatórias Intestinais/tratamento farmacológico , Imunossupressores/efeitos adversos , Mineração de Dados/métodos , Efeitos Colaterais e Reações Adversas Relacionados a Medicamentos/diagnóstico , Sistemas de Notificação de Reações Adversas a Medicamentos , Registros Eletrônicos de Saúde , Feminino , Masculino , Hospitalização/estatística & dados numéricosRESUMO
Digital therapeutics (DTx) are a somewhat novel class of US Food and Drug Administration-regulated software that help patients prevent, manage, or treat disease. Here, we use natural language processing to characterise registered DTx clinical trials and provide insights into the clinical development landscape for these novel therapeutics. We identified 449 DTx clinical trials, initiated or expected to be initiated between 2010 and 2030, from ClinicalTrials.gov using 27 search terms, and available data were analysed, including trial durations, locations, MeSH categories, enrolment, and sponsor types. Topic modelling of eligibility criteria, done with BERTopic, showed that DTx trials frequently exclude patients on the basis of age, comorbidities, pregnancy, language barriers, and digital determinants of health, including smartphone or data plan access. Our comprehensive overview of the DTx development landscape highlights challenges in designing inclusive DTx clinical trials and presents opportunities for clinicians and researchers to address these challenges. Finally, we provide an interactive dashboard for readers to conduct their own analyses.
Assuntos
Ensaios Clínicos como Assunto , Processamento de Linguagem Natural , Humanos , Estados Unidos , United States Food and Drug AdministrationRESUMO
Electronic health records (EHRs) provide meaningful knowledge of drug-related adverse events (AEs) that are not captured in standard drug development and postmarketing surveillance. Using variables obtained from EHR data in the University of California San Francisco de-identified Clinical Data Warehouse, we aimed to evaluate the potential of machine learning to predict two hematological AEs, thrombocytopenia and anemia, in a cohort of patients treated with linezolid for 3 or more days. Features for model input were extracted at linezolid initiation (index), and outcomes were characterized from index to 14 days post-treatment. Random forest classification (RFC) was used for AE prediction, and reduced feature models were evaluated using cumulative importance (cImp) for feature selection. Grade 3+ thrombocytopenia and anemia occurred in 31% of 2,171 and 56% of 2,170 evaluable patients, respectively. Of the total 53 features, as few as 7 contributed at least 50% cImp, resulting in prediction accuracies of 70% or higher and area under the receiver operating characteristic curves of 0.886 for grade 3+ thrombocytopenia and 0.759 for grade 3+ anemia. Sensitivity analyses in strictly defined patient subgroups revealed similarly high predictive performance in full and reduced feature models. A logistic regression model with the same 50% cImp features showed similar predictive performance as RFC and good concordance with RFC probability predictions after isotonic calibration, adding interpretability. Collectively, this work demonstrates potential for machine learning prediction of AE risk in real-world patients using few variables regularly available in EHRs, which may aid in clinical decision making and/or monitoring.
Assuntos
Anemia , Trombocitopenia , Humanos , Linezolida/efeitos adversos , Anemia/induzido quimicamente , Anemia/epidemiologia , Trombocitopenia/induzido quimicamente , Trombocitopenia/diagnóstico , Trombocitopenia/epidemiologia , Modelos Logísticos , São FranciscoRESUMO
Although supervised machine learning is popular for information extraction from clinical notes, creating large, annotated datasets requires extensive domain expertise and is time-consuming. Meanwhile, large language models (LLMs) have demonstrated promising transfer learning capability. In this study, we explored whether recent LLMs can reduce the need for large-scale data annotations. We curated a manually labeled dataset of 769 breast cancer pathology reports, labeled with 13 categories, to compare zero-shot classification capability of the GPT-4 model and the GPT-3.5 model with supervised classification performance of three model architectures: random forests classifier, long short-term memory networks with attention (LSTM-Att), and the UCSF-BERT model. Across all 13 tasks, the GPT-4 model performed either significantly better than or as well as the best supervised model, the LSTM-Att model (average macro F1 score of 0.83 vs. 0.75). On tasks with a high imbalance between labels, the differences were more prominent. Frequent sources of GPT-4 errors included inferences from multiple samples and complex task design. On complex tasks where large annotated datasets cannot be easily collected, LLMs can reduce the burden of large-scale data labeling. However, if the use of LLMs is prohibitive, the use of simpler supervised models with large annotated datasets can provide comparable results. LLMs demonstrated the potential to speed up the execution of clinical NLP studies by reducing the need for curating large annotated datasets. This may increase the utilization of NLP-based variables and outcomes in observational clinical studies.
RESUMO
BACKGROUND: Diabetes mellitus (DM) is a major health concern among children with the widespread adoption of advanced technologies. However, concerns are growing about the transparency, replicability, biasedness, and overall validity of artificial intelligence studies in medicine. OBJECTIVE: We aimed to systematically review the reporting quality of machine learning (ML) studies of pediatric DM using the Minimum Information About Clinical Artificial Intelligence Modelling (MI-CLAIM) checklist, a general reporting guideline for medical artificial intelligence studies. METHODS: We searched the PubMed and Web of Science databases from 2016 to 2020. Studies were included if the use of ML was reported in children with DM aged 2 to 18 years, including studies on complications, screening studies, and in silico samples. In studies following the ML workflow of training, validation, and testing of results, reporting quality was assessed via MI-CLAIM by consensus judgments of independent reviewer pairs. Positive answers to the 17 binary items regarding sufficient reporting were qualitatively summarized and counted as a proxy measure of reporting quality. The synthesis of results included testing the association of reporting quality with publication and data type, participants (human or in silico), research goals, level of code sharing, and the scientific field of publication (medical or engineering), as well as with expert judgments of clinical impact and reproducibility. RESULTS: After screening 1043 records, 28 studies were included. The sample size of the training cohort ranged from 5 to 561. Six studies featured only in silico patients. The reporting quality was low, with great variation among the 21 studies assessed using MI-CLAIM. The number of items with sufficient reporting ranged from 4 to 12 (mean 7.43, SD 2.62). The items on research questions and data characterization were reported adequately most often, whereas items on patient characteristics and model examination were reported adequately least often. The representativeness of the training and test cohorts to real-world settings and the adequacy of model performance evaluation were the most difficult to judge. Reporting quality improved over time (r=0.50; P=.02); it was higher than average in prognostic biomarker and risk factor studies (P=.04) and lower in noninvasive hypoglycemia detection studies (P=.006), higher in studies published in medical versus engineering journals (P=.004), and higher in studies sharing any code of the ML pipeline versus not sharing (P=.003). The association between expert judgments and MI-CLAIM ratings was not significant. CONCLUSIONS: The reporting quality of ML studies in the pediatric population with DM was generally low. Important details for clinicians, such as patient characteristics; comparison with the state-of-the-art solution; and model examination for valid, unbiased, and robust results, were often the weak points of reporting. To assess their clinical utility, the reporting standards of ML studies must evolve, and algorithms for this challenging population must become more transparent and replicable.
Assuntos
Inteligência Artificial , Diabetes Mellitus , Humanos , Criança , Reprodutibilidade dos Testes , Aprendizado de Máquina , Diabetes Mellitus/diagnóstico , Lista de ChecagemRESUMO
Objective: Existing research on social determinants of health (SDoH) predominantly focuses on physician notes and structured data within electronic medical records. This study posits that social work notes are an untapped, potentially rich source for SDoH information. We hypothesize that clinical notes recorded by social workers, whose role is to ameliorate social and economic factors, might provide a complementary information source of data on SDoH compared to physician notes, which primarily concentrate on medical diagnoses and treatments. We aimed to use word frequency analysis and topic modeling to identify prevalent terms and robust topics of discussion within a large cohort of social work notes including both outpatient and in-patient consultations. Materials and methods: We retrieved a diverse, deidentified corpus of 0.95 million clinical social work notes from 181â644 patients at the University of California, San Francisco. We conducted word frequency analysis related to ICD-10 chapters to identify prevalent terms within the notes. We then applied Latent Dirichlet Allocation (LDA) topic modeling analysis to characterize this corpus and identify potential topics of discussion, which was further stratified by note types and disease groups. Results: Word frequency analysis primarily identified medical-related terms associated with specific ICD10 chapters, though it also detected some subtle SDoH terms. In contrast, the LDA topic modeling analysis extracted 11 topics explicitly related to social determinants of health risk factors, such as financial status, abuse history, social support, risk of death, and mental health. The topic modeling approach effectively demonstrated variations between different types of social work notes and across patients with different types of diseases or conditions. Discussion: Our findings highlight LDA topic modeling's effectiveness in extracting SDoH-related themes and capturing variations in social work notes, demonstrating its potential for informing targeted interventions for at-risk populations. Conclusion: Social work notes offer a wealth of unique and valuable information on an individual's SDoH. These notes present consistent and meaningful topics of discussion that can be effectively analyzed and utilized to improve patient care and inform targeted interventions for at-risk populations.
RESUMO
OBJECTIVES: Natural language processing (NLP) of clinical notes in electronic medical records is increasingly used to extract otherwise sparsely available patient characteristics, to assess their association with relevant health outcomes. Manual data curation is resource intensive and NLP methods make these studies more feasible. However, the methodology of using NLP methods reliably in clinical research is understudied. The objective of this study is to investigate how NLP models could be used to extract study variables (specifically exposures) to reliably conduct exposure-outcome association studies. STUDY DESIGN AND SETTING: In a convenience sample of patients admitted to the intensive care unit of a US academic health system, multiple association studies are conducted, comparing the association estimates based on NLP-extracted vs. manually extracted exposure variables. The association studies varied in NLP model architecture (Bidirectional Encoder Decoder from Transformers, Long Short-Term Memory), training paradigm (training a new model, fine-tuning an existing external model), extracted exposures (employment status, living status, and substance use), health outcomes (having a do-not-resuscitate/intubate code, length of stay, and in-hospital mortality), missing data handling (multiple imputation vs. complete case analysis), and the application of measurement error correction (via regression calibration). RESULTS: The study was conducted on 1,174 participants (median [interquartile range] age, 61 [50, 73] years; 60.6% male). Additionally, up to 500 discharge reports of participants from the same health system and 2,528 reports of participants from an external health system were used to train the NLP models. Substantial differences were found between the associations based on NLP-extracted and manually extracted exposures under all settings. The error in association was only weakly correlated with the overall F1 score of the NLP models. CONCLUSION: Associations estimated using NLP-extracted exposures should be interpreted with caution. Further research is needed to set conditions for reliable use of NLP in medical association studies.