S1. Lung tumor development in NNK-exposed Gprc5a-/- mice. S2. Evolutionarily conserved patterns of tobacco-carcinogen mediated gene expression in murine and human airway epithelia. S3. Early and persistent changes in mouse airway gene expression in vivo following tobacco carcinogen exposure and during lung oncogenesis. S4. Gene profiles downregulated in the mouse normal-appearing airway field of injury are overall suppressed in lung tumors relative to adjacent normal lung.

Supplementary Methods and Supplementary Figure Legends

ImportanceDuplicated text is a well-documented hazard in electronic medical records (EMRs), leading to wasted clinician time, medical error, and burnout. This study hypothesizes that text duplication is prevalent and increases with time and EMR size and that duplicate information is shared across authors.ObjectiveTo examine the prevalence and scope of duplication behavior in clinical notes from a large academic health system and the factors associated with duplication.Design, Setting, and ParticipantsThis retrospective, cross-sectional analysis of note length and content duplication rates used a set of 10 adjacent word tokens (ie, a 10-gram) sliding-window approach to identify spans of text duplicated exactly from earlier notes in a patient’s record for all inpatient and outpatient notes written within the University of Pennsylvania Health System from January 1, 2015, through December 31, 2020. Text duplicated from a different author vs text duplicated from the same author was quantified. Furthermore, novel text and duplicated text per author for various note types and author types, as well as per patient record by number of notes in the record, were quantified. Information scatter, another documentation hazard, was defined as the inverse of novel text per note, and the association between information duplication and information scatter was graphed. Data analysis was performed from January to March 2022.Main Outcomes and MeasuresTotal, novel, and duplicate text by note type and note author were determined, as were the mean intra-author and inter-author duplication per note by type and author.ResultsThere were a total of 104 456 653 notes for 1 960 689 unique patients consisting of 32 991 489 889 words; 50.1% of the total text in the record (16 523 851 210 words) was duplicated from prior text written about the same patient. The duplication fraction increased year-over-year, from 33.0% for notes written in 2015 to 54.2% for notes written in 2020. Of the text duplicated, 54.1% came from text written by the same author, whereas 45.9% was duplicated from a different author. Records with more notes had more total duplicate text, approaching 60%. Note types with high information scatter tended to have low information overload, and vice versa, suggesting a trade-off between these 2 hazards under the current documentation paradigm.Conclusions and RelevanceDuplicate text casts doubt on the veracity of all information in the medical record, making it difficult to find and verify information in day-to-day clinical work. The findings of this cross-sectional study suggest that text duplication is a systemic hazard, requiring systemic interventions to fix, and simple solutions such as banning copy-paste may have unintended consequences, such as worsening information scatter. The note paradigm should be further examined as a major cause of duplication and scatter, and alternative paradigms should be evaluated.

Clinicians spend a substantial part of their workday reviewing and writing electronic medical notes. Here we describe how the current, widely accepted paradigm for electronic medical notes represents a poor organizational framework for both the individual clinician and the broader medical team. As described in this viewpoint, the medical chart-including notes, labs, and imaging results-can be reconceptualized as a dynamic, fully collaborative workspace organized by topic rather than time, writer, or data type. This revised framework enables a more accurate and complete assessment of the current state of the patient and easy historical review, saving clinicians substantial time on both data input and retrieval. Collectively, this approach has the potential to improve health care delivery effectiveness and efficiency.

BACKGROUND Clinicians spend large amounts of their workday using electronic medical records (EMRs). Poorly designed documentation systems contribute to the proliferation of out-of-date information, increased time spent on medical records, clinician burnout, and medical errors. Beyond software interfaces, examining the underlying paradigms and organizational structures for clinical information may provide insights into ways to improve documentation systems. In particular, our attachment to the note as the major organizational unit for storing unstructured medical data may be a cause of many of the problems with modern clinical documentation. Notes, as currently understood, systematically incentivize information duplication and information scattering, both within a single clinician’s notes over time and across multiple clinicians’ notes. Therefore, it is worthwhile to explore alternative paradigms for unstructured data organization. OBJECTIVE The aim of this study is to demonstrate the feasibility of building an EMR that does not use notes as the core organizational unit for unstructured data and which is designed specifically to disincentivize information duplication and information scattering. METHODS We used specific design principles to minimize the incentive for users to duplicate and scatter information. By default, the majority of a patient’s medical history remains the same over time, so users should not have to redocument that information. Clinicians on different teams or services mostly share the same medical information, so all data should be collaboratively shared across teams and services (while still allowing for disagreement and nuance). In all cases where a clinician must state that information has remained the same, they should be able to attest to the information without redocumenting it. We designed and built a web-based EMR based on these design principles. RESULTS We built a medical documentation system that does not use notes and instead treats the chart as a single, dynamically updating, and fully collaborative workspace. All information is organized by clinical topic or problem. Version history functionality is used to enable granular tracking of changes over time. Our system is highly customizable to individual workflows and enables each individual user to decide which data should be structured and which should be unstructured, enabling individuals to leverage the advantages of structured templating and clinical decision support as desired without requiring programming knowledge. The system is designed to facilitate real-time, fully collaborative documentation and communication among multiple clinicians. CONCLUSIONS We demonstrated the feasibility of building a non–note-based, fully collaborative EMR system. Our attachment to the note as the only possible atomic unit of unstructured medical data should be reevaluated, and alternative models should be considered.

Introduction: Machine learning (ML) and natural language processing have great potential to improve information extraction (IE) within electronic medical records (EMRs) for a wide variety of clinical search and summarization tools. Despite ML advancements, clinical adoption of real time IE tools for patient care remains low. Clinically motivated IE task definitions, publicly available annotated clinical datasets, and inclusion of subtasks such as coreference resolution and named entity normalization are critical for the development of useful clinical tools. Materials and methods: We provide a task definition and comprehensive annotation requirements for a clinically motivated symptom extraction task. Four annotators labeled symptom mentions within 1108 discharge summaries from two public clinical note datasets for the tasks of named entity recognition, coreference resolution, and named entity normalization; these annotations will be released to the public. Baseline human performance was assessed and two ML models were evaluated on the symptom extraction task. Results: 16,922 symptom mentions were identified within the discharge summaries, with 11,944 symptom instances after coreference resolution and 1255 unique normalized answer forms. Human annotator performance averaged 92.2% FI. Recurrent network model performance was 85.6% FI (recall 85.8%, precision 85.4%), and Transformer-based model performance was 86.3% FI (recall 86.6%, precision 86.1%). Our models extracted vague symptoms, acronyms, typographical errors, and grouping statements. The models generalized effectively to a separate clinical note corpus and can run in real time. Conclusion: To our knowledge, this dataset will be the largest and most comprehensive publicly released, annotated dataset for clinically motivated symptom extraction, as it includes annotations for named entity recognition, coreference, and normalization for more than 1000 clinical documents. Our neural network models extracted symptoms from unstructured clinical free text at near human performance in real time. In this paper, we present a clinically motivated task definition, dataset, and simple supervised natural language processing models to demonstrate the feasibility of building clinically applicable information extraction tools.

Motivational deficits play a central role in disability caused by schizophrenia and constitute a major unmet therapeutic need. Negative symptoms have previously been linked to hypofunction in ventral striatum (VS), a core component of brain motivation circuitry. However, it remains unclear to what extent this relationship holds for specific negative symptoms such as amotivation, and this question has not been addressed with integrated behavioral, clinical, and imaging measures. Here, 41 individuals with schizophrenia and 37 controls performed a brief, computerized progressive ratio task (PRT) that quantifies effort exerted in pursuit of monetary reward. Clinical amotivation was assessed using the recently validated Clinical Assessment Interview for Negative Symptoms (CAINS). VS function was probed during functional magnetic resonance imaging using a monetary guessing paradigm. We found that individuals with schizophrenia had diminished motivation as measured by the PRT, which significantly and selectively related to clinical amotivation as measured by the CAINS. Critically, lower PRT motivation in schizophrenia was also dimensionally related to VS hypofunction. Our results demonstrate robust dimensional associations between behavioral amotivation, clinical amotivation, and VS hypofunction in schizophrenia. Integrating behavioral measures such as the PRT will facilitate translational efforts to identify biomarkers of amotivation and to assess response to novel therapeutic interventions.