AI chatbots are proliferating in healthcare systems. It is essential to explore how physicians use these tools in order to understand their influence on clinical care and outcomes. Our goal was to understand how physicians conceive of and incorporate AI into clinical decision-making. We conducted semistructured interviews with generalist physicians from inpatient and outpatient settings in the USA. Prior to the interview, participants were asked to use an AI chatbot, ChatGPT-4, to complete three mock clinical cases. Physicians were interviewed regarding their perspectives on the AI chatbot. Interviews were analyzed using reflexive thematic analysis and conducted via video conference meeting, where they were recorded and transcribed. We interviewed 22 physicians with 2–32 years of experience (median = 3 years). We identified a central organizing concept of “physician as filter” defining how physicians used the AI chatbot. This idea was composed of four themes. Theme 1: Physicians perceive clinical decision-making as a problem-solving activity, applying internally held knowledge to externally gathered information. Theme 2: AI chatbot systems are part of a continuum of information resources. Theme 3: Trust in the AI chatbot’s outputs depends on the user’s own clinical knowledge. Theme 4: Clinical decision-making is understood as the personalization of clinical knowledge and context. AI chatbots may help physicians with formulating a clinical problem and generating a hypothesis by expanding their repertoire of possible cases. Despite the “wealth of information” provided by AI chatbots, physician trust in the outputs is limited, especially when AI chatbots do not provide references. Physician users described filtering chatbot outputs, using their own clinical knowledge and experience, to determine what information is relevant. In describing how providers perceive AI chatbots, we hope to guide further investigation of physician AI interaction and chatbot development that facilitates improved clinical reasoning.

Recent studies have found that physicians with access to a large language model (LLM) chatbot during clinical reasoning tests may score no better to worse compared to the same chatbot performing alone with an input that included the entire clinical case. This study explores how physicians approach using LLM chatbots during clinical reasoning tasks and whether the amount of clinical case content included in the input affects performance. We conducted semi-structured interviews with U.S. physicians on experiences using an LLM chatbot and developed a typology based on input patterns. We then analyzed physician chat logs from two randomized controlled trials, coding each clinical case to an input approach type. Lastly, we used a linear mixed-effects model to compare the case scores of different input approach types. We identified four input approach types based on patterns of content amount: copy-paster (entire case), selective copy-paster (pieces of a case), summarizer (user-generated case summary), and searcher (short queries). Copy-pasting and searching were utilized most. No single type was associated with scoring higher on clinical cases. Other factors such as different prompting strategies, cognitive engagement, and interpretation of the outputs may have more impact and should be explored in future studies.

Background:Large language model (LLM) chatbots demonstrate high degrees of accuracy, yet recent studies found that physicians using these same chatbots may score no better to worse on clinical reasoning tests compared to the chatbot performing alone with researcher-curated prompts. It is unknown how physicians approach inputting information into chatbots. Objective:This study aimed to identify how physicians interacted with LLM chatbots on clinical reasoning tasks to create a typology of input approaches, exploring whether input approach type was associated with improved clinical reasoning performance. Methods:We carried out a mixed methods study in three steps. First, we conducted semi-structured interviews with U.S. physicians on experiences using an LLM chatbot and analyzed transcripts using the Framework Method to develop a typology based on input patterns. Next, we analyzed the chat logs of physicians who used a chatbot while solving clinical cases, categorizing each case to an input approach type. Lastly, we used a linear mixed-effects model to compare each input approach type with performance on the clinical cases. Results:We identified four input approach types based on patterns of "content amount": copy-paster (entire case), selective copy-paster (pieces of a case), summarizer (user-generated case summary), and searcher (short queries). Copy-pasting and searching were utilized most. No single type was associated with scoring higher on clinical cases. Discussion:This study adds to our understanding of how physicians approach using chatbots and identifies ways in which physicians intuitively interact with chatbots. Conclusions:Purposeful training and support is needed to help physicians effectively use emerging AI technologies and realize their potential for supporting safe and effective medical decision-making in practice.

While large language models (LLMs) have shown promise in diagnostic reasoning, their impact on management reasoning, which involves balancing treatment decisions and testing strategies while managing risk, is unknown. This prospective, randomized, controlled trial assessed whether LLM assistance improves physician performance on open-ended management reasoning tasks compared to conventional resources. From November 2023 to April 2024, 92 practicing physicians were randomized to use either GPT-4 plus conventional resources or conventional resources alone to answer five expert-developed clinical vignettes in a simulated setting. All cases were based on real, de-identified patient encounters, with information revealed sequentially to mirror the nature of clinical environments. The primary outcome was the difference in total score between groups on expert-developed scoring rubrics. Secondary outcomes included domain-specific scores and time spent per case. Physicians using the LLM scored significantly higher compared to those using conventional resources (mean difference = 6.5 NCT06208423 . In a prospective study involving 92 physicians from multiple institutions, access to large language model assistance on top of conventional resources increased a score expressing the quality of their reasoning in addressing patient care while assessing five clinical vignettes.

Assessing Diagnostic PerformanceDiagnosis is an action and a goal in medicine. This article is the introduction to a series of review articles on varying facets of diagnosis. Clinical diagnosis is an exercise in classification; that is, placing the patient's condition in the correct diagnostic category. However, consideration must also be given to the performance objective, whether it is technical performance of a test, acquiring diagnostic information with respect to clinical management for an individual or a population's health outcomes, or cost-effectiveness and equity of care.

Funders of research have an opportunity to advance health equity and social justice by incorporating principles of diversity, equity, inclusion, and justice (DEIJ) in their approach to grantmaking. We conducted a pragmatic review to identify opportunities for grantmakers in the health care sector to integrate DEIJ in their funding activities. The resulting framework discusses recommendations within three phases as follows: (1) Organizational Context (i.e., initiate DEIJ efforts within the grantmaking organization, invest in community partnerships, and establish DEIJ goals), (2) Grantmaking Process (i.e., DEIJ-specific practices related to grant design, application, proposal review processes, and support for grantees), and (3) Assessment of Process and Outcomes (i.e., measurement, evaluation, and dissemination to maximize impact of DEIJ efforts). Throughout all grantmaking phases, it is critical to partner with and engage individuals and communities that have been historically marginalized in health care and research. In this article, we describe how adoption of framework practices can leverage grantmaking to advance DEIJ for communities, researchers, and projects.

Diagnosis usually proceeds along standard pathways. First check an EKG for chest pain to rule out a heart attack. Get a CT scan before a biopsy for possible cancer. Clinicians learn and faithfully replicate conventional strategies.

This Viewpoint describes 3 learning methods that form the basis of many systems of diagnostic artificial intelligence systems—learning from experts, examples, and experience—and their parallels to clinicians’ existing approaches to learning.

Clinical decision support systems that use artificial intelligence (AI) to improve diagnostic accuracy, efficiency, and safety have long been aspirational goals for computer scientists and clinicians. Yet diagnostic AI development has seen multiple cycles of inflated peaks of expectations followed by troughs of disillusionment. Clinicians are understandably wary of embracing new diagnostic AI solutions without understanding how they work and relate to their existing practice. Diagnostic AI refers to a broad range of applications that use learning strategies that mimic human approaches to learning. When clinicians understand the underlying mechanisms of diagnostic AI, they can become informed usersofthesetools,appreciatingboththeiradvantagesand limitations.ThisViewpointoutlines3learningmethodsthat formthebasisofmanydiagnosticAIsystems—learningfrom experts, examples, and experience—and their parallels to clinicians’ existing approaches to learning.

This article investigates several parallelizable alternatives to DTW for estimating the alignment between two long sequences. Whereas most previous work has focused on reducing the total computation and/or memory costs of DTW, our focus is instead on reducing wall clock time by utilizing common hardware like GPUs that are optimized for parallel processing. We propose and study four different parallelizable alignment algorithms: the first three algorithms compute approximations of DTW by breaking the pairwise cost matrix into rectangular regions and processing the regions in parallel, and the fourth algorithm computes an exact DTW alignment by processing the cost matrix along diagonals rather than rows or columns. We characterize the performance of our proposed alignment algorithms on an audio-audio alignment task, and we develop GPU-based implementations for the two best-performing algorithms, which we call weakly-ordered Segmental DTW (WSDTW) and Parallelized Diagonal DTW (ParDTW). Our experiments indicate that ParDTW is the most practical and useful of the four algorithms: it computes an exact DTW alignment and reduces runtime by 1.5 to 2 orders of magnitude on long sequences compared to current alternatives. We present a comprehensive evaluation and study of the alignment accuracy, runtime, and practical limitations of the proposed alignment algorithms.

Our website uses cookies to enhance your experience. By continuing to use our site, or clicking "Continue," you are agreeing to our Cookie Policy | Continue JAMA HomeNew OnlineCurrent IssueFor Authors Publications JAMA JAMA Network Open JAMA Cardiology JAMA Dermatology JAMA Health Forum JAMA Internal Medicine JAMA Neurology JAMA Oncology JAMA Ophthalmology JAMA Otolaryngology–Head & Neck Surgery JAMA Pediatrics JAMA Psychiatry JAMA Surgery Archives of Neurology & Psychiatry (1919-1959) Podcasts Clinical Reviews Editors' Summary Medical News Author Interviews More JN Learning / CMESubscribeJobsInstitutions / LibrariansReprints & Permissions Terms of Use | Privacy Policy | Accessibility Statement 2023 American Medical Association. All Rights Reserved Search All JAMA JAMA Network Open JAMA Cardiology JAMA Dermatology JAMA Forum Archive JAMA Health Forum JAMA Internal Medicine JAMA Neurology JAMA Oncology JAMA Ophthalmology JAMA Otolaryngology–Head & Neck Surgery JAMA Pediatrics JAMA Psychiatry JAMA Surgery Archives of Neurology & Psychiatry Input Search Term Sign In Individual Sign In Sign inCreate an Account Access through your institution Sign In Purchase Options: Buy this article Rent this article Subscribe to the JAMA journal

This paper studies the problem of identifying piano music in various modalities using a single, unified approach called marketplace fingerprinting. The key defining characteristic of marketplace fingerprinting is choice: we consider a broad range of fingerprint designs based on a generalization of standard n-grams, and then select the fingerprint designs at runtime that are best for a specific query. We show that the large-scale retrieval problem can be framed as an economics problem in which a consumer and a store interact. In our analogy, the runtime search is like a consumer shopping in the store, the items for sale correspond to fingerprints, and purchasing an item corresponds to doing a fingerprint lookup in the database. Using basic principles of economics, we design an efficient marketplace in which the consumer has many options and adopts a rational buying strategy that explicitly considers the cost and expected utility of each item. We evaluate our marketplace fingerprinting approach on four different sheet music retrieval tasks involving sheet music images, MIDI files, and audio recordings. Using a database containing approximately 375,000 pages of sheet music, our method is able to achieve 0.91 mean reciprocal rank with sub-second average runtime on cell phone image queries. On all four retrieval tasks, the marketplace method substantially outperforms previous methods while simultaneously reducing average runtime. We present comprehensive experimental results, as well as detailed analyses to provide deeper intuition into system behavior.

This article introduces a method for large-scale retrieval of piano sheet music images. We study this problem in two different scenarios: camera-based sheet music identification and MIDI-sheet image retrieval. Our proposed method combines bootleg score features with a novel hashing scheme called dynamic N-gram fingerprinting. This hashing scheme ensures that every fingerprint is discriminative enough to warrant a table lookup, which improves both retrieval accuracy and runtime. On experiments using all piano sheet music images in the IMSLP database, the proposed method achieves >0.8 mean reciprocal rank with sub-second runtimes. As a practical application, we use our system to find matches between the Lakh MIDI dataset and IMSLP, which augments the IMSLP sheet music data with symbolic music information for a subset of pieces. We release our code and Lakh-IMSLP matches to facilitate future study.

Our website uses cookies to enhance your experience. By continuing to use our site, or clicking "Continue," you are agreeing to our Cookie Policy | Continue JAMA HomeNew OnlineCurrent IssueFor Authors Publications JAMA JAMA Network Open JAMA Cardiology JAMA Dermatology JAMA Health Forum JAMA Internal Medicine JAMA Neurology JAMA Oncology JAMA Ophthalmology JAMA Otolaryngology–Head & Neck Surgery JAMA Pediatrics JAMA Psychiatry JAMA Surgery Archives of Neurology & Psychiatry (1919-1959) Podcasts Clinical Reviews Editors' Summary Medical News Author Interviews More JN Learning / CMESubscribeJobsInstitutions / LibrariansReprints & Permissions Terms of Use | Privacy Policy | Accessibility Statement 2023 American Medical Association. All Rights Reserved Search All JAMA JAMA Network Open JAMA Cardiology JAMA Dermatology JAMA Forum Archive JAMA Health Forum JAMA Internal Medicine JAMA Neurology JAMA Oncology JAMA Ophthalmology JAMA Otolaryngology–Head & Neck Surgery JAMA Pediatrics JAMA Psychiatry JAMA Surgery Archives of Neurology & Psychiatry Input Search Term Sign In Individual Sign In Sign inCreate an Account Access through your institution Sign In Purchase Options: Buy this article Rent this article Subscribe to the JAMA journal

This paper explores an application that would enable a group of musicians in quarantine to produce a performance of a chamber work by recording each part in isolation in a completely unsynchronized manner, and then generating a synchronized performance by aligning, time scale modifying, and mixing the individual part recordings. We focus on the main technical challenge of aligning the individual part recordings against a reference “full mix” recording containing a performance of the work. We propose an iterative subtractive alignment approach, in which each part recording is aligned against the full mix recording and then subtracted from it. We also explore different feature representations and cost metrics to handle the asymmetrical nature of the part–full mix comparison. We evaluate our proposed approach on two different datasets: one that is a modification of the URMP dataset that presents an idealized setting, and another that contains a small set of piano trio data collected from musicians during the pandemic specifically for this study. Compared to a standard pairwise alignment approach, we find that the proposed approach has strong performance on the URMP dataset and mixed success on the more realistic piano trio data.

This paper studies instrument classification of solo sheet music. Whereas previous work has focused on instrument recognition in audio data, we instead approach the instrument classification problem using raw sheet music images. Our approach first converts the sheet music image into a sequence of musical words based on the bootleg score representation, and then treats the problem as a text classification task. We show that it is possible to significantly improve classifier performance by training a language model on unlabeled data, initializing a classifier with the pretrained language model weights, and then finetuning the classifier on labeled data. In this work, we train AWD-LSTM, GPT-2, and RoBERTa models on solo sheet music images from IMSLP for eight different instruments. We find that GPT-2 and RoBERTa slightly outperform AWD-LSTM, and that pretraining increases classification accuracy for RoBERTa from 34.5% to 42.9%. Furthermore, we propose two data augmentation methods that increase classification accuracy for RoBERTa by an additional 15%.

Effective insect pollination requires appropriate responses to internal and external environmental cues in both the plant and the pollinator. Helianthus annuus, a highly outcrossing species, is marked for its uniform eastward orientation of mature pseudanthia, or capitula. Here we investigate how this orientation affects floral microclimate and the consequent effects on plant and pollinator interactions and reproductive fitness. We artificially manipulated sunflower capitulum orientation and temperature in both field and controlled conditions and assessed flower physiology, pollinator visits, seed traits and siring success. East-facing capitula were found to have earlier style elongation, pollen presentation and pollinator visits compared with capitula manipulated to face west. East-facing capitula also sired more offspring than west-facing capitula and under some conditions produced heavier and better-filled seeds. Local ambient temperature change on the capitulum was found to be a key factor regulating the timing of style elongation, pollen emergence and pollinator visits. These results indicate that eastward capitulum orientation helps to control daily rhythms in floral temperature, with direct consequences on the timing of style elongation and pollen emergence, pollinator visitation, and plant fitness.

This paper studies composer style classification of piano sheet music, MIDI, and audio data. We expand upon previous work in three ways. First, we explore several musically motivated data augmentation schemes based on pitch-shifting and random removal of individual notes or groups of notes. We show that these augmentation schemes lead to dramatic improvements in model performance, of a magnitude that exceeds the benefit of pretraining on all solo piano sheet music images in IMSLP. Second, we describe a way to modify previous models in order to enable cross-model transfer learning, in which a model trained entirely on sheet music can be used to perform composer classification of audio or MIDI data. Third, we explore the performance of trained models in a 1-shot learning context, in which the model performs classification among a set of composers that are unseen in training. Our results indicate that models learn a representation of compositional style that generalizes beyond the set of composers used in training.

This article studies a composer style classification task based on raw sheet music images. While previous works on composer recognition have relied exclusively on supervised learning, we explore the use of self-supervised pretraining methods that have been recently developed for natural language processing. We first convert sheet music images to sequences of musical words, train a language model on a large set of unlabeled musical “sentences”, initialize a classifier with the pretrained language model weights, and then finetune the classifier on a small set of labeled data. We conduct extensive experiments on International Music Score Library Project (IMSLP) piano data using a range of modern language model architectures. We show that pretraining substantially improves classification performance and that Transformer-based architectures perform best. We also introduce two data augmentation strategies and present evidence that the model learns generalizable and semantically meaningful information.