Qian, Ray

This chapter provides a high-level overview of clinical informatics (CI) and artificial intelligence (AI) in healthcare. It covers foundational concepts such as electronic health records (EHRs) and data standards, current applications including Clinical Decision Support Systems (CDSS) and ambient scribing/documentation, and near-term directions for both clinicians and patients. The chapter also introduces how foundational CI systems and healthcare data are leveraged to develop AI solutions, ranging from traditional machine learning to large language models, while addressing key issues such as bias, generalizability, and regulatory considerations. Finally, the chapter examines a potential future in which decentralized AI models augment clinicians in their daily work, generate deeper clinical insights, and transform patient care through advanced predictive models and digital twins.

Abstract Background: Spatial Reasoning AI (SRAI) systems are emerging as a transformative class of clinical artificial intelligence, enabling real-time interpretation of complex anatomy in imaging, surgery, and chronic disease management. Unlike traditional AI approaches constrained to tabular or 2D inputs, SRAI models incorporate geometric priors, multimodal fusion, and 3D anatomical reasoning to support high-impact tasks such as volumetric segmentation, lesion localization, intraoperative guidance, and prognostic modeling. Objective: This scoping review aimed to (1) map the emerging landscape of SRAI in healthcare, (2) assess its clinical performance across diagnostic, prognostic, and workflow applications, and (3) identify opportunities and barriers for safe translation into practice. Methods: Following PRISMA 2020 guidelines, we systematically searched PubMed, Springer Nature, and IEEE Xplore (including CVPR, ICCV, ISBI, and EMBC) for original studies implementing spatially aware AI models with clinical validation or workflow relevance. Data extraction captured model architecture, input modality, anatomical scope, application domain, and performance outcomes. Results: We identified eligible studies spanning oncology, neurology, cardiology, surgery, and infectious diseases. SRAI systems consistently outperformed conventional methods in segmentation, lesion classification, and risk stratification. A paradigm shift is underway from task-specific CNNs to foundation-level models, including MedSAM and MedCLIP for zero-shot segmentation and retrieval, and NeRF-based pipelines for anatomically faithful 3D reconstruction. Randomized evidence shows that SRAI can improve workflow efficiency without compromising diagnostic accuracy. Conclusion: SRAI models demonstrate strong potential to advance diagnostic precision, prognostic accuracy, and workflow integration across multiple clinical domains. Their safe adoption will require standardized evaluation metrics, prospective multi-institutional validation, and interpretable outputs. As foundation models evolve to better encode spatial priors, SRAI is poised to become a cornerstone of workflow-integrated precision medicine.

Abstract Background: Spatial Reasoning AI (SRAI) systems are reshaping clinical practice by enabling real-time interpretation of complex anatomical structures in medical imaging, surgery, and chronic disease management (Lin et al., 2023, Qiao et al., 2021; Song et al., 2024) . Unlike traditional AI approaches that rely on tabular or 2D data, SRAI models incorporate geometric priors, multimodal fusion, and 3D anatomical reasoning to support high-impact tasks such as volumetric segmentation, disease localization, and intraoperative guidance (Milletari et al., 2016; Hatamizadeh et al., 2022; Zhang et al., 2022) . Objective: This scoping review aimed to (1) characterize the emerging landscape of spatial reasoning models in healthcare, (2) evaluate their clinical performance across diagnostic and prognostic applications, and (3) identify architectural trends that underpin successful translation into practice. Methods: Following PRISMA guidelines, we systematically screened PubMed to identify studies that implemented spatially aware AI models with real-time or clinically validated outcomes (Page et al., 2021) . Data extraction captured model architecture, modality, anatomical scope, clinical application, and performance metrics. Results: We identified 124 eligible studies across the clinical domains of oncology, neurology, cardiology, orthopedic surgery, and infectious diseases (Nie et al., 2019; Hao et al., 2020; Tasken et al., 2023) . SRAI systems consistently outperformed conventional methods in segmentation, lesion classification, and risk stratification. (Lin et al., 2023; Qiao et al., 2021; Mahootiha et al., 2024) . A paradigm shift from task-specific CNNs to foundation models that reason across spatial structures has emerged, beginning with adaptations of generalist models such as MedSAM and MedCLIP for zero-shot segmentation and cross-modal retrieval, and NeRF-based reconstruction for anatomically faithful 3D modeling (Ma et al., 2024; Mildenhall et al., 2020; Radford et al., 2021). Beyond technical performance, randomized evidence shows that SRAI systems can improve workflow efficiency without compromising outcomes (Lang et al., 2023) . Conclusion: SRAI models hold promise for enhancing diagnostic accuracy, prognostic precision, and clinical efficiency across diverse applications. Their successful integration will depend on standardized evaluation metrics, robust validation, and interpretable outputs. As foundation models evolve to better encode spatial priors, SRAI is poised to become a cornerstone of personalized and procedural medicine.

Prolonged QT interval is an independent risk factor for all-cause mortality. However, evaluation of mortality associated to the implementation of a clinical decision support system to increase awareness and provide management recommendations has been challenging. Here we present our attempt to develop a model using only electronic data and different control groups.

Introduction: The main goal of Clinical Decision Support (CDS) is to provide timely and useful information for providers to deliver high-quality and safe care. Issues, like alert fatigue and provider burnout are commonly cited as unintended consequences of the CDS systems. Herein, we describe leveraging electronic health record (EHR) self-service reporting tools to gain insights on a CDS rule designed to avoid providers from ordering QT-prolonging medication in patients with history of QT-prolongation. Methods: Our EHR (Epic) SlicerDicer reporting tool was used to identify the frequency of QT-prolongation Best Practice Advisory (BPA) triggerings from 1/1/2020 to 12/31/2020 across Mayo Clinic sites. Additionally, associated patient encounter and BPA-specific data were queried. Text from acknowledgement comments to the BPA were reviewed and central themes and comments were categorized. Epic Clarity Data Warehouse was queried to identify the BPA-triggering medications and frequencies. Comparisons of percent action taken on the BPA were compared internally to Mayo Clinic’s BPA benchmark, and with national benchmarks using Epic BestPractice Pulse dashboard. Results: A total of 17,538 BPAs of interest were triggered across the Mayo Clinic sites in 2020, of which 3,696 (20.1%) were acted upon through either monitoring or medication discontinuation. This is below Mayo Clinic’s median of 29.2% for inpatient BPAs and 45.6% BPAs for outpatient, but above the national median of 10% (IQR 6.1-13.1%) for inpatient and 10% (IQR 4.3-19.5%) for outpatient BPAs actioned upon. A total of 30 different medications triggered the BPA, with the most common being ondansetron (41.5%), amiodarone (11.3%), and haloperidol (10.1%). User comments were left on 2,382 orders (13.5%) that acknowledged the BPA, but provided argument to prescribe drug. Three most common themes identified from comments on overridden BPAs: patient previously tolerated medication (19.0%), QT interval not prolonged on recent ECG (14.2%), and patient on hospice care (5.2%). Conclusion: Analysis of free text comments of CDS can be and should be performed to reveal opportunities for further improvement of CDS. Providers should be encouraged to provide comments when encountering CDS interventions.

Abstract Hospital census prediction has well-described implications for efficient hospital resource utilization, and recent issues with hospital crowding due to CoVID-19 have emphasized the importance of this task. Our team has been leading an institutional effort to develop machine-learning models that can predict hospital census 12 hours into the future. We describe our efforts at developing accurate empirical models for this task. Ultimately, with limited resources and time, we were able to develop simple yet useful models for 12-hour census prediction and design a dashboard application to display this output to our hospital’s decision-makers. Specifically, we found that linear models with ElasticNet regularization performed well for this task with relative 95% error of +/− 3.4% and that this work could be completed in approximately 7 months.