The Impact of Information Relevancy and Interactivity on Intensivists' Trust in a Machine Learning-Based Bacteremia Prediction System: Simulation Study.

Background: The exponential growth in computing power and the increasing digitization of information have substantially advanced the machine learning (ML) research field. However, ML algorithms are often considered "black boxes," and this fosters distrust. In medical domains, in which mistakes can result in fatal outcomes, practitioners may be especially reluctant to trust ML algorithms. Objective: The aim of this study is to explore the effect of user-interface design features on intensivists' trust in an ML-based clinical decision support system. Methods: A total of 47 physicians from critical care specialties were presented with 3 patient cases of bacteremia in the setting of an ML-based simulation system. Three conditions of the simulation were tested according to combinations of information relevancy and interactivity. Participants' trust in the system was assessed by their agreement with the system's prediction and a postexperiment questionnaire. Linear regression models were applied to measure the effects. Results: Participants' agreement with the system's prediction did not differ according to the experimental conditions. However, in the postexperiment questionnaire, higher information relevancy ratings and interactivity ratings were associated with higher perceived trust in the system (P<.001 for both). The explicit visual presentation of the features of the ML algorithm on the user interface resulted in lower trust among the participants (P=.05). Conclusions: Information relevancy and interactivity features should be considered in the design of the user interface of ML-based clinical decision support systems to enhance intensivists' trust. This study sheds light on the connection between information relevancy, interactivity, and trust in human-ML interaction, specifically in the intensive care unit environment.

Evaluation of a real-life experience with a digital fluid balance monitoring technology.

BACKGROUND: Innovations in healthcare technologies have the potential to address challenges, including the monitoring of fluid balance. OBJECTIVE: This study aims to evaluate the functionality and accuracy of a digital technology compared to standard manual documentation in a real-life setting. METHODS: The digital technology, LICENSE, was designed to calculate fluid balance using data collected from devices measuring urine, oral and intravenous fluids. Participating patients were connected to the LICENSE system, which transmitted data wirelessly to a database. These data were compared to the nursing staff's manual measurements documented in the electronic patient record according to their usual practice. RESULTS: We included 55 patients in the Urology Department needing fluid balance charting and observed them for an average of 22.9 hours. We found a mean difference of -44.2 ml in total fluid balance between the two methods. Differences ranged from -2230 ml to 2695 ml, with a divergence exceeding 500 ml in 57.4% of cases. The primary source of error was inaccurate or omitted manual documentation. However, errors were also identified in the oral LICENSE device. CONCLUSIONS: When used correctly, the LICENSE system performs satisfactorily in measuring urine and intravenous fluids, although the oral device requires revision due to identified errors.

Automation in Flow Cytometry.

Automation in clinical flow cytometry has the potential to revolutionize the field by improving processes and enhancing efficiency and accuracy. Integrating advanced robotics and artificial intelligence, these technologies can streamline sample preparation, data acquisition, and analysis. Automated sample handling reduces human error and increases throughput, allowing laboratories to handle larger volumes with consistent precision. Intelligent algorithms contribute to rapid data interpretation, aiding in the identification of cellular markers for disease diagnosis and monitoring. This automation not only accelerates turnaround times but also ensures reproducibility, making clinical flow cytometry a reliable tool in the realm of personalized medicine and diagnostics.

Heparin Induced Thrombocytopenia Testing.

This article provides a comprehensive overview of Heparin-Induced Thrombocytopenia (HIT) with an emphasis on laboratory testing and advantages of automation. HIT is a critical condition arising from heparin exposure, leading to a contradictory combination of thrombocytopenia with an increased thrombosis risk. The article discusses HIT's history, clinical presentation, laboratory diagnosis, and management strategies. It highlights the importance of interdisciplinary collaboration for effective diagnosis and treatment, underscoring advancements in technology and targeted therapies that are shaping future approaches to HIT management.

Construction of a Calibration Curve for Lycopene on a Liquid-Handling Platform─Wider Lessons for the Development of Automated Dilution Protocols.

Liquid-handling is a fundamental operation in synthetic biology─all protocols involve one or more liquid-handling operations. It is, therefore, crucial that this step be carefully automated in order to unlock the benefits of automation (e.g., higher throughput, higher replicability). In the paper, we present a study, conducted at the London Biofoundry at SynbiCITE, that approaches liquid-handling and its reliable automation from the standpoint of the construction of the calibration curve for lycopene in dimethyl sulfoxide (DMSO). The study has important practical industrial applications (e.g., lycopene is a carotenoid of industrial interest, DMSO is a popular extractant). The study was also an effective testbed for the automation of liquid-handling. It necessitated the development of flexible liquid-handling methods, which can be generalizable to other automated applications. In addition, because lycopene/DMSO is a difficult mix, it was capable of revealing issues with automated liquid-handling protocols and stress-testing them. An important component of the study is the constraint that, due to the omnipresence of liquid-handling steps, errors should be controlled to a high standard. It is important to avoid such errors propagating to other parts of the protocol. To achieve this, a practical framework based on regression was developed and utilized throughout the study to identify, assess, and monitor transfer errors. The paper concludes with recommendations regarding automation of liquid-handling, which are applicable to a large set of applications (not just to complex liquids such as lycopene in DMSO or calibration curves).

The BioRECIPE Knowledge Representation Format.

The BioRECIPE (Biological system Representation for Evaluation, Curation, Interoperability, Preserving, and Execution) knowledge representation format was introduced to standardize and facilitate human-machine interaction while creating, verifying, evaluating, curating, and expanding executable models of intra- and intercellular signaling. This format allows a human user to easily preview and modify any model component, while it is at the same time readable by machines and can be processed by a suite of model development and analysis tools. The BioRECIPE format is compatible with multiple representation formats, natural language processing tools, modeling tools, and databases that are used by the systems and synthetic biology communities.

Drug Screening Using Normal Cell and Cancer Cell Mixture in an Automated 3D Cell Culture System.

Three-dimensional (3D) cell culture creates a more physiologically relevant environment for enhanced drug screening capabilities using microcarriers. An automated 3D system that integrates robotic manipulators, liquid handling systems, sensors, and environment control systems has the capacity to handle multiple samples in parallel, perform repetitive tasks, and provide real-time monitoring and analysis. This chapter describes a potential 3D cell culture drug screening model by combining renal proximal tubule cells as a representative normal cell line with cancer cell lines. This combination is subjected to drug screening to evaluate the drug's efficacy in suppressing cancer cells while minimizing impact on normal cells with the added benefit of having the ability to separate the two cell types by magnetic isolation for high content screens including mass spectrometry-based proteomics. This study presents advancements in 3D cell culture techniques, emphasizing the importance of automation and the potential of microcarriers in drug screening and disease modeling.

Automated Immunoprecipitation Workflow for Comprehensive Acetylome Analysis.

Immunoprecipitation is one of the most effective methods for enrichment of lysine-acetylated peptides for comprehensive acetylome analysis using mass spectrometry. Manual acetyl peptide enrichment method using non-conjugated antibodies and agarose beads has been developed and applied in various studies. However, it is time-consuming and can introduce contaminants and variability that leads to potential sample loss and decreased sensitivity and robustness of the analysis. Here we describe a fast, automated enrichment protocol that enables reproducible and comprehensive acetylome analysis using a magnetic bead-based immunoprecipitation reagent.

Poly(3,4-dihydroxyphenylalanine)-modified cellulose paper for the extraction of deoxyribonucleic acid by a laboratory-built automated extraction device.

The success of polymerase chain reaction (PCR) depends on the quality of deoxyribonucleic acid (DNA) templates. This study developed a cost-effective and eco-friendly DNA extraction system utilizing poly(3,4-dihydroxyphenylalanine)-modified cellulose paper (polyDOPA@paper). PolyDOPA@paper was prepared by oxidatively self-polymerizing DOPA under weak alkaline conditions and utilizing the adhesive property of polyDOPA on different materials. Compared to the uncoated cellulose paper, polyDOPA coating significantly enhances DNA adsorption owing to its abundant amino, carboxyl, and hydroxyl moieties. The DNA extraction mechanism using polyDOPA@paper was discussed. The maximum adsorption capacity of polyDOPA@paper for DNA was 20.7 µg cm-2. Moreover, an automated extraction system was designed and fabricated using 3D printing technology. The device simplifies the operation and ensures the reproducibility and consistency of the results. More importantly, it eliminates the need for specialized training of operators. The feasibility of the polyDOPA@paper-based automated extraction system was evaluated by quantitatively detecting Escherichia coli in spiked milk samples via a real-time PCR. The detection limit was 102 cfu mL-1. The results suggest that the system would have significant potential in detecting pathogens.

Laboratory automation and high-throughput biology.

BACKGROUND: Modern high-throughput technologies enable the processing of a large number of samples simultaneously, while also providing rapid and accurate procedures. In recent years, automated liquid handling workstations have emerged as an established technology for reproducible sample preparation. They offer flexibility, making them suitable for an expanding range of applications. Commonly, such approaches are well-developed for experimental procedures primarily designed for cell-line processing and xenobiotics testing. Conversely, little attention is focused on the application of automated liquid handlers in the analysis of whole organisms, which often involves time-consuming laboratory procedures. RESULTS: Here, Annona et al present a fully automated workflow for all steps, from RNA extraction to real-time PCR processing, for gene expression quantification in the ascidian marine model Ciona robusta. For procedure validation, the authors compared the results obtained with the liquid handler with those of the classical manual procedure. The outcome revealed comparable results, demonstrating a remarkable time saving particularly in the initial steps of sample processing. CONCLUSIONS: This work expands the possible application fields of this technology to whole-body organisms, mitigating issues that can arise from manual procedures. By minimizing errors, avoiding cross-contamination, decreasing hands-on time and streamlining the procedure, it could be employed for large-scale screening investigations.

Multilevel Confirmatory Factor Analysis Reveals Two Distinct Human-Automation Trust Constructs.

OBJECTIVE: This work examined the relationship of the constructs measured by the trust scales developed by Chancey et al. (2017) and Jian et al. (2000) using a multilevel confirmatory factor analysis (CFA). BACKGROUND: Modern theories of automation trust have been proposed based on data collected using trust scales. Chancey et al. (2017) adapted Madsen and Gregor's (2000) trust scale to align with Lee and See's (2004) human-automation trust framework. In contrast, Jian et al. (2000) developed a scale empirically with trust and distrust as factors. However, it remains unclear whether these two scales measure the same construct. METHOD: We analyzed data collected from previous experiments to investigate the relationship between the two trust scales using a multilevel CFA. RESULTS: Data provided evidence that Jian et al. (2000) and Chancey et al. (2017) automation trust scales are only weakly related. Trust and distrust are found to be distinct factors in Jian et al.'s (2000) scale, whereas performance, process, and purpose are distinct factors in Chancey et al.'s (2017) trust scale. CONCLUSION: The analysis suggested that the two scales purporting to measure human-automation trust are only weakly related. APPLICATION: Trust researchers and automation designers may consider using Chancey et al. (2017) and Jian et al. (2000) scales to capture different characteristics of human-automation trust.

Modeling package size-conscious automated dispensing cabinet replenishment to improve efficiency.

DISCLAIMER: In an effort to expedite the publication of articles, AJHP is posting manuscripts online as soon as possible after acceptance. Accepted manuscripts have been peer-reviewed and copyedited, but are posted online before technical formatting and author proofing. These manuscripts are not the final version of record and will be replaced with the final article (formatted per AJHP style and proofed by the authors) at a later time. PURPOSE: Optimization of automated dispensing cabinets (ADCs) has traditionally focused on modifying the inventory within these devices and ignored the replenishment process itself. Rounding replenishment quantities to the nearest package size, termed package size-conscious replenishment (PSCR), was investigated as a way to optimize labor needs for ADC replenishment. METHODS: A simulation of PSCR for a subset of medications stocked in ADCs at the University of North Carolina Medical Center was conducted. The simulation utilized real-world vend data and rounding factors to model the impact of PSCR on key ADC metrics. The final simulation utilized 2 months of ADC transactions across 410 medications in 149 ADCs. Four replenishment methodologies were simulated: standard replenishment and 3 PSCR strategies, including rounding down, rounding any direction, and rounding up. RESULTS: All 3 PSCR methodologies had significantly lower stockout frequencies than standard replenishment at 0.722% (P = 0.026) for rounding down, 0.698% (P = 0.024) for rounding any direction, and 0.680% (P = 0.024) for rounding up vs 0.773% for standard replenishment. PSCR methods were associated with significant time savings for both technician and pharmacist activities (P < 0.001 for all 3 strategies), with a savings of up to 0.27 technician and 0.52 pharmacist full-time equivalents estimated for the rounding-up methodology. Maximum carrying cost was higher for all 3 PSCR methodologies. CONCLUSION: PSCR was modeled to significantly decrease both pharmacist and technician time needed to replenish ADCs while also decreasing stockout frequency. Modest increases in maximum carrying cost were also shown. The simulation created for this evaluation could also be utilized to model other components of the ADC replenishment process.

Embracing the illusion of explanatory depth: A strategic framework for using iterative prompting for integrating large language models in healthcare education.

Healthcare educators are exploring ways to integrate Large Language Models (LLMs) into the curriculum. At the same time, they are concerned about the negative impact on students' cognitive development. There is concern that the students will not learn to think and problem-solve by themselves and instead become dependent on LLMs to find answers. In addition, the students could start accepting the LLM generated responses at face value. The Illusion of Explanatory Depth (IoED) is a cognitive bias where humans believe they understand complex phenomena in more depth than they do. This illusion is caused when people rely on external sources of information rather than deeper levels of internalized knowledge. This illusion can be exposed by asking follow-up in depth questions. Using the same approach, specifically iterative prompting, can help students interact with LLM's while learning actively, gaining deeper levels of knowledge, and exposing the LLM shortcomings. The article proposes that educators encourage use of LLMs to complete assignments using a template, that promotes students' reflections on their interactions with LLMs, using iterative prompting. This process based on IoED, and iterative prompting will help educators integrate LLMs in the curriculum while mitigating the risk of students becoming dependent on these tools. Students will practice active learning and experience firsthand the inaccuracies and inconsistencies in LLM responses.

Generic semi-automated radiofluorination strategy for single domain antibodies: [18F]FB-labelled single domain antibodies for PET imaging of fibroblast activation protein-α or folate receptor-α overexpression in cancer.

BACKGROUND: Radiofluorination of single domain antibodies (sdAbs) via N-succinimidyl-4-[18F]fluorobenzoate ([18F]SFB) has shown to be a promising strategy in the development of sdAb-based PET tracers. While automation of the prosthetic group (PG) [18F]SFB production, has been successfully reported, no practical method for large scale sdAb labelling has been reported. Therefore, we optimized and automated the PG production, enabling a subsequently efficient manual conjugation reaction to an anti-fibroblast activation protein (FAP)-α sdAb (4AH29) and an anti-folate receptor (FR)-α sdAb (2BD42). Both the alpha isoform of FAP and the FR are established tumour markers. FAP-α is known to be overexpressed mainly by cancer-associated fibroblasts in breast, ovarian, and other cancers, while its expression in normal tissues is low or undetectable. FR-α has an elevated expression in epithelial cancers, such as ovarian, brain and lung cancers. Non-invasive imaging techniques, such as PET-imaging, using tracers targeting specific tumour markers can provide molecular information over both the tumour and its environment, which aides in the diagnosis, therapy selection and assessment of the cancer treatment. RESULTS: [18F]SFB was synthesized using a fully automated three-step, one-pot reaction. The total procedure time was 54 min and results in [18F]SFB with a RCP > 90% and a RCY d.c. of 44 ± 4% (n = 13). The manual conjugation reaction after purification produced [18F]FB-sdAbs with a RCP > 95%, an end of synthesis activity > 600 MBq and an apparent molar activity > 10 GBq/µmol. Overall RCY d.c., corrected to the trapping of [18F]F- on the QMA, were 9% (n = 1) and 5 ± 2% (n = 3) for [18F]FB-2BD42 and [18F]FB-4AH29, respectively. CONCLUSION: [18F]SFB synthesis was successfully automated and upscaled on a Trasis AllInOne module. The anti-hFAP-α and anti-hFR-α sdAbs were radiofluorinated, yielding similar RCYs d.c. and RCPs, showing the potential of this method as a generic radiofluorination strategy for sdAbs. The radiofluorinated sdAbs showed a favourable biodistribution pattern and are attractive for further characterization as new PET tracers for FAP-α and FR-α imaging.

Automation of systematic reviews of biomedical literature: a scoping review of studies indexed in PubMed.

BACKGROUND: The demand for high-quality systematic literature reviews (SRs) for evidence-based medical decision-making is growing. SRs are costly and require the scarce resource of highly skilled reviewers. Automation technology has been proposed to save workload and expedite the SR workflow. We aimed to provide a comprehensive overview of SR automation studies indexed in PubMed, focusing on the applicability of these technologies in real world practice. METHODS: In November 2022, we extracted, combined, and ran an integrated PubMed search for SRs on SR automation. Full-text English peer-reviewed articles were included if they reported studies on SR automation methods (SSAM), or automated SRs (ASR). Bibliographic analyses and knowledge-discovery studies were excluded. Record screening was performed by single reviewers, and the selection of full text papers was performed in duplicate. We summarized the publication details, automated review stages, automation goals, applied tools, data sources, methods, results, and Google Scholar citations of SR automation studies. RESULTS: From 5321 records screened by title and abstract, we included 123 full text articles, of which 108 were SSAM and 15 ASR. Automation was applied for search (19/123, 15.4%), record screening (89/123, 72.4%), full-text selection (6/123, 4.9%), data extraction (13/123, 10.6%), risk of bias assessment (9/123, 7.3%), evidence synthesis (2/123, 1.6%), assessment of evidence quality (2/123, 1.6%), and reporting (2/123, 1.6%). Multiple SR stages were automated by 11 (8.9%) studies. The performance of automated record screening varied largely across SR topics. In published ASR, we found examples of automated search, record screening, full-text selection, and data extraction. In some ASRs, automation fully complemented manual reviews to increase sensitivity rather than to save workload. Reporting of automation details was often incomplete in ASRs. CONCLUSIONS: Automation techniques are being developed for all SR stages, but with limited real-world adoption. Most SR automation tools target single SR stages, with modest time savings for the entire SR process and varying sensitivity and specificity across studies. Therefore, the real-world benefits of SR automation remain uncertain. Standardizing the terminology, reporting, and metrics of study reports could enhance the adoption of SR automation techniques in real-world practice.

Automation of ePROMs in radiation oncology and its impact on patient response and bias.

PURPOSE: This study evaluates the impact of integrating a novel, in-house developed electronic Patient-Reported Outcome Measures (ePROMs) tool with a commercial Oncology Information System (OIS) on patient response rates and potential biases in real-world data science applications. MATERIALS AND METHODS: We designed an ePROMs tool using the NodeJS web application framework, automatically sending e-mail questionnaires to patients based on their treatment schedules in the OIS. The tool is used across various treatment sites to collect PROMs data in a real-world setting. This research examined the effects of increasing automation levels on both recruitment and response rates, as well as potential biases across different patient cohorts. Automation was implemented in three escalating levels, from telephone reminders for missing reports to minimal intervention from study nurses. RESULTS: From August 2020 to December 2023, 1,944 patients participated in the PROMs study. Our findings indicate that automating the workflows substantially reduced the patient management workload. However, higher levels of automation led to lower response rates, particularly in collecting late-phase symptoms in breast and head-and-neck cancer cohorts. Additionally, email-based PROMs introduced an age bias when recruiting new patients for the ePROMs study. Nevertheless, age was not a significant predictor of early dropout or missing symptom reports among patients participating. Notably, increased automation was significantly correlated with lower response rates in breast (p = 0.026) and head-and-neck cancer patients (p < 0.001). CONCLUSION: Integrating ePROMs within the OIS can significantly reduce workload and personnel resources. However, this efficiency may compromise patient responses in certain groups. A balance must be achieved between workload, resource allocation, and the sensitivity needed to detect clinically significant effects. This may necessitate customized automation levels tailored to specific cancer groups, highlighting a fundamental trade-off between operational efficiency and data quality.

Evaluation of Ethos intelligent optimization engine for left locally advanced breast cancer.

Purpose: To evaluate the feasibility to use a standard Ethos planning template to treat left-sided breast cancer with regional lymph nodes. Material/Methods: The tuning cohort of 5 patients was used to create a planning template. The validation cohort included 15 patients treated for a locally advanced left breast cancer randomly enrolled. The Ethos planning template was tuned using standard 3 partial arc VMAT and two collimator rotation configurations: 45/285/345° and 30/60/330°. Re-planning was performed automatically using the template without editing. The study was conducted with a schedule of 42.3 Gy in 18 fractions to the breast/chestwall, internal mammary chain (IMC) and regional lymph nodes ("Nodes"). The PTV was defined as a 3D extension of the CTV with a margin of 7 mm, excluding the 5mm below the skin. The manual treatment plans were performed using Eclipse treatment planning system with AAA and PO algorithms (v15.6) and a manual arc VMAT configuration and imported in Ethos TPS (v1.1) for a dose calculation with Ethos Acuros algorithm. The automated plans were compared with the manual plans using PTV and CTV coverage, homogeneity and conformity indices (HI and CN) and doses to organs at risk (OAR) via DVH metrics. For each plan, the patient quality assurance (QA) were performed using Mobius3D and gamma index. Finally, two breast radiation oncologists performed a blinded assessment of the clinical acceptability of each of the three plans (manual and automated) for each patient. Results: The manual and automated plans provided suitable treatment planning as regards dose constraints. The dosimetric comparison showed the CTV_breast D99% were significantly improved with both automated plans (p< 0,002) while PTV coverage was comparable. The doses to the organs at risk were equivalent for the three plans. Concerning treatment delivery, the Ethos-45° and Ethos-30° plans led to an increase in MUs compared to the manual plans, without affecting the beam on time. The average gamma index pass rates remained consistently above 98% regardless of the type of plan utilized. In the blinded evaluation, clinicians 1 and 2 assessed 13 out of 15 plans for Ethos 45° and 11 out of 15 plans for Ethos 30° as clinically acceptable. Conclusion: Using a standard planning template for locally advanced breast cancer, the Ethos TPS provided automated plans that were clinically acceptable and comparable in quality to manually generated plans. Automated plans also dramatically reduce workflow and operator variability.

The Impact of Laboratory Automation on the Time to Urine Microbiological Results: A Five-Year Retrospective Study.

Total laboratory automation (TLA) is a valuable component of microbiology laboratories and a growing number of publications suggest the potential impact of automation in terms of analysis standardization, streaking quality, and the turnaround time (TAT). The aim of this project was to perform a detailed investigation of the impact of TLA on the workflow of commonly treated specimens such as urine. This is a retrospective observational study comparing two time periods (pre TLA versus post TLA) for urine specimen culture processing. A total of 35,864 urine specimens were plated during the pre-TLA period and 47,283 were plated during the post-TLA period. The median time from streaking to identification decreased from 22.3 h pre TLA to 21.4 h post TLA (p < 0.001), and the median time from streaking to final validation of the report decreased from 24.3 h pre TLA to 23 h post TLA (p < 0.001). Further analysis revealed that the observed differences in TAT were mainly driven by the contaminated and positive samples. Our findings demonstrate that TLA has the potential to decrease turnaround times of samples in a laboratory. Nevertheless, changes in laboratory workflow (such as extended opening hours for plate reading and antibiotic susceptibility testing or decreased incubation times) might further maximize the efficiency of TLA and optimize TATs.

Development and assessment of an abbreviated medication regimen complexity index (the A-MRCI).

DISCLAIMER: In an effort to expedite the publication of articles, AJHP is posting manuscripts online as soon as possible after acceptance. Accepted manuscripts have been peer-reviewed and copyedited, but are posted online before technical formatting and author proofing. These manuscripts are not the final version of record and will be replaced with the final article (formatted per AJHP style and proofed by the authors) at a later time. PURPOSE: Adaptation of the Medication Regimen Complexity Index (MRCI) for automation in an electronic medical record has the potential to improve medication optimization and patient outcomes. The purpose of this study was to develop and evaluate an abbreviated medication regimen complexity index (A-MRCI) and compare its associations with patient-level factors to those of the MRCI. METHODS: The MRCI was modified via several rounds of review with an expert panel of clinical pharmacists and outcomes researchers. Medication data from 138 electronic health records were abstracted to calculate MRCI and A-MRCI scores for dosage form, dosing frequency, and additional directions. Comparison between indices was performed using inferential statistics for a 1-month sample of patients admitted to a cardiology or advanced heart failure service in 2017. RESULTS: A-MRCI scores were higher than MRCI scores (mean difference of 3.97, P < 0.0005; 95% CI, 2.21-5.71). A significant association was observed between the A-MRCI score and both length of stay (P = 0.0005) and polypharmacy (P < 0.0005), whereas an association between MRCI score and the patient-level factors examined was not demonstrated. CONCLUSION: On average, A-MRCI scores were higher and more likely to be associated with several patient-level factors. Internal analyses show the potential for integration into an electronic health record for automation. However, further exploration of the A-MRCI in a larger external validation sample is warranted.