Machine Learning Prediction Model to Predict Length of Stay of Patients Undergoing Hip or Knee Arthroplasties: Results from a High-Volume Single-Center Multivariate Analysis.

Background: The growth of arthroplasty procedures requires innovative strategies to reduce inpatients' hospital length of stay (LOS). This study aims to develop a machine learning prediction model that may aid in predicting LOS after hip or knee arthroplasties. Methods: A collection of all the clinical notes of patients who underwent elective primary or revision arthroplasty from 1 January 2019 to 31 December 2019 was performed. The hospitalization was classified as "short LOS" if it was less than or equal to 6 days and "long LOS" if it was greater than 7 days. Clinical data from pre-operative laboratory analysis, vital parameters, and demographic characteristics of patients were screened. Final data were used to train a logistic regression model with the aim of predicting short or long LOS. Results: The final dataset was composed of 1517 patients (795 "long LOS", 722 "short LOS", p = 0.3196) with a total of 1541 hospital admissions (729 "long LOS", 812 "short LOS", p < 0.001). The complete model had a prediction efficacy of 78.99% (AUC 0.7899). Conclusions: Machine learning may facilitate day-by-day clinical practice determination of which patients are suitable for a shorter LOS and which for a longer LOS, in which a cautious approach could be recommended.

MOSAIC: An Artificial Intelligence-Based Framework for Multimodal Analysis, Classification, and Personalized Prognostic Assessment in Rare Cancers.

PURPOSE: Rare cancers constitute over 20% of human neoplasms, often affecting patients with unmet medical needs. The development of effective classification and prognostication systems is crucial to improve the decision-making process and drive innovative treatment strategies. We have created and implemented MOSAIC, an artificial intelligence (AI)-based framework designed for multimodal analysis, classification, and personalized prognostic assessment in rare cancers. Clinical validation was performed on myelodysplastic syndrome (MDS), a rare hematologic cancer with clinical and genomic heterogeneities. METHODS: We analyzed 4,427 patients with MDS divided into training and validation cohorts. Deep learning methods were applied to integrate and impute clinical/genomic features. Clustering was performed by combining Uniform Manifold Approximation and Projection for Dimension Reduction + Hierarchical Density-Based Spatial Clustering of Applications with Noise (UMAP + HDBSCAN) methods, compared with the conventional Hierarchical Dirichlet Process (HDP). Linear and AI-based nonlinear approaches were compared for survival prediction. Explainable AI (Shapley Additive Explanations approach [SHAP]) and federated learning were used to improve the interpretation and the performance of the clinical models, integrating them into distributed infrastructure. RESULTS: UMAP + HDBSCAN clustering obtained a more granular patient stratification, achieving a higher average silhouette coefficient (0.16) with respect to HDP (0.01) and higher balanced accuracy in cluster classification by Random Forest (92.7% ± 1.3% and 85.8% ± 0.8%). AI methods for survival prediction outperform conventional statistical techniques and the reference prognostic tool for MDS. Nonlinear Gradient Boosting Survival stands in the internal (Concordance-Index [C-Index], 0.77; SD, 0.01) and external validation (C-Index, 0.74; SD, 0.02). SHAP analysis revealed that similar features drove patients' subgroups and outcomes in both training and validation cohorts. Federated implementation improved the accuracy of developed models. CONCLUSION: MOSAIC provides an explainable and robust framework to optimize classification and prognostic assessment of rare cancers. AI-based approaches demonstrated superior accuracy in capturing genomic similarities and providing individual prognostic information compared with conventional statistical methods. Its federated implementation ensures broad clinical application, guaranteeing high performance and data protection.

The long Pentraxin PTX3 serves as an early predictive biomarker of co-infections in COVID-19.

BACKGROUND: COVID-19 clinical course is highly variable and secondary infections contribute to COVID-19 complexity. Early detection of secondary infections is clinically relevant for patient outcome. Procalcitonin (PCT) and C-reactive protein (CRP) are the most used biomarkers of infections. Pentraxin 3 (PTX3) is an acute phase protein with promising performance as early biomarker in infections. In patients with COVID-19, PTX3 plasma concentrations at hospital admission are independent predictor of poor outcome. In this study, we assessed whether PTX3 contributes to early identification of co-infections during the course of COVID-19. METHODS: We analyzed PTX3 levels in patients affected by COVID-19 with (n = 101) or without (n = 179) community or hospital-acquired fungal or bacterial secondary infections (CAIs or HAIs). FINDINGS: PTX3 plasma concentrations at diagnosis of CAI or HAI were significantly higher than those in patients without secondary infections. Compared to PCT and CRP, the increase of PTX3 plasma levels was associated with the highest hazard ratio for CAIs and HAIs (aHR 11.68 and 24.90). In multivariable Cox regression analysis, PTX3 was also the most significant predictor of 28-days mortality or intensive care unit admission of patients with potential co-infections, faring more pronounced than CRP and PCT. INTERPRETATION: PTX3 is a promising predictive biomarker for early identification and risk stratification of patients with COVID-19 and co-infections. FUNDING: Dolce & Gabbana fashion house donation; Ministero della Salute for COVID-19; EU funding within the MUR PNRR Extended Partnership initiative on Emerging Infectious Diseases (Project no. PE00000007, INF-ACT) and MUR PNRR Italian network of excellence for advanced diagnosis (Project no. PNC-E3-2022-23683266 PNC-HLS-DA); EU MSCA (project CORVOS 860044).

Clinical and Genomic-Based Decision Support System to Define the Optimal Timing of Allogeneic Hematopoietic Stem-Cell Transplantation in Patients With Myelodysplastic Syndromes.

PURPOSE: Allogeneic hematopoietic stem-cell transplantation (HSCT) is the only potentially curative treatment for patients with myelodysplastic syndromes (MDS). Several issues must be considered when evaluating the benefits and risks of HSCT for patients with MDS, with the timing of transplantation being a crucial question. Here, we aimed to develop and validate a decision support system to define the optimal timing of HSCT for patients with MDS on the basis of clinical and genomic information as provided by the Molecular International Prognostic Scoring System (IPSS-M). PATIENTS AND METHODS: We studied a retrospective population of 7,118 patients, stratified into training and validation cohorts. A decision strategy was built to estimate the average survival over an 8-year time horizon (restricted mean survival time [RMST]) for each combination of clinical and genomic covariates and to determine the optimal transplantation policy by comparing different strategies. RESULTS: Under an IPSS-M based policy, patients with either low and moderate-low risk benefited from a delayed transplantation policy, whereas in those belonging to moderately high-, high- and very high-risk categories, immediate transplantation was associated with a prolonged life expectancy (RMST). Modeling decision analysis on IPSS-M versus conventional Revised IPSS (IPSS-R) changed the transplantation policy in a significant proportion of patients (15% of patient candidate to be immediately transplanted under an IPSS-R-based policy would benefit from a delayed strategy by IPSS-M, whereas 19% of candidates to delayed transplantation by IPSS-R would benefit from immediate HSCT by IPSS-M), resulting in a significant gain-in-life expectancy under an IPSS-M-based policy (P = .001). CONCLUSION: These results provide evidence for the clinical relevance of including genomic features into the transplantation decision making process, allowing personalizing the hazards and effectiveness of HSCT in patients with MDS.

Multimodal deep learning for COVID-19 prognosis prediction in the emergency department: a bi-centric study.

Predicting clinical deterioration in COVID-19 patients remains a challenging task in the Emergency Department (ED). To address this aim, we developed an artificial neural network using textual (e.g. patient history) and tabular (e.g. laboratory values) data from ED electronic medical reports. The predicted outcomes were 30-day mortality and ICU admission. We included consecutive patients from Humanitas Research Hospital and San Raffaele Hospital in the Milan area between February 20 and May 5, 2020. We included 1296 COVID-19 patients. Textual predictors consisted of patient history, physical exam, and radiological reports. Tabular predictors included age, creatinine, C-reactive protein, hemoglobin, and platelet count. TensorFlow tabular-textual model performance indices were compared to those of models implementing only tabular data. For 30-day mortality, the combined model yielded slightly better performances than the tabular fastai and XGBoost models, with AUC 0.87 ± 0.02, F1 score 0.62 ± 0.10 and an MCC 0.52 ± 0.04 (p < 0.32). As for ICU admission, the combined model MCC was superior (p < 0.024) to the tabular models. Our results suggest that a combined textual and tabular model can effectively predict COVID-19 prognosis which may assist ED physicians in their decision-making process.

Connecting the use of innovative treatments and glucocorticoids with the multidisciplinary evaluation through rule-based natural-language processing: a real-world study on patients with rheumatoid arthritis, psoriatic arthritis, and psoriasis.

Background: The impact of a multidisciplinary management of rheumatoid arthritis (RA), psoriatic arthritis (PsA), and psoriasis on systemic glucocorticoids or innovative treatments remains unknown. Rule-based natural language processing and text extraction help to manage large datasets of unstructured information and provide insights into the profile of treatment choices. Methods: We obtained structured information from text data of outpatient visits between 2017 and 2022 using regular expressions (RegEx) to define elastic search patterns and to consider only affirmative citation of diseases or prescribed therapy by detecting negations. Care processes were described by binary flags which express the presence of RA, PsA and psoriasis and the prescription of glucocorticoids and biologics or small molecules in each cases. Logistic regression analyses were used to train the classifier to predict outcomes using the number of visits and the other specialist visits as the main variables. Results: We identified 1743 patients with RA, 1359 with PsA and 2,287 with psoriasis, accounting for 5,677, 4,468 and 7,770 outpatient visits, respectively. Among these, 25% of RA, 32% of PsA and 25% of psoriasis cases received biologics or small molecules, while 49% of RA, 28% of PsA, and 40% of psoriasis cases received glucocorticoids. Patients evaluated also by other specialists were treated more frequently with glucocorticoids (70% vs. 49% for RA, 60% vs. 28% for PsA, 51% vs. 40% for psoriasis; p < 0.001) as well as with biologics/small molecules (49% vs. 25% for RA, 64% vs. 32% in PsA; 51% vs. 25% for psoriasis; p < 0.001) compared to cases seen only by the main specialist. Conclusion: Patients with RA, PsA, or psoriasis undergoing multiple evaluations are more likely to receive innovative treatments or glucocorticoids, possibly reflecting more complex cases.

Synthetic Data Generation by Artificial Intelligence to Accelerate Research and Precision Medicine in Hematology.

PURPOSE: Synthetic data are artificial data generated without including any real patient information by an algorithm trained to learn the characteristics of a real source data set and became widely used to accelerate research in life sciences. We aimed to (1) apply generative artificial intelligence to build synthetic data in different hematologic neoplasms; (2) develop a synthetic validation framework to assess data fidelity and privacy preservability; and (3) test the capability of synthetic data to accelerate clinical/translational research in hematology. METHODS: A conditional generative adversarial network architecture was implemented to generate synthetic data. Use cases were myelodysplastic syndromes (MDS) and AML: 7,133 patients were included. A fully explainable validation framework was created to assess fidelity and privacy preservability of synthetic data. RESULTS: We generated MDS/AML synthetic cohorts (including information on clinical features, genomics, treatment, and outcomes) with high fidelity and privacy performances. This technology allowed resolution of lack/incomplete information and data augmentation. We then assessed the potential value of synthetic data on accelerating research in hematology. Starting from 944 patients with MDS available since 2014, we generated a 300% augmented synthetic cohort and anticipated the development of molecular classification and molecular scoring system obtained many years later from 2,043 to 2,957 real patients, respectively. Moreover, starting from 187 MDS treated with luspatercept into a clinical trial, we generated a synthetic cohort that recapitulated all the clinical end points of the study. Finally, we developed a website to enable clinicians generating high-quality synthetic data from an existing biobank of real patients. CONCLUSION: Synthetic data mimic real clinical-genomic features and outcomes, and anonymize patient information. The implementation of this technology allows to increase the scientific use and value of real data, thus accelerating precision medicine in hematology and the conduction of clinical trials.

CT-based radiomics can identify physiological modifications of bone structure related to subjects' age and sex.

PURPOSE: Radiomics of vertebral bone structure is a promising technique for identification of osteoporosis. We aimed at assessing the accuracy of machine learning in identifying physiological changes related to subjects' sex and age through analysis of radiomics features from CT images of lumbar vertebrae, and define its generalizability across different scanners. MATERIALS AND METHODS: We annotated spherical volumes-of-interest (VOIs) in the center of the vertebral body for each lumbar vertebra in 233 subjects who had undergone lumbar CT for back pain on 3 different scanners, and we evaluated radiomics features from each VOI. Subjects with history of bone metabolism disorders, cancer, and vertebral fractures were excluded. We performed machine learning classification and regression models to identify subjects' sex and age respectively, and we computed a voting model which combined predictions. RESULTS: The model was trained on 173 subjects and tested on an internal validation dataset of 60. Radiomics was able to identify subjects' sex within single CT scanner (ROC AUC: up to 0.9714), with lower performance on the combined dataset of the 3 scanners (ROC AUC: 0.5545). Higher consistency among different scanners was found in identification of subjects' age (R2 0.568 on all scanners, MAD 7.232 years), with highest results on a single CT scanner (R2 0.667, MAD 3.296 years). CONCLUSION: Radiomics features are able to extract biometric data from lumbar trabecular bone, and determine bone modifications related to subjects' sex and age with great accuracy. However, acquisition from different CT scanners reduces the accuracy of the analysis.

Real-World Validation of Molecular International Prognostic Scoring System for Myelodysplastic Syndromes.

PURPOSE: Myelodysplastic syndromes (MDS) are heterogeneous myeloid neoplasms in which a risk-adapted treatment strategy is needed. Recently, a new clinical-molecular prognostic model, the Molecular International Prognostic Scoring System (IPSS-M) was proposed to improve the prediction of clinical outcome of the currently available tool (Revised International Prognostic Scoring System [IPSS-R]). We aimed to provide an extensive validation of IPSS-M. METHODS: A total of 2,876 patients with primary MDS from the GenoMed4All consortium were retrospectively analyzed. RESULTS: IPSS-M improved prognostic discrimination across all clinical end points with respect to IPSS-R (concordance was 0.81 v 0.74 for overall survival and 0.89 v 0.76 for leukemia-free survival, respectively). This was true even in those patients without detectable gene mutations. Compared with the IPSS-R based stratification, the IPSS-M risk group changed in 46% of patients (23.6% and 22.4% of subjects were upstaged and downstaged, respectively).In patients treated with hematopoietic stem cell transplantation (HSCT), IPSS-M significantly improved the prediction of the risk of disease relapse and the probability of post-transplantation survival versus IPSS-R (concordance was 0.76 v 0.60 for overall survival and 0.89 v 0.70 for probability of relapse, respectively). In high-risk patients treated with hypomethylating agents (HMA), IPSS-M failed to stratify individual probability of response; response duration and probability of survival were inversely related to IPSS-M risk.Finally, we tested the accuracy in predicting IPSS-M when molecular information was missed and we defined a minimum set of 15 relevant genes associated with high performance of the score. CONCLUSION: IPSS-M improves MDS prognostication and might result in a more effective selection of candidates to HSCT. Additional factors other than gene mutations can be involved in determining HMA sensitivity. The definition of a minimum set of relevant genes may facilitate the clinical implementation of the score.

Advanced Imaging Supports the Mechanistic Role of Autoimmunity and Plaque Rupture in COVID-19 Heart Involvement.

The cardiovascular system is frequently affected by coronavirus disease-19 (COVID-19), particularly in hospitalized cases, and these manifestations are associated with a worse prognosis. Most commonly, heart involvement is represented by myocarditis, myocardial infarction, and pulmonary embolism, while arrhythmias, heart valve damage, and pericarditis are less frequent. While the clinical suspicion is necessary for a prompt disease recognition, imaging allows the early detection of cardiovascular complications in patients with COVID-19. The combination of cardiothoracic approaches has been proposed for advanced imaging techniques, i.e., CT scan and MRI, for a simultaneous evaluation of cardiovascular structures, pulmonary arteries, and lung parenchyma. Several mechanisms have been proposed to explain the cardiovascular injury, and among these, it is established that the host immune system is responsible for the aberrant response characterizing severe COVID-19 and inducing organ-specific injury. We illustrate novel evidence to support the hypothesis that molecular mimicry may be the immunological mechanism for myocarditis in COVID-19. The present article provides a comprehensive review of the available evidence of the immune mechanisms of the COVID-19 cardiovascular injury and the imaging tools to be used in the diagnostic workup. As some of these techniques cannot be implemented for general screening of all cases, we critically discuss the need to maximize the sustainability and the specificity of the proposed tests while illustrating the findings of some paradigmatic cases.

Radiomics-based machine learning for the diagnosis of lymph node metastases in patients with head and neck cancer: Systematic review.

Machine learning (ML) is increasingly used to detect lymph node (LN) metastases in head and neck (H&N) carcinoma. We systematically reviewed the literature on radiomic-based ML for the detection of pathological LNs in H&N cancer. A systematic review was conducted in PubMed, EMBASE, and the Cochrane Library. Baseline study characteristics and methodological quality items (modeling, performance evaluation, clinical utility, and transparency items) were extracted and evaluated. The qualitative synthesis is presented using descriptive statistics. Seven studies were included in this study. Overall, the methodological quality items were generally favorable for modeling (57% of studies). The studies were mostly unsuccessful in terms of transparency (85.7%), evaluation of clinical utility (71.3%), and assessment of generalizability employing independent or external validation (72.5%). ML may be able to predict LN metastases in H&N cancer. Further studies are warranted to improve the generalizability assessment, clinical utility evaluation, and transparency items.

Artificial intelligence in gastroenterology: Where are we heading?

Background and study aims Artificial intelligence (AI) is set to impact several fields within gastroenterology. In gastrointestinal endoscopy, AI-based tools have translated into clinical practice faster than expected. We aimed to evaluate the status of research for AI in gastroenterology while predicting its future applications. Methods All studies registered on Clinicaltrials.gov up to November 2021 were analyzed. The studies included used AI in gastrointestinal endoscopy, inflammatory bowel disease (IBD), hepatology, and pancreatobiliary diseases. Data regarding the study field, methodology, endpoints, and publication status were retrieved, pooled, and analyzed to observe underlying temporal and geographical trends. Results Of the 103 study entries retrieved according to our inclusion/exclusion criteria, 76 (74 %) were based on AI application to gastrointestinal endoscopy, mainly for detection and characterization of colorectal neoplasia (52/103, 50 %). Image analysis was also more frequently reported than data analysis for pancreaticobiliary (six of 10 [60 %]), liver diseases (eight of nine [89 %]), and IBD (six of eight [75 %]). Overall, 48 of 103 study entries (47 %) were interventional and 55 (53 %) observational. In 2018, one of eight studies (12.5 %) were interventional, while in 2021, 21 of 34 (61.8 %) were interventional, with an inverse ratio between observational and interventional studies during the study period. The majority of the studies were planned as single-center (74 of 103 [72 %]) and more were in Asia (45 of 103 [44 %]) and Europe (44 of 103 [43 %]). Conclusions AI implementation in gastroenterology is dominated by computer-aided detection and characterization of colorectal neoplasia. The timeframe for translational research is characterized by a swift conversion of observational into interventional studies.

Artificial Intelligence Applied to Pancreatic Imaging: A Narrative Review.

The diagnosis, evaluation, and treatment planning of pancreatic pathologies usually require the combined use of different imaging modalities, mainly, computed tomography (CT), magnetic resonance imaging (MRI), and positron emission tomography (PET). Artificial intelligence (AI) has the potential to transform the clinical practice of medical imaging and has been applied to various radiological techniques for different purposes, such as segmentation, lesion detection, characterization, risk stratification, or prediction of response to treatments. The aim of the present narrative review is to assess the available literature on the role of AI applied to pancreatic imaging. Up to now, the use of computer-aided diagnosis (CAD) and radiomics in pancreatic imaging has proven to be useful for both non-oncological and oncological purposes and represents a promising tool for personalized approaches to patients. Although great developments have occurred in recent years, it is important to address the obstacles that still need to be overcome before these technologies can be implemented into our clinical routine, mainly considering the heterogeneity among studies.

Artificial intelligence processing electronic health records to identify commonalities and comorbidities cluster at Immuno Center Humanitas.

Background: Comorbidities are common in chronic inflammatory conditions, requiring multidisciplinary treatment approach. Understanding the link between a single disease and its comorbidities is important for appropriate treatment and management. We evaluate the ability of an NLP-based process for knowledge discovery to detect information about pathologies, patients' phenotype, doctors' prescriptions and commonalities in electronic medical records, by extracting information from free narrative text written by clinicians during medical visits, resulting in the extraction of valuable information and enriching real world evidence data from a multidisciplinary setting. Methods: We collected clinical notes from the Allergy Department of Humanitas Research Hospital written in the last 3 years and used it to look for diseases that cluster together as comorbidities associated to the main pathology of our patients, and for the extent of prescription of systemic corticosteroids, thus evaluating the ability of NLP-based tools for knowledge discovery to extract structured information from free text. Results: We found that the 3 most frequent comorbidities to appear in our clusters were asthma, rhinitis, and urticaria, and that 991 (of 2057) patients suffered from at least one of these comorbidities. The clusters which co-occur particularly often are oral allergy syndrome and urticaria (131 patients), angioedema and urticaria (105 patients), rhinitis and asthma (227 patients). With regards to systemic corticosteroid prescription volume by our clinicians, we found it was lower when compared to the therapy the patients followed before coming to our attention, with the exception of two diseases: Chronic obstructive pulmonary disease and Angioedema. Conclusions: This analysis seems to be valid and is confirmed by the data from the literature. This means that NLP tools could have significant role in many other research fields of medicine, as it may help identify other important, and possibly previously neglected clusters of patients with comorbidities and commonalities. Another potential benefit of this approach lies in its potential ability to foster a multidisciplinary approach, using the same drugs to treat pathologies normally treated by physicians in different branches of medicine, thus saving resources and improving the pharmacological management of patients.

An individualized algorithm to predict mortality in COVID-19 pneumonia: a machine learning based study.

Introduction: Identifying SARS-CoV-2 patients at higher risk of mortality is crucial in the management of a pandemic. Artificial intelligence techniques allow one to analyze large amounts of data to find hidden patterns. We aimed to develop and validate a mortality score at admission for COVID-19 based on high-level machine learning. Material and methods: We conducted a retrospective cohort study on hospitalized adult COVID-19 patients between March and December 2020. The primary outcome was in-hospital mortality. A machine learning approach based on vital parameters, laboratory values and demographic features was applied to develop different models. Then, a feature importance analysis was performed to reduce the number of variables included in the model, to develop a risk score with good overall performance, that was finally evaluated in terms of discrimination and calibration capabilities. All results underwent cross-validation. Results: 1,135 consecutive patients (median age 70 years, 64% male) were enrolled, 48 patients were excluded, and the cohort was randomly divided into training (760) and test (327) groups. During hospitalization, 251 (22%) patients died. After feature selection, the best performing classifier was random forest (AUC 0.88 ±0.03). Based on the relative importance of each variable, a pragmatic score was developed, showing good performances (AUC 0.85 ±0.025), and three levels were defined that correlated well with in-hospital mortality. Conclusions: Machine learning techniques were applied in order to develop an accurate in-hospital mortality risk score for COVID-19 based on ten variables. The application of the proposed score has utility in clinical settings to guide the management and prognostication of COVID-19 patients.

Generative Adversarial Networks in Brain Imaging: A Narrative Review.

Artificial intelligence (AI) is expected to have a major effect on radiology as it demonstrated remarkable progress in many clinical tasks, mostly regarding the detection, segmentation, classification, monitoring, and prediction of diseases. Generative Adversarial Networks have been proposed as one of the most exciting applications of deep learning in radiology. GANs are a new approach to deep learning that leverages adversarial learning to tackle a wide array of computer vision challenges. Brain radiology was one of the first fields where GANs found their application. In neuroradiology, indeed, GANs open unexplored scenarios, allowing new processes such as image-to-image and cross-modality synthesis, image reconstruction, image segmentation, image synthesis, data augmentation, disease progression models, and brain decoding. In this narrative review, we will provide an introduction to GANs in brain imaging, discussing the clinical potential of GANs, future clinical applications, as well as pitfalls that radiologists should be aware of.

Measuring the critical shoulder angle on radiographs: an accurate and repeatable deep learning model.

PURPOSE: Since the critical shoulder angle (CSA) is considered a risk factor for shoulder pathology and the intra- and inter-rater variabilities in its calculation are not negligible, we developed a deep learning model that calculates it automatically and accurately. METHODS: We used a dataset of 8467 anteroposterior x-ray images of the shoulder annotated with 3 landmarks of interest. A Convolutional Neural Network model coupled with a spatial to numerical transform (DSNT) layer was used to predict the landmark coordinates from which the CSA was calculated. The performances were evaluated by calculating the Euclidean distance between the ground truth coordinates and the predicted ones normalized with respect to the distance between the first and the second points, and the error between the CSA angle measured by a human observer and the predicted one. RESULTS: Regarding the normalized point distances, we obtained a median error of 2.9%, 2.5%, and 2% for the three points among the entire set. Considering CSA calculations, the median errors were 1° (standard deviation 1.2°), 0.88° (standard deviation 0.87°), and 0.99° (standard deviation 1°) for angles below 30°, between 30° and 35°, and above 35°, respectively. DISCUSSION: These results demonstrate that the model has the potential to be used in clinical settings where the replicability is important. The reported standard error of the CSA measurement is greater than 2° that is above the median error of our model, indicating a potential accuracy sufficient to be used in a clinical setting.