Internal Validation Dataset Research Articles

An artificial intelligence-enabled electrocardiogram model outperforms the revised cardiac risk index score for predicting major adverse cardiovascular events in patients undergoing noncardiac surgery

Abstract Background Existing clinical preoperative risk assessment tools such as the Revised Cardiac Risk Index (RCRI) have been used extensively to predict perioperative major adverse cardiovascular events (MACE). Electrocardiogram (ECG) analysis using Deep Learning can identify hidden features that human eyes cannot identify and might help further risk stratify patients undergoing noncardiac surgery. Objective We aimed to develop a Deep Learning model that predicts perioperative MACE in patients undergoing elective noncardiac surgeries. Methods We included patients ≥ 18-year-old who underwent elective non-cardiac surgery between 2000-2021. MACE was validated in duplicate and were defined as a composite of in-hospital myocardial infarction, cardiac arrest or mortality. A convolutional neural network was developed using ECGs within 30 days before surgery. We randomly split subjects into training, internal validation, and testing datasets in a 7:1:2 ratio. Performance was evaluated using the area under the receiver operator characteristics curve (AUC) values on the testing dataset. Models trained included AI-ECG models to predict in-hospital MACE and to predict in-hospital mortality, and AI-ECG+RCRI models to predict in-hospital MACE and to predict in-hospital mortality. All models were validated using 30-day validated outcomes (MACE or all-cause mortality) in a community-based cohort and were compared with the Revised Cardiac Risk Index (RCRI) score using AUC values. Findings: We included 195,214 patients who underwent a total of 241,999 surgeries. 169,214 ECGs were used in the training dataset, 24,234 in the internal validation dataset, and 48,551 in the testing dataset. In the test cohort, the AI-ECG algorithm discriminated risk for in-hospital MACE with an AUC of 0.82 (95% CI 0.79-0.85). The algorithm similarly discriminated 30-day MACE with an AUC value of 0.79 (95% CI 0.77-0.81) surpassing the discrimination of the RCRI score AUC of 0.69 (95% CI 0.66-0.72). All models’ performances are shown in Figure1A. The AI-ECG model to predict in-hospital mortality had an AUC of 0.83 (95% CI 0.80-0.86) and predicted 30-day mortality with an AUC of 0.80 (95% CI 0.77-0.82). Other models’ performances are shown Figure1B. Training the AI-ECG models including RCRI data did not improve the AI-ECG models’ performance. Conclusion AI-ECG models with no additional clinical data can improve perioperative risk prediction in non-cardiac surgery, outperforming a conventional and widely used risk stratification tool such as the RCRI.

Left atrial enlargement: a crucial indicator for identifying atrial fibrillation in patients with hypertension

Abstract Background Left atrial enlargement resulting from hypertension is closely linked to the development and persistence of atrial fibrillation (AF). The newly proposed staging recognizes AF as disease continuum, which makes us aware that AF prevention should focus on the Pre-AF stage, and atrial enlargement is one of the important manifestations in this stage. Previous scoring systems, such as CHA2DS2-VASc and C2HEST, along with the recently highlighted left atrial diameter (LAD), have been significant tools for predicting AF occurrence. However, a comprehensive assessment of their utility is currently lacking. Purpose This study aims to explore the role of left atrial size in identifying atrial fibrillation (AF) among hospitalized hypertensives, and to compare its recognition effectiveness with previous scoring systems. Methods We conducted a cross-sectional analysis within hospitalized hypertensives. The discovery, internal and external validation datasets were established. The XGBoost was employed to identify key variables related to AF occurrence, which were ranked based on their importance scores. To gauge the predictive prowess of LAD regarding AF occurrence, we plotted the receiver operating characteristic curve (ROC) and calculated the area under the curve (AUC). This enabled us to pinpoint the LAD cutoff value corresponding to the maximum Youden index, indicative of susceptibility to AF. Subsequently, Youden index determined the optimal cutoff value from the ROC curve. Delong’s test compared the identification abilities of different tools within the same dataset. Logistic regression analysis assessed the correlation between clinical variables and left atrial size. Results The XGBoost revealed 17 variables affecting AF occurrence in hypertensives, with LAD, age, and HF ranking among the top 3 (Figure 2a). LAD had a more pronounced impact on AF occurrence than other variables. LAD-based identification of AF in hypertensives had AUC of 0.827 (95%CI: 0.816-0.837), with an optimal cutoff of 38mm. Subgrouping the study population by LAD≥38mm, ROC curves showed AUCs of 0.757 (95%CI: 0.745-0.768) for the discovery set, 0.750 (95%CI: 0.731-0.768) for internal validation, and 0.759 (95%CI: 0.743-0.776) for external validation. LAD≥38mm had a more higher and stable AUC value for judging the AF occurrence than CHA2DS2-VASc and C2HEST scores (Figure 2b). Hypertensives with LAD≥38mm had a 9.72-fold higher AF risk than those with LAD<38mm. Conclusion LAD is a pivot determinant for AF occurrence. LAD≥38mm is a valuable identifier for high-risk hypertensives prone to AF.Figure 1.Center illustrationFigure 2.XGboost and Delong’s test of ROC

Automated quantification of cerebral microbleeds in susceptibility-weighted MRI: association with vascular risk factors, white matter hyperintensity burden, and cognitive function.

To train and validate a deep learning (DL)-based segmentation model for cerebral microbleeds (CMB) on susceptibility-weighted MRI; and to find associations between CMB, cognitive impairment, and vascular risk factors. Participants in this single-institution retrospective study underwent brain MRI to evaluate cognitive impairment between January-September 2023. For training the DL model, the nnU-Net framework was used without modifications. The DL model's performance was evaluated on independent internal and external validation datasets. Linear regression analysis was used to find associations between log-transformed CMB numbers, cognitive function (mini-mental status examination [MMSE]), white matter hyperintensity (WMH) burden, and clinical vascular risk factors (age, sex, hypertension, diabetes, lipid profiles, and body mass index). Training of the DL model (n = 287) resulted in a robust segmentation performance with an average dice score of 0.73 (95% CI, 0.67-0.79) in an internal validation set, (n = 67) and modest performance in an external validation set (dice score = 0.46, 95% CI, 0.33-0.59, n = 68). In a temporally independent clinical dataset (n = 448), older age, hypertension, and WMH burden were significantly associated with CMB numbers in all distributions (total, lobar, deep, and cerebellar; all P <.01). MMSE was significantly associated with hyperlipidemia (β = 1.88, 95% CI, 0.96-2.81, P <.001), WMH burden (β = -0.17 per 1% WMH burden, 95% CI, -0.27-0.08, P <.001), and total CMB number (β = -0.01 per 1 CMB, 95% CI, -0.02-0.001, P = .04) after adjusting for age and sex. The DL model showed a robust segmentation performance for CMB. In all distributions, CMB had significant positive associations with WMH burden. Increased WMH burden and CMB numbers were associated with decreased cognitive function. CMB = cerebral microbleed; DL = deep learning, DSC = dice similarity coefficient; MMSE = mini-mental status examination; SVD = small vessel disease; SWI = susceptibility-weighted image; WMH = white matter hyperintensity.

Development, validation, and visualization of a web-based nomogram for predicting chronic kidney disease incidence at health examination centers

Purpose To develop and validate a web-based nomogram for predicting new incident chronic kidney disease (CKD) within 4 years in a cohort undergoing routine physical examination from two health examination centers. Methods One center was utilized for training and internal validation of a nomogram model involving 6515 patients, while a separate center was employed for external validation with 3152 patients. Sixteen candidate predictors, including patient demographics, medical histories, physical examination, and laboratory test data, were included in this study to ascertain factors linked to new incident CKD. A nomogram was created to predict CKD risks using a logistic model. The nomogram’s performance was assessed using the area under the receiver operating characteristic curve (AUC), calibration plot, and decision curve analysis. Results Out of the 9667 healthy individuals included in the study with mean age of 46 years, sex ratio (male/female) of 1.69 (6075/3592), 118 (2.59%), 51 (2.61%), and 60 (1.90%) individuals developed CKD in the training (n = 4563), internal validation (n = 1952), and external validation (n = 3152) datasets, respectively. Age, history of diabetes mellitus, systolic blood pressure, serum creatinine, albumin, and triglyceride levels were used to build the nomogram, which yielded excellent discrimination ability (training cohort, AUC = 0.8806, 95% confidence interval [CI] 0.8472–0.9141; internal validation cohort, AUC = 0.8506, 95% CI 0.7856–0.9156; external validation cohort, AUC = 0.9183, 95% CI 0.8698–0.9669). We further developed a web-based calculator for convenient application (https://luochuxuan.shinyapps.io/dynnomapp/). Conclusion Our web-based nomogram accurately predicted CKD risks in Chinese health individuals and can be easily used in clinical settings.

External validation of an artificial intelligence multi-label deep learning model capable of ankle fracture classification

BackgroundAdvances in medical imaging have made it possible to classify ankle fractures using Artificial Intelligence (AI). Recent studies have demonstrated good internal validity for machine learning algorithms using the AO/OTA 2018 classification. This study aimed to externally validate one such model for ankle fracture classification and ways to improve external validity.MethodsIn this retrospective observation study, we trained a deep-learning neural network (7,500 ankle studies) to classify traumatic malleolar fractures according to the AO/OTA classification. Our internal validation dataset (IVD) contained 409 studies collected from Danderyd Hospital in Stockholm, Sweden, between 2002 and 2016. The external validation dataset (EVD) contained 399 studies collected from Flinders Medical Centre, Adelaide, Australia, between 2016 and 2020. Our primary outcome measures were the area under the receiver operating characteristic (AUC) and the area under the precision-recall curve (AUPR) for fracture classification of AO/OTA malleolar (44) fractures. Secondary outcomes were performance on other fractures visible on ankle radiographs and inter-observer reliability of reviewers.ResultsCompared to the weighted mean AUC (wAUC) 0.86 (95%CI 0.82–0.89) for fracture detection in the EVD, the network attained wAUC 0.95 (95%CI 0.94–0.97) for the IVD. The area under the precision-recall curve (AUPR) was 0.93 vs. 0.96. The wAUC for individual outcomes (type 44A-C, group 44A1-C3, and subgroup 44A1.1-C3.3) was 0.82 for the EVD and 0.93 for the IVD. The weighted mean AUPR (wAUPR) was 0.59 vs 0.63. Throughout, the performance was superior to that of a random classifier for the EVD.ConclusionAlthough the two datasets had considerable differences, the model transferred well to the EVD and the alternative clinical scenario it represents. The direct clinical implications of this study are that algorithms developed elsewhere need local validation and that discrepancies can be rectified using targeted training. In a wider sense, we believe this opens up possibilities for building advanced treatment recommendations based on exact fracture types that are more objective than current clinical decisions, often influenced by who is present during rounds.

Image-based ECG analyzing deep-learning algorithm to predict biological age and mortality risks: interethnic validation.

Cardiovascular risk assessment is a critical component of healthcare, guiding preventive and therapeutic strategies. In this study, we developed and evaluated an image-based electrocardiogram (ECG) analyzing an artificial intelligence (AI) model that estimates biological age and mortality risk. Using a dataset of 978 319 ECGs from 250 145 patients at Seoul National University Bundang Hospital, we developed a deep-learning model utilizing printed 12-lead ECG images to estimate patients' age (ECG-Age) and 1- and 5-year mortality risks. The model was validated externally using the CODE-15% dataset from Brazil. The ECG-Age showed a high correlation with chronological age in both the internal and external validation datasets (Pearson's R = 0.888 and 0.852, respectively). In the internal validation, the direct mortality risk prediction models showed area under the curves (AUCs) of 0.843 and 0.867 for 5- and 1-year all-cause mortality, respectively. For 5- and 1-year cardiovascular mortality, the AUCs were 0.920 and 0.916, respectively. In the CODE-15%, the mortality risk predictions showed AUCs of 0.818 and 0.836 for the prediction of 5- and 1-year all-cause mortality, respectively. Compared to the neutral Delta-Age (ECG-Age - chronological age) group, hazard ratios for deaths were 1.88 [95% confidence interval (CI): 1.14-3.92], 2.12 (95% CI: 1.15-3.92), 4.46 (95% CI: 2.22-8.96) and 7.68 (95% CI: 3.32-17.76) for positive Delta-Age groups (5-10, 10-15, 15-20, >20), respectively. An image-based AI-ECG model is a feasible tool for estimating biological age and assessing all-cause and cardiovascular mortality risks, providing a practical approach for utilizing standardized ECG images in predicting long-term health outcomes.

Comparative prognosis analysis of ovarian squamous cell carcinoma versus serous carcinoma: Insights from the SEER database.

The aim of this study was to identify survival rates and potential prognostic factors of ovarian squamous cell carcinoma (OSCC), offering valuable insights for clinical decision making. Leveraging the Surveillance, Epidemiology, and End Results (SEER) database, we selected 11 078 serous carcinoma (SC) patients and 198 OSCC patients based on predetermined criteria diagnosed from 2000 to 2020. We compared the overall survival (OS) and cancer-specific survival (CSS) before and after propensity score matching (PSM) in two groups. Prognostic differences were also compared between OSCC and SC groups at different stages. Univariate and multivariate Cox regression analyses were performed to investigate the impact of clinical and pathologic variables on the survival of patients with OSCC. Finally, we developed and validated a nomogram predictive model. OSCC tumors exhibited distinct characteristics, being relatively larger, more frequently unilateral, and better differentiated than SC tumors. After PSM, Kaplan-Meier analysis revealed significantly lower survival rates for OSCC patients in Stages IIB-IV, while Stages IA-IC displayed comparable survival. Independent risk factors for OSCC patients included advanced age, single marital status, higher tumor stage, and increased tumor size. Conversely, higher median household income and chemotherapy emerged as independent protective factors. Our predictive model and nomogram accurately forecasted patient survival rates in both SEER and internal validation datasets. OSCC patients face significantly poorer prognosis than their SC counterparts, except in the very early stages. Higher median household income was associated with better OSCC survival.

Internal validation of modified Mirels’ scoring system for pathologic femur fractures

BackgroundThe proximal femur is a common site of bone metastasis. The Mirels’ score is a frequently utilized system to identify patients at risk for pathologic fracture and while it has consistently demonstrated strong sensitivity, specificity has been relatively poor. Our group previously developed a Modified Mirels’ scoring system which demonstrated improved ability to predict cases at risk of fracture in this patient population through modification of the Mirels’ location score. The purpose of the present study is to internally validate this newly developed scoring system on an independent patient series.MethodsRetrospective review was performed to identify patients who were evaluated for proximal femoral bone lesions. Patients were stratified into one of two groups: 1) those who went on to fracture within 4 months after initial evaluation (Fracture Group) and 2) those who did not fracture within 4 months of initial evaluation (No Fracture Group). Retrospective chart review was performed to assign an Original Mirels’ (OM) Score and Modified Mirels’ (MM) score to each patient at the time of initial evaluation. Descriptive statistics, logistic regression, receiver operating curve, and net benefit analyses were performed to determine the predictability of fractures when utilizing both scoring systems.ResultsThe use of the MM scoring improved fracture prediction over OM scoring for patients observed over a 4 month follow up based on logistic regression. Decision curve analysis showed that there was a net benefit using the MM score over the OM scoring for a full range of fracture threshold probabilities. Fracture prevalence was similar for current internal validation dataset when compared to the dataset of our index study with a comparable reduction in misclassification of fracture prediction when utilizing the modified scoring system versus the original.ConclusionsUse of MM scoring was found to improve fracture prediction over OM scoring when tested on an internal validation set of patients with disseminated metastatic lesions to the proximal femur. The improvement in fracture prediction demonstrated in the present study mirrored the results of our index study during which the MM system was developed.

Prediction of Microinvasion in Breast Ductal Carcinoma in Situ Using Conventional Ultrasound Combined with Contrast-Enhanced Ultrasound Features: A Two-Center Study

BackgroundTo develop and validate a model based on conventional ultrasound (CUS) and contrast-enhanced ultrasound (CEUS) features to preoperatively predict microinvasion in breast ductal carcinoma in situ (DCIS). Patients and MethodsData from 163 patients with DCIS who underwent CUS and CEUS from the internal hospital was retrospectively collected and randomly apportioned into training and internal validation sets in a ratio of 7:3. External validation set included 56 patients with DCIS from the external hospital. Univariate and multivariate logistic regression analysis were performed to determine the independent risk factors associated with microinvasion. These factors were used to develop predictive models. The performance was evaluated through calibration, discrimination, and clinical utility. ResultsMultivariate analysis indicated that centripetal enhancement direction (odds ratio [OR], 13.268; 95% confidence interval [CI], 3.687-47.746) and enhancement range enlarged on CEUS (OR, 4.876; 95% CI, 1.470-16.181), lesion size of ≥20 mm (OR, 3.265; 95% CI, 1.230-8.669) and calcification detected on CUS (OR, 5.174; 95% CI, 1.903-14.066) were independent risk factors associated with microinvasion. The nomogram incorporated the CUS and CEUS features achieved favorable discrimination (AUCs of 0.850, 0.848, and 0.879 for the training, internal and external validation datasets), with good calibration. The nomogram outperformed the CUS model and CEUS model (all P < .05). Decision curve analysis confirmed that the predictive nomogram was clinically useful. ConclusionThe nomogram based on CUS and CEUS features showed promising predictive value for the preoperative identification of microinvasion in patients with DCIS.

Longitudinal registration of thoracic CT images with radiation-induced lung diseases: A divide-and-conquer approach based on component structure wise registration using coherent point drift

Background and ObjectiveRegistration of pulmonary computed tomography (CT) images with radiation-induced lung diseases (RILD) was essential to investigate the voxel-wise relationship between the formation of RILD and the radiation dose received by different tissues. Although various approaches had been developed for the registration of lung CTs, their performances remained clinically unsatisfactory for registration of lung CT images with RILD. The main difficulties arose from the longitudinal change in lung parenchyma, including RILD and volumetric change of lung cancers, after radiation therapy, leading to inaccurate registration and artifacts caused by erroneous matching of the RILD tissues. MethodsTo overcome the influence of the parenchymal changes, a divide-and-conquer approach rooted in the coherent point drift (CPD) paradigm was proposed. The proposed method was based on two kernel ideas. One was the idea of component structure wise registration. Specifically, the proposed method relaxed the intrinsic assumption of equal isotropic covariances in CPD by decomposing a lung and its surrounding tissues into component structures and independently registering the component structures pairwise by CPD. The other was the idea of defining a vascular subtree centered at a matched branch point as a component structure. This idea could not only provide a sufficient number of matched feature points within a parenchyma, but avoid being corrupted by the false feature points resided in the RILD tissues due to globally and indiscriminately sampling using mathematical operators. The overall deformation model was built by using the Thin Plate Spline based on all matched points. ResultsThis study recruited 30 pairs of lung CT images with RILD, 15 of which were used for internal validation (leave-one-out cross-validation) and the other 15 for external validation. The experimental results showed that the proposed algorithm achieved a mean and a mean of maximum 1 % of average surface distances <2 and 8 mm, respectively, and a mean and a maximum target registration error <2 mm and 5 mm on both internal and external validation datasets. The paired two-sample t-tests corroborated that the proposed algorithm outperformed a recent method, the Stavropoulou's method, on the external validation dataset (p < 0.05). ConclusionsThe proposed algorithm effectively reduced the influence of parenchymal changes, resulting in a reasonably accurate and artifact-free registration.

A graph-learning based model for automatic diagnosis of Sjögren’s syndrome on digital pathological images: a multicentre cohort study

BackgroundSjögren’s Syndrome (SS) is a rare chronic autoimmune disorder primarily affecting adult females, characterized by chronic inflammation and salivary and lacrimal gland dysfunction. It is often associated with systemic lupus erythematosus, rheumatoid arthritis and kidney disease, which can lead to increased mortality. Early diagnosis is critical, but traditional methods for diagnosing SS, mainly through histopathological evaluation of salivary gland tissue, have limitations.MethodsThe study used 100 labial gland biopsy, creating whole-slide images (WSIs) for analysis. The proposed model, named Cell-tissue-graph-based pathological image analysis model (CTG-PAM) and based on graph theory, characterizes single-cell feature, cell-cell feature, and cell-tissue feature. Building upon these features, CTG-PAM achieves cellular-level classification, enabling lymphocyte recognition. Furthermore, it leverages connected component analysis techniques in the cell graph structure to perform SS diagnosis based on lymphocyte counts.FindingsCTG-PAM outperforms traditional deep learning methods in diagnosing SS. Its area under the receiver operating characteristic curve (AUC) is 1.0 for the internal validation dataset and 0.8035 for the external test dataset. This indicates high accuracy. The sensitivity of CTG-PAM for the external dataset is 98.21%, while the accuracy is 93.75%. In comparison, the sensitivity and accuracy for traditional deep learning methods (ResNet-50) are lower. The study also shows that CTG-PAM’s diagnostic accuracy is closer to skilled pathologists compared to beginners.InterpretationOur findings indicate that CTG-PAM is a reliable method for diagnosing SS. Additionally, CTG-PAM shows promise in enhancing the prognosis of SS patients and holds significant potential for the differential diagnosis of both non-neoplastic and neoplastic diseases. The AI model potentially extends its application to diagnosing immune cells in tumor microenvironments.

Extending Canadian forest disturbance history maps prior to 1985

AbstractAn accurate depiction of wildfire, harvesting, and insect outbreak disturbances is essential for sustainable ecosystem management of forests in Canada. Even though the advent of temporally consistent 30‐m resolution Landsat data has enabled the detailed mapping of forest disturbances in Canada from 1985 onward, the disturbance record prior to 1985 remains sparse. This study aimed to extend the existing pre‐1985 disturbance history record by mapping wildfire, harvest, and insect outbreaks in Canadian forests between 1965 and 1984. Our geospatial data processing methodology relied on multilayer perceptrons (MLP) trained on spectral recovery signatures to map and age these disturbances. Our model detected approximately 4.8, 7.3, and 3.8 million ha of burnt, harvested, and insect‐ravaged forest areas, respectively, that were absent from national and provincial disturbance databases and forest inventories. Results were validated using both internal and external validation datasets. Our disturbance detection methodology was highly effective, with an internal validation kappa score of 0.91 and an external score of 0.81. The fire and harvest age disturbance MLPs, whose predictions can also be used as a proxy of forest stand age, performed adequately on the internal (fire R2 = 0.675; root mean squared error [RMSE] = 4.42; harvest R2 = 0.723; RMSE = 3.17) and external validation datasets (fire R2 = 0.242; RMSE = 4.69; harvest R2 = 0.257; RMSE = 5.46), outperforming existing forest age disturbance products. Finally, we relied on several open data products, such as provincial forest inventories, to correct our disturbance type and year prediction whenever these more reliable, but incomplete, data sources were available. Specific years were not assigned to insect outbreaks due to the lack of dependable training and validation data. We also illustrate how extending the existing forest disturbance record by 20 years may provide a more in‐depth understanding of landscape‐disturbance dynamics with a case study of the 2023 Canadian wildfire season.

Artificial intelligence-based personalized clinical decision-making for patients with localized prostate cancer: surgery versus radiotherapy.

Surgery and radiotherapy are primary nonconservative treatments for prostate cancer (PCa). However, personalizing treatment options between these treatment modalities is challenging due to unclear criteria. We developed an artificial intelligence (AI)-based model that can identify patients with localized PCa who would benefit more from either radiotherapy or surgery, thereby providing personalized clinical decision-making. Data from consecutive patients with localized PCa who received radiotherapy or surgery with complete records of clinicopathological variables and follow-up results in 12 registries of the Surveillance, Epidemiology, and End Results database were analyzed. Patients from 7 registries were randomly assigned to training (TD) and internal validation datasets (IVD) at a 9:1 ratio. The remaining 5 registries constituted the external validation dataset (EVD). TD was divided into training-radiotherapy (TRD) and training-surgery (TSD) datasets, and IVD was divided into internal-radiotherapy (IRD) and internal-surgery (ISD) datasets. Six models for radiotherapy and surgery were trained using TRD and TSD to predict radiotherapy survival probability (RSP) and surgery survival probability (SSP), respectively. The models with the highest concordance index (C-index) on IRD and ISD were chosen to form the final treatment recommendation model (FTR). FTR recommendations were based on the higher value between RSP and SSP. Kaplan-Meier curves were generated for patients receiving recommended (consistent group) and nonrecommended treatments (inconsistent group), which were compared using the log-rank test. The study included 118 236 patients, categorized into TD (TRD: 44 621; TSD: 41 500), IVD (IRD: 4949; ISD: 4621), and EVD (22 545). Both radiotherapy and surgery models accurately predicted RSP and SSP (C-index: 0.735-0.787 and 0.769-0.797, respectively). The consistent group exhibited higher survival rates than the inconsistent group, particularly among patients not suitable for active surveillance (P < .001). FTR accurately identifies patients with localized PCa who would benefit more from either radiotherapy or surgery, offering clinicians an effective AI tool to make informed choices between these 2 treatments.

Development and validation of early prediction models for new-onset functional impairment of patients with trauma at hospital discharge.

Early identification of individuals at risk of functional impairment after trauma is crucial for the timely clinical decision-making and intervention to improve reintegration into the society. This study aimed to develop and validate models for predicting new-onset functional impairment after trauma using predictors that are routinely collected within 2 days of hospital admission. In this multicenter retrospective cohort study of acute care hospitals in Japan, we identified adult patients with trauma with independence in carrying out activities of daily living before hospitalization, treated in the intensive or high-dependency care unit, and survived for at least 2 days between April 2008 and September 2023. The primary outcome was functional impairment defined as Barthel Index ≤60 at hospital discharge. In the internal validation data set (between April 2008 and August 2022), using the routinely collected 129 candidate predictors within 2 days of admission, we trained and tuned the four conventional and machine learning models with repeated random subsampling cross-validation. We measured the performance of these models in the temporal validation data set (between September 2022 and September 2023). We also computed the importance of each predictor variable in our model. We identified 8,529 eligible patients. Functional impairment at discharge was observed in 41% of the patients (n = 3,506/8,529). In the temporal validation data set, all four models showed moderate discrimination ability, with areas under the curve above 0.79, and extreme gradient boosting showing the best performance (0.83). In the variable importance analyses, age was the most important predictor, followed by consciousness, severity score, cervical spinal cord injury, mild dementia, and serum albumin level at admission. We successfully developed early prediction models for patients with trauma with new-onset functional impairment at discharge that achieved high predictive performance using routinely collected data within 2 days of hospital admission. Prognostic/Epidemiological; Level II.

Development of a deep learning-based fully automated segmentation of rotator cuff muscles from clinical MR scans.

The fatty infiltration and atrophy in the muscle after a rotator cuff (RC) tear are important in surgical decision-making and are linked to poor clinical outcomes after rotator cuff repair. An accurate and reliable quantitative method should be developed to assess the entire RC muscles. To develop a fully automated approach based on a deep neural network to segment RC muscles from clinical magnetic resonance imaging (MRI) scans. In total, 94 shoulder MRI scans (mean age = 62.3 years) were utilized for the training and internal validation datasets, while an additional 20 MRI scans (mean age = 62.6 years) were collected from another institution for external validation. An orthopedic surgeon and a radiologist manually segmented muscles and bones as reference masks. Segmentation performance was evaluated using the Dice score, sensitivities, precision, and percent difference in muscle volume (%). In addition, the segmentation performance was assessed based on sex, age, and the presence of a RC tendon tear. The average Dice score, sensitivities, precision, and percentage difference in muscle volume of the developed algorithm were 0.920, 0.933, 0.912, and 4.58%, respectively, in external validation. There was no difference in the prediction of shoulder muscles, with the exception of teres minor, where significant prediction errors were observed (0.831, 0.854, 0.835, and 10.88%, respectively). The segmentation performance of the algorithm was generally unaffected by age, sex, and the presence of RC tears. We developed a fully automated deep neural network for RC muscle and bone segmentation with excellent performance from clinical MRI scans.

P-383 Development and validation of a visualized prediction model for early miscarriage risk in patients undergoing IVF/ICSI procedures: a real-world multi-center study

Abstract Study question What are the key predictors of early miscarriage in patients undergoing IVF/ICSI treatment? Summary answer This study identified risk factors for early miscarriage in IVF/ICSI patients, and developed a validated predictive nomogram, highlighting age-dependent factor variations. What is known already Early miscarriage, occurring in 15-20% of confirmed pregnancies, can lead to complications, psychological distress, and fertility impairment. It is especially prevalent during the first trimester, with up to 80% of all miscarriages happening during this phase. Women who conceive via Assisted Reproductive Technology (ART) face higher stress levels and increased risk of miscarriage. Although many contributing factors to early miscarriage have been identified, there is a scarcity of integrated predictive models for IVF/ICSI patients. This paper aims to develop a validated, user-friendly nomogram to predict first-trimester miscarriage risk in IVF/ICSI patients and help clinicians and patients make informed decisions. Study design, size, duration A retrospective analysis was conducted on 20,322 first cycles out of 31,307 for IVF/ICSI at a reproductive centre in Southern China, After excluding ineligible cycles, 6,724 first fresh cycles were included and randomly divided into a training dataset (n = 4,516) and an internal validation dataset (n = 2,208). An external validation dataset (n = 1,179) was obtained from a reproductive center in Northern China, further ensuring the robustness and generalizability of the findings. Participants/materials, setting, methods This retrospective study analysed 6,724 out of 31,307 IVF/ICSI treatments from 2011 to 2020 at a Southern China reproductive center and 1,179 cycles from a Northern China center (2013-2018) for validation. Early miscarriage was defined as a loss before 12 weeks’ gestation. Patients were divided into two age groups: ≥35 and &amp;lt;35 years. The study followed the TRIPOD statement and received Institutional Review Board approval. Main results and the role of chance The study found statistically significant differences across the training, internal validation, and external validation sets in terms of patient age, BMI, number of good quality embryos, antral follicle count (AFC), basal testosterone (T), luteinizing hormone (LH) levels, among other variables. The early miscarriage rates were 9.43%, 10.55%, and 13.50% across these sets. Elder women (age ≥35 years) had a higher duration of infertility and early miscarriage rate, but lower AFC and numbers of retrieved oocytes, 2PN, and MII oocytes compared to younger women (age &amp;lt;35 years). A nomogram prediction model was developed using variables such as female age, BMI, number of spontaneous abortions, number of induced abortions, and basal FSH, which were found to be independent prognostic factors for early miscarriage. The model’s performance was validated using AUC, calibration plots, and DCA, indicating acceptable performance and good agreement between prediction and observation. The model was more beneficial for predicting miscarriage risk than the treat-all or treat-none schemes. Subgroup analysis for elder and younger women showed different risk factors for miscarriage, notably female age, basal FSH for elder women, and female age, BMI, and the number of spontaneous abortions for younger women. The subgroup models also showed consistent results and good clinical relevance. Limitations, reasons for caution The retrospective design of our study may have introduced certain limitations and potential biases. To overcome these limitations, it is advisable that future research endeavors adopt a prospective clinical study design. Wider implications of the findings This study uses a diverse dataset and rigorous methods to create a user-friendly prediction model for early miscarriage in ART. By considering regional differences, it ensures the model’s broader applicability and accuracy, enabling personalized treatment strategies and improving infertility treatment outcomes. Trial registration number The study was a retrospective study, and it was approved by the Institutional Review Boards of Sun Yat-Sen Memorial Hospital (SYSEC-KY-KS-2021-121) and the First Affiliated Hospital of Xinjiang Medical University (K202106-17) and is reported in accordance with the TRIPOD statement

Derivation and validation of the first web-based nomogram to predict the spontaneous pregnancy after reproductive surgery using machine learning models.

Infertility remains a significant global burden over the years. Reproductive surgery is an effective strategy for infertile women. Early prediction of spontaneous pregnancy after reproductive surgery is of high interest for the patients seeking the infertility treatment. However, there are no high-quality models and clinical applicable tools to predict the probability of natural conception after reproductive surgery. The eligible data involving 1013 patients who operated for infertility between June 2016 and June 2021 in Yantai Yuhuangding Hospital in China, were randomly divided into training and internal testing cohorts. 195 subjects from the Linyi People's Hospital in China were considered for external validation. Both univariate combining with multivariate logistic regression and the least absolute shrinkage and selection operator (LASSO) algorithm were performed to identify independent predictors. Multiple common machine learning algorithms, namely logistic regression, decision tree, random forest, support vector machine, k-nearest neighbor, and extreme gradient boosting, were employed to construct the predictive models. The optimal model was verified by evaluating the model performance in both the internal and external validation datasets. Six clinical indicators, including female age, infertility type, duration of infertility, intraoperative diagnosis, ovulation monitoring, and anti-Müllerian hormone (AMH) level, were screened out. Based on the logistic regression model's superior clinical predictive value, as indicated by the area under the receiver operating characteristic curve (AUC) in both the internal (0.870) and external (0.880) validation sets, we ultimately selected it as the optimal model. Consequently, we utilized it to generate a web-based nomogram for predicting the probability of spontaneous pregnancy after reproductive surgery. Furthermore, the calibration curve, Hosmer-Lemeshow (H-L) test, the decision curve analysis (DCA) and clinical impact curve analysis (CIC) demonstrated that the model has superior calibration degree, clinical net benefit and generalization ability, which were confirmed by both internal and external validations. Overall, our developed first nomogram with online operation provides an early and accurate prediction for the probability of natural conception after reproductive surgery, which helps clinicians and infertile couples make sensible decision of choosing the mode of subsequent conception, natural or IVF, to further improve the clinical practices of infertility treatment.

Radiomics based on HRCT can predict RP-ILD and mortality in anti-MDA5 + dermatomyositis patients: a multi-center retrospective study

ObjectivesTo assess the effectiveness of HRCT-based radiomics in predicting rapidly progressive interstitial lung disease (RP-ILD) and mortality in anti-MDA5 positive dermatomyositis-related interstitial lung disease (anti-MDA5 + DM-ILD).MethodsFrom August 2014 to March 2022, 160 patients from Institution 1 were retrospectively and consecutively enrolled and were randomly divided into the training dataset (n = 119) and internal validation dataset (n = 41), while 29 patients from Institution 2 were retrospectively and consecutively enrolled as external validation dataset. We generated four Risk-scores based on radiomics features extracted from four areas of HRCT. A nomogram was established by integrating the selected clinico-radiologic variables and the Risk-score of the most discriminative radiomics model. The RP-ILD prediction performance of the models was evaluated by using the area under the receiver operating characteristic curves, calibration curves, and decision curves. Survival analysis was conducted with Kaplan-Meier curves, Mantel-Haenszel test, and Cox regression.ResultsOver a median follow-up time of 31.6 months (interquartile range: 12.9–49.1 months), 24 patients lost to follow-up and 46 patients lost their lives (27.9%, 46/165). The Risk-score based on bilateral lungs performed best, attaining AUCs of 0.869 and 0.905 in the internal and external validation datasets. The nomogram outperformed clinico-radiologic model and Risk-score with AUCs of 0.882 and 0.916 in the internal and external validation datasets. Patients were classified into low- and high-risk groups with 50:50 based on nomogram. High-risk group patients demonstrated a significantly higher risk of mortality than low-risk group patients in institution 1 (HR = 4.117) and institution 2 cohorts (HR = 7.515).ConclusionFor anti-MDA5 + DM-ILD, the nomogram, mainly based on radiomics, can predict RP-ILD and is an independent predictor of mortality.

A simple and effective machine learning model for predicting the stability of intracranial aneurysms using CT angiography.

It is vital to accurately and promptly distinguish unstable from stable intracranial aneurysms (IAs) to facilitate treatment optimization and avoid unnecessary treatment. The aim of this study is to develop a simple and effective predictive model for the clinical evaluation of the stability of IAs. In total, 1,053 patients with 1,239 IAs were randomly divided the dataset into training (70%) and internal validation (30%) datasets. One hundred and ninety seven patients with 229 IAs from another hospital were evaluated as an external validation dataset. The prediction models were developed using machine learning based on clinical information, manual parameters, and radiomic features. In addition, a simple model for predicting the stability of IAs was developed, and a nomogram was drawn for clinical use. Fourteen machine learning models exhibited excellent classification performance. Logistic regression Model E (clinical information, manual parameters, and radiomic shape features) had the highest AUC of 0.963 (95% CI 0.943-0.980). Compared to manual parameters, radiomic features did not significantly improve the identification of unstable IAs. In the external validation dataset, the simplified model demonstrated excellent performance (AUC = 0.950) using only five manual parameters. Machine learning models have excellent potential in the classification of unstable IAs. The manual parameters from CTA images are sufficient for developing a simple and effective model for identifying unstable IAs.

Streamlining Acute Abdominal Aortic Dissection Management-An AI-based CT Imaging Workflow.

Life-threatening acute aortic dissection (AD) demands timely diagnosis for effective intervention. To streamline intrahospital workflows, automated detection of AD in abdominal computed tomography (CT) scans seems useful to assist humans. We aimed at creating a robust convolutional neural network (CNN)-based pipeline capable of real-time screening for signs of abdominal AD in CT. In this retrospective study, abdominal CT data from AD patients presenting with AD and from non-AD patients were collected (n 195, AD cases 94, mean age 65.9years, female ratio 35.8%). A CNN-based algorithm was developed with the goal of enabling a robust, automated, and highly sensitive detection of abdominal AD. Two sets from internal (n = 32, AD cases 16) and external sources (n = 1189, AD cases 100) were procured for validation. The abdominal region was extracted, followed by the automatic isolation of the aorta region of interest (ROI) and highlighting of the membrane via edge extraction, followed by classification of the aortic ROI as dissected/healthy. A fivefold cross-validation was employed on the internal set, and an ensemble of the 5 trained models was used to predict the internal and external validation set. Evaluation metrics included receiver operating characteristic curve (AUC) and balanced accuracy. The AUC, balanced accuracy, and sensitivity scores of the internal dataset were 0.932 (CI 0.891-0.963), 0.860, and 0.885, respectively. For the internal validation dataset, the AUC, balanced accuracy, and sensitivity scores were 0.887 (CI 0.732-0.988), 0.781, and 0.875, respectively. Furthermore, for the external validation dataset, AUC, balanced accuracy, and sensitivity scores were 0.993 (CI 0.918-0.994), 0.933, and 1.000, respectively. The proposed automated pipeline could assist humans in expediting acute aortic dissection management when integrated into clinical workflows.