Preoperative Prediction Research Articles

A Computer Modeling-Based Target Zone for Transposition Osteotomy of the Acetabulum in Patients with Hip Dysplasia.

This study aimed to determine the acetabular position to optimize hip biomechanics after transposition osteotomy of the acetabulum (TOA), a specific form of periacetabular osteotomy, in patients with hip dysplasia. We created patient-specific finite-element models of 46 patients with hip dysplasia to simulate 12 virtual TOA scenarios: lateral rotation to achieve a lateral center-edge angle (LCEA) of 30°, 35°, and 40° combined with anterior rotation of 0°, 5°, 10°, and 15°. Joint contact pressure (CP) on the acetabular cartilage during a single-leg stance and simulated hip range of motion without osseous impingement were calculated. The optimal acetabular position was defined as satisfying both normal joint CP and the required range of motion for activities of daily living. Multivariable logistic regression analysis was used to identify preoperative morphological predictors of osseous impingement after virtual TOA with adequate acetabular correction. The prevalence of hips in the optimal position was highest (65.2%) at an LCEA of 30°, regardless of the amount of anterior rotation. While the acetabular position minimizing peak CP varied among patients, approximately 80% exhibited normalized peak CP at an LCEA of 30° and 35° with 15° of anterior rotation, which were the 2 most favorable configurations among the 12 simulated scenarios. In this context, the preoperative head-neck offset ratio (HNOR) at the 1:30 clock position (p = 0.018) was an independent predictor of postoperative osseous impingement within the required range of motion. Specifically, an HNOR of <0.14 at the 1:30 clock position predicted limitation of required range of motion after virtual TOA (sensitivity, 57%; specificity, 81%; and area under the receiver operating characteristic curve, 0.70). Acetabular reorientation to an LCEA of between 30° and 35° with an additional 15° of anterior rotation may serve as a biomechanics-based target zone for surgeons performing TOA in most patients with hip dysplasia. However, patients with a reduced HNOR at the 1:30 clock position may experience limited range of motion in activities of daily living postoperatively. This study provides a biomechanics-based target for refining acetabular reorientation strategies during TOA while considering morphological factors that may limit the required range of motion.

Prediction of Pathologic Complete Response in Esophageal Squamous Cell Carcinoma Using Preoperative Serum Small Ribonucleic Acid Obtained After Neoadjuvant Chemoradiotherapy.

The authors hypothesized that small ribonucleic acid (sRNA) obtained from blood samples after neoadjuvant therapy from patients treated with neoadjuvant chemoradiation therapy (NACRT) could serve as a novel biomarker for predicting pathologic complete response (pCR). This study included 99 patients treated with esophagectomy after NACRT between March 2010 and October 2021 whose blood samples were collected between the end of NACRT and surgery. Next-generation sequencing (NGS) was used to analyze sRNAs from the blood samples. A predictive model for pCR comprising micro-RNA isoforms (isomiR), transfer RNA (tRNA)-derived sRNAs (tsRNAs), and clinical factors was constructed using cross-validation. Of the 99 patients, pCR was diagnosed for 30 and non-pCR for 69 of the patients. Among sRNAs, the isomiRs of let-7b and miR-93 and the tsRNA group derived from tRNA-Gly-CCC/GCC were identified as predictive factors. The clinical factors included a decrease in the maximum standardized uptake value (SUVmax) at the primary site, clinical complete response post-NACRT, preoperative biopsy, and post-NACRT carcinoembryonic antigen levels. The combined predictive model for pCR (C-PM) was established using the three sRNAs and four clinical factors. The area under the curve for the C-PM was 0.84, which was a significant factor in the multivariate analysis (odds ratio, 89.41; 95 % confidence interval 8.1-987.5; p < 0.001). Pathologic complete response after NACRT can be predicted by a predictive model constructed from preoperative clinical factors obtained via minimally invasive procedures and sRNA identified by NGS. Preoperative pCR prediction may influence treatment decision-making after NACRT.

Letter to “Preoperative Prediction of Microvascular Invasion by EOB-MRI Imaging for Surgical Decision”

Letter to “Preoperative Prediction of Microvascular Invasion by EOB-MRI Imaging for Surgical Decision”

Left bundle branch area pacing for atrioventricular block and mild to moderately reduced left ventricular systolic function.

The clinical efficacy of left bundle branch area pacing (LBBAP) has not been fully elucidated in patients with atrioventricular block and mild to moderately reduced left ventricular ejection fraction (LVEF). This study evaluated the impact of LBBAP on patients with an LVEF of ≤50% and dependent on ventricular pacing. Thirty-seven patients with atrioventricular block underwent successful LBBAP. All patients had a reduced LVEF of 36%-50% and underwent pacemaker implantation. Ventricular pacing was performed using the LBBAP alone throughout the follow-up period. Clinical outcomes, including death from any cause, fatal ventricular arrhythmias, hospitalization for heart failure, and echocardiographic improvements after 1 year, were assessed. Thirty-three (89%) patients were free from the composite endpoint during a median follow-up of 36 months, whereas four patients experienced noncardiovascular deaths or hospitalization for heart failure. No fatal ventricular arrhythmias occurred. LVEF was improved using LBBAP from 42.6 ± 4.7% to 52.1 ± 9.1% (p < .001). LVEF normalization (>50%) was achieved in 64.5% of patients, while in 11 patients LVEF remained stable demonstrating no deterioration (from 42.5 ± 4.7% to 42.4 ± 6.3%). Nonischemic cardiomyopathy (odds ratio, 21.52; 95% confidence interval, 1.96-236.45) and Pre-existing bundle branch block (odds ratio, 11.79; 95% confidence interval, 1.11-125.75) were independent preoperative predictors of LVEF normalization using LBBAP. LBBAP significantly improved cardiac systolic dysfunction without causing fatal ventricular arrhythmias. Moreover, LBBAP may provide a promising alternative to biventricular pacing in patients with atrioventricular block and a reduced LVEF of 36%-50%.

Preoperative collateralization depending on posterior components in the prediction of transient neurological events in moyamoya disease.

Changes in local cerebral blood flow (CBF) are a major cause of transient neurological events (TNEs) after revascularization for moyamoya disease (MMD); however, the influence of preoperative collateral pathway development on TNEs has not yet been investigated. This study included 28 hemispheres from 28 consecutive patients with MMD who underwent surgical revascularization, including a superficial temporal artery (STA) to middle cerebral artery (MCA) bypass, between January 2014 and March 2022. The collateralization pathways included the anterior communicating artery (AcomA) collaterals, posterior communicating artery (PcomA) collaterals, transdural collaterals, posterior pericallosal anastomosis, lenticulostriate anastomosis, thalamic anastomosis, and choroidal anastomosis. These collateral pathways were analyzed to identify predictive factors significantly associated with TNEs. TNEs were observed in 11 (39.3%) hemispheres. The development of posterior pericallosal anastomosis and choroidal anastomosis was a significant independent predictor of the occurrence of TNEs after bypass surgery for MMD (P = 0.01, OR 26.9, 95% CI 1.50-480.0; P = 0.002, OR 47.6, 95% CI 2.65-856.6). The development of choroidal and posterior pericallosal anastomosis could be reliable preoperative predictors of TNEs after bypass surgery for MMD. Our results provide useful information for future studies aimed at clarifying the mechanisms underlying TNEs.

Multimodal apparent diffusion MRI model in noninvasive evaluation of breast cancer and Ki-67 expression

BackgroundTo assess the capability of multimodal apparent diffusion (MAD) weighted magnetic resonance imaging (MRI) to distinguish between malignant and benign breast lesions, and to predict Ki-67 expression level in breast cancer.MethodsThis retrospective study was conducted with 93 patients who had postoperative pathology-confirmed breast cancer or benign breast lesions. MAD images were acquired using a 3.0 T MRI scanner with 16 b values. The MAD parameters, as flow (fF, DF), unimpeded (fluid) (fUI), hindered (fH, DH, and αH), and restricted (fR, DR), were calculated. The differences of the parameters were compared by Mann–Whitney U test between the benign/malignant lesions and high/low Ki-67 expression level. The diagnostic performance was assessed by the area under the receiver operating characteristic curve (AUC).ResultsThe fR in the malignant lesions was significantly higher than in the benign lesions (P = 0.001), whereas the fUI and DH were found to be significantly lower (P = 0.007 and P < 0.001, respectively). Compared with individual parameter in differentiating malignant from benign breast lesions, the combination parameters of MAD (fR, DH, and fUI) provided the highest AUC (0.851). Of the 73 malignant lesions, 42 (57.5%) were assessed as Ki-67 low expression and 31 (42.5%) were Ki-67 high expression. The Ki-67 high status showed lower DH, higher DF and higher αH (P < 0.05). The combination parameters of DH, DF, and αH provided the highest AUC (0.691) for evaluating Ki-67 expression level.ConclusionsMAD weighted MRI is a useful method for the breast lesions diagnostics and the preoperative prediction of Ki-67 expression level.

Habitat-based CT radiomics enhances the ability to predict spread through air spaces in stage T1 invasive lung adenocarcinoma.

Spread through air spaces (STAS) represents a novel invasive pattern in lung adenocarcinoma (LUAD) and is a risk factor for poor prognosis in stage T1 LUAD. This study aims to develop and validate a CT habitat imaging analysis model for predicting STAS in stage T1 invasive LUAD. We retrospectively analyzed 217 patients with preoperative stage T1 invasive LUAD (115 STAS-positive and 102 STAS-negative cases, including 151 in the train set and 66 in the test set). Semi-automatic segmentation was performed on the regions of interest (ROIs) in all CT images, with an automatic 3mm expansion around the tumor, considering the intratumoral and peritumoral 3mm area. This area was divided into three sub-regions via K-means clustering, and 1197 radiomic features were extracted from each sub-region and the overall combined region. After dimension reduction through the Mann-Whitney U test, Pearson correlation analysis, and least absolute shrinkage and selection operator(LASSO), the best features for each sub-region and overall were selected. Models were then built using the selected radiomic features through the Adaptive Boosting (AdaBoost) and Multilayer Perceptron (MLP) classifiers. Four different models were established based on different sub-regions and the overall features. The performance of these models was evaluated through receiver operating characteristic curves (AUC) under the DeLong test, calibration curves via the Hosmer-Lemeshow test, and decision curve analysis to assess the performance of these features. In this study, we evaluated the predictive performance of AdaBoost and MLP classifiers on rad feature models across various subregions and the overall dataset. In the test set, the AdaBoost classifier achieved a maximum AUC of 0.871 in Habitat 3, whereas the MLP classifier demonstrated slightly superior performance with an AUC of 0.879. Both classifiers exhibited high efficiency in habitat 3, with the MLP algorithm showing enhanced model performance. CT habitat imaging analysis for the preoperative prediction of STAS in stage T1 invasive LUAD shows satisfactory diagnostic performance, with the habitat3 model exhibiting the highest efficacy, reflecting tumor heterogeneity.

Prevalence and clinical burden of venous thromboembolic events (VTEs) in contemporary total knee arthroplasties (TKAs) in US hospitals

IntroductionTotal knee arthroplasty (TKA) is a highly demanded procedure in orthopedic surgery, with over 1.3 million joint arthroplasties performed annually in the U.S. The increasing need for TKAs is driven by an aging population, rising obesity rates, and advances in surgical techniques. Venous thromboembolism (VTE), including pulmonary embolism (PE) and deep vein thrombosis (DVT), significantly impacts TKA patients' mortality and morbidity. Despite advances in prophylaxis and Enhanced Recovery After Surgery (ERAS) protocols reducing VTE incidence, survival rates have not markedly improved. This study aims to identify preoperative predictors of PE and DVT in TKA patients and examine their impact on hospital stays and mortality. MethodsA retrospective observational study was conducted using data from the American College of Surgeons National Surgical Quality Improvement Program (ACS NSQIP) database, focusing on 367,365 TKA patients from 2016 to 2021. Preoperative variables, including demographic factors, comorbidities, and functional status, were analyzed. Primary endpoints were PE and DVT predictors; secondary endpoints included 30-day mortality and prolonged hospital stay. Univariate and logistic regression analyses were performed using SPSS version 26. ResultsUnivariate analysis revealed significant associations of male gender, older age, Hispanic ethnicity, smoking, dyspnea, CHF, and COPD with DVT and PE. Multivariate analysis confirmed female sex, younger age, Hispanic ethnicity, and COPD as independent DVT predictors, and independent functional status, smoking, COPD, CHF, and metastatic malignancy as PE predictors. VTE prevalence was 1.09 % (0.67 % DVT, 0.42 % PE), with PE associated with higher mortality (0.78 %) and prolonged hospital stays. ConclusionDemographic and clinical variables significantly influence VTE risk post-TKA. Tailored interventions and comprehensive preoperative assessments are crucial for optimizing patient outcomes and reducing thrombotic risks.

THE ROLE OF CA 19.9 IN PREDICTING THE OPERABILITY OF CARCINOMA PANCREAS

Objectives: Adenocarcinoma of the pancreas remains a relatively incurable disease despite advances in surgical care. Approximately 25% of patients will be found to have unresectable tumors during surgery even though computed tomography (CT) has demonstrated that they are resectable. There is a controversy regarding the use of cancer antigen 19-9 (CA 19-9) to decide the resectability of pancreatic adenocarcinoma [1]. Our aim is to study the use of CA 19-9 in determining the operability of carcinoma pancreas [2]. Methods: This was a prospective study which included 69 patients and the study period was from December 2021 to December 2022. Data were collected from all patients with carcinoma of the pancreas who underwent surgical management. CA 19-9 levels were measured and recorded [3]. During surgery, the operative findings on resectability were documented and tabulated against corresponding CA 19-9 levels and contrast-enhanced CT (CECT) findings. Results: Of the 69 patients who were operated on, 38 patients had resectable tumors and underwent the Whipples procedure and 31 of them had non-resectable tumors and had to undergo palliative bypass procedures. Among the 31 patients whose tumors were non-resectable, only four were diagnosed non-resectable preoperatively with CECT, and the other 27 were found to be non-resectable only during surgery. That shows the relevance of this study. Of the 31 non-resectable cases, 14 (45.2%) patients had elevated CA 19-9 values of more than 501, and the rest 17 (54.8%) patients had low CA 19-9 values. Among the 38 resectable cases, 12 patients (31.6%) had elevated CA 19-9 more than 501, and 26 patients (68.4%) had low values. In conclusion, among non-resectable cases, 45.2% had raised CA 19-9, and among operable cases, 31.6% showed raised CA 19-9. Hence, CA 19-9 seems to be an insignificant predictor of tumor resectability [4]. Conclusion: It was found that the need for a pre-operative predictor for resectability of carcinoma pancreas is relevant while considering mortality and morbidity in operating carcinoma pancreas cases. On evaluating CA 19-9 as a pre-operative predictor, we found that CA 19-9 has no significant role as an indicator of local advancement or metastasis. Hence, we cannot consider CA 19-9 as a predictor of resectability of carcinoma pancreas preoperatively [5].

Assessing anatomical variations of the superior mesenteric artery via three-dimensional CT angiography and laparoscopic right hemicolectomy: a retrospective observational study.

This study aimed to analyse the anatomical relationships and differences between the superior mesenteric vessels and their branches by reviewing a laparoscopic right hemicolectomy surgery video and comparing it with preoperative three-dimensional computed tomography (3D-CT) angiography and to verify the accuracy of 3D-CT vascular reconstruction techniques. Surgical videos and preoperative imaging data of 52 patients undergoing laparoscopic right hemicolectomy were analysed to observe and summarize the probability of occurrence and adjacency of superior mesenteric vascular branches, and the lengths of specific sites of their branches were measured using the above two methods. Preoperative CT images and surgical video showed that the ileocolic artery (ICA) was present in 98.1% (51/52) and the ileocolic vein (ICV) was present in 100% (52/52), and ICA was present in 13.7% (7/51) of the ICV directly anteriorly, 13.7% (7/51) anteriorly superiorly, 3.9% (2/51) anteriorly inferiorly, 11.8% (6/51) directly posteriorly, 37.2% (19/51) post superiorly, and 19.7% (10/51) posteriorly inferiorly. In the surgical video, the probability of presence of the right colic artery (RCA) was 21.2% (11/52). On CT images, the RCA was present in 10 patients. The length of the origin of the middle colic artery (MCA) from its bifurcations was 2.33 ± 0.87 cm measured intraoperatively using a sterile isometric filament, and the length measured using 3D-CT vascular reconstruction was 2.36 ± 0.91 cm; the difference was not statistically significant (P = 0.348). The length of the MCA and ICA initiation points was 3.22 ± 0.75 cm measured intraoperatively using sterile isometric filaments and 3.36 ± 0.72 cm measured using 3D-CT vascular reconstruction, which was a statistically significant difference (P < 0.001). 3D-CT vascular reconstruction can accurately predict the vessels related to right hemicolectomy in most cases. It is an important method for preoperative prediction of superior mesenteric vessels, which can guide surgeons in the intraoperative vessel identification.

Ranking attention multiple instance learning for lymph node metastasis prediction on multicenter cervical cancer MRI.

In the current clinical diagnostic process, the gold standard for lymph node metastasis (LNM) diagnosis is histopathological examination following surgical lymphadenectomy. Developing a non-invasive and preoperative method for predicting LNM is necessary and holds significant clinical importance. We develop a ranking attention multiple instance learning (RA-MIL) model that integrates convolutional neural networks (CNNs) and ranking attention pooling to diagnose LNM from T2 MRI. Our RA-MIL model applies the CNNs to derive imaging features from 2D MRI slices and employs ranking attention pooling to create patient-level feature representation for diagnostic classification. Based on the MIL and attention theory, informative regions of top-ranking MRI slices from LNM-positive patients are visualized to enhance the interpretability of automatic LNM prediction. This retrospective study collected 300 female patients with cervical cancer who underwent T2-weighted magnetic resonance imaging (MRI) scanning and histopathological diagnosis from one hospital (289 patients) and one open-source dataset (11 patients). Our RA-MIL model delivers promising LNM prediction performance, achieving the area under the receiver operating characteristic curve (AUC) of 0.809 on the internal test set and 0.833 on the public dataset. Experiments show significant improvements in LNM status prediction using the proposed RA-MIL model compared with other state-of-the-art (SOTA) comparative deep learning models. The developed RA-MIL model has the potential to serve as a non-invasive auxiliary tool for preoperative LNM prediction, offering visual interpretability regarding informative MRI slices and regions in LNM-positive patients.

6871 Hungry Bone Syndrome After Parathyroidectomy in End-Stage Kidney Disease: A Case Report Analysis

Abstract Disclosure: R. Rani: None. C. Mullarkey-desapio: None. Introduction: Hungry Bone Syndrome (HBS) is a rare yet severe complication following parathyroidectomy, characterized by pronounced hypocalcemia subsequent to a rapid decline in parathyroid hormone (PTH) levels. Renal hyperparathyroidism (RHPT) carries a heightened risk of HBS compared to primary hyperparathyroidism (PHPT), with prevalence varying from 15% to 25% in PHPT to as high as 75-92% in RHPT. This elevated risk in RHPT is attributed to chronically elevated PTH levels, both in terms of duration and intensity as compared to PHPT. Preoperative predictors for HBS occurrence and severity include younger age, larger gland size, lower preoperative calcium levels, elevated bone turnover markers, and the magnitude of PTH elevation. Case Report: We present a case of a 36-year-old female with End-Stage Renal Disease (ESRD) requiring dialysis, complicated by renal osteodystrophy and a radial fracture, unresponsive to medical therapy, who was admitted for parathyroidectomy. Preoperative labs revealed calcium at 8.3 mg/dL, phosphate at 4.1 mg/dL, alkaline phosphatase (ALP) at 797 IU/L, and an extremely elevated parathyroid hormone (PTH) level at 4139 pg/ml. Within 24 hours of parathyroidectomy (three and a half glands were removed, the largest weighing 0.7gm), her PTH levels declined to the 130s, accompanied by symptomatic hypocalcemia (calcium 6.5mg/dL). Initial management involved intravenous calcium gluconate and subsequent high-dose oral calcium (up to 10-16gm daily) with Calcitriol 1 mcg twice daily. Despite repletion, her calcium levels remained low on postoperative day 4 (calcium 6.8mg/dL, phosphate 1.9 mg/dL, magnesium 1.7mg/dL) with PTH at 131 pg/ml, confirming Hungry Bone Syndrome. After seven days of aggressive intravenous and oral calcium supplementation with high-dose Calcitriol, she was discharged with a calcium level of 8.9mg/dL. Discussion: Management of HBS following renal hyperparathyroidism surgery presents significant challenges due to associated comorbidities and other electrolyte abnormalities, with limited literature providing guidance on prevention and management. Our case demonstrated that early suspicion and aggressive management improved patient outcomes. Suspecting HBS in high-risk individuals and initiating interventions pre and post-surgery, including pre-treatment with calcitriol, bisphosphonates, and early aggressive intravenous calcium supplementation post-surgery, could potentially reduce morbidity and length of hospital stay. Presentation: 6/1/2024

Intratumoral and peritumoral radiomics model for the preoperative prediction of cribriform component in invasive lung adenocarcinoma: a multicenter study.

This study aimed to investigate the predictive value of intratumoral and peritumoral radiomics model for the cribriform component (CC) of invasive lung adenocarcinoma (LUAD). The 144 patients with invasive LUAD from our center were randomly divided into training set (n = 100) and internal validation set (n = 44) in a ratio of 7:3, and 75 patients from center 2 were regarded as the external validation set. Clinical risk factors were examined using univariate and multivariate logistic regression to construct the clinical model. We extracted radiomics features from gross tumor volume (GTV), gross and peritumoral volume (GPTV), and peritumoral volume (PTV), respectively. Radiomics models were constructed with selected features. A combined model based on the optimal Radscore and clinically independent predictors was constructed, and its predictive performance was assessed by receiver operating characteristic curve (ROC), calibration curve, and decision curve analysis (DCA). The area under curves (AUCs) of the GTV model were 0.882 (95% CI 0.817-0.948), 0.794 (95% CI 0.656-0.932), and 0.766 (95% CI 0.657-0.875) in the training, internal validation, and external validation sets, and the PTV model had AUCs of 0.812 (95% CI 0.725-0.899), 0.749 (95% CI 0.597-0.902), and 0.670 (95% CI 0.543-0.798) in the training, internal validation, and external validation sets, respectively. However, the GPTV radiomics model showed better predictive performance compared with the GTV and PTV radiomics models, with the AUCs of 0.950 (95% CI 0.911-0.989), 0.844 (95% CI 0.728-0.959), and 0.815 (95% CI 0.713-0.917) in the training, internal validation and external validation sets, respectively. In the clinical model, tumor shape, lobulation sign and maximal diameter were the independent predictors of CC in invasive LUAD. The combined model including independent clinical predictors and GPTV-Radscore show the considerable instructive to clinical practice, with the AUCs of 0.954(95% CI 0.918-0.990), 0.861(95% CI 0.752-0.970), and 0.794(95% CI 0.690-0.898) in training, internal validation, and external validation sets, respectively. DCA showed that the combined model had good clinical value and correction effect. Radiomics model is a very powerful tool for predicting CC growth pattern in invasive LUAD and can help clinicians make the strategies of treatment and surveillance in patients with invasive LUAD.

Computed tomography-based radiomics nomogram for prediction of lympho-vascular and perineural invasion in esophageal squamous cell cancer patients: a retrospective cohort study

PurposeLympho-vascular invasion (LVI) and perineural invasion (PNI) have been established as prognostic factors in various types of cancers. The preoperative prediction of LVI and PNI has the potential to guide personalized medicine strategies for patients with esophageal squamous cell cancer (ESCC). This study investigates whether radiomics features derived from preoperative contrast-enhanced CT could predict LVI and PNI in ESCC patients.Methods and materialsA retrospective cohort of 544 ESCC patients who underwent esophagectomy were included in this study. Preoperative contrast-enhanced CT images, pathological results of PNI and LVI, and clinical characteristics were collected. For each patient, the gross tumor volume (GTV-T) and lymph nodes volume (GTV-N) were delineated and four categories of radiomics features (first-order, shape, textural and wavelet) were extracted from GTV-T and GTV-N. The Mann–Whitney U test was used to select significant features associated with LVI and PNI in turn. Subsequently, radiomics signatures for LVI and PNI were constructed using LASSO regression with ten-fold cross-validation. Significant clinical characteristics were combined with radiomics signature to develop two nomogram models for predicting LVI and PNI, respectively. The area under the curve (AUC) and calibration curve were used to evaluate the predictive performance of the models.ResultsThe radiomics signature for LVI prediction consisted of 28 features, while the PNI radiomics signature comprised 14 features. The AUCs of the LVI radiomics signature were 0.77 and 0.74 in the training and validation groups, respectively, while the AUCs of the PNI radiomics signature were 0.69 and 0.68 in the training and validation groups. The nomograms incorporating radiomics signatures and significant clinical characteristics such as age, gender, thrombin time and D-Dimer showed improved predictive performance for both LVI (AUC: 0.82 and 0.80 in the training and validation group) and PNI (AUC: 0.75 and 0.72 in the training and validation groups) compared to the radiomics signature alone.ConclusionThe radiomics features extracted from preoperative contrast-enhanced CT of gross tumor and lymph nodes have demonstrated their potential in predicting LVI and PNI in ESCC patients. Furthermore, the incorporation of clinical characteristics has shown additional value, resulting in improved predictive performance.

Prediction of preoperative lymph-vascular space invasion and survival outcomes of cervical squamous cell carcinoma by utilizing 18 F-FDG PET/CT imaging at early stage.

To establish nomograms for predicting preoperative lymph-vascular space invasion (LVSI) and survival outcomes of cervical squamous cell carcinoma (CSCC) based on PET/CT radiomics. One hundred and twenty-three patients with CSCC and LVSI status were enrolled retrospectively. Independent predictors of LVSI were identified through clinicopathological factors and PET/CT metabolic parameters. We extracted 1316 features from PET and CT volume of interest, respectively. Additionally, four models (PET-RS: radiomic signature of PET only; CT-RS: radiomic signature of CT only; PET/CT-RS + clinical data; PET/CT-RS: radiomic signature of PET and CT) were established to predict LVSI status. Calculation of radiomics scores of PET/CT was executed for assessment of the survival outcomes, followed by development of nomograms with radiomics (NR) or without radiomics (NWR). One hundred and twenty-three patients with pathologically confirmed CSCC had been categorized into two sets (training and testing sets). It was found that only maximum standardized uptake value (SUV max ) and squamous cell carcinoma antigen were independent predictors of LVSI. Meanwhile, the PET/CT-RS + clinical data outperformed the other three models in the training set [area under the curve (AUC): 0.91 vs. 0.861 vs. 0.81 vs. 0.814] and the testing set (AUC: 0.885 vs. 0.857 vs. 0.783 vs. 0.798). Additionally, SUV max and LVSI had been demonstrated to be independent prognostic indicators for progression-free survival and overall survival. Decision curve analysis and calibration curve indicated that NRs were superior to NWRs. The survival outcomes were assessed. PET/CT-based radiomic signature nomogram enables a new method for preoperative prediction of LVSI and survival prognosis for patients with CSCC.

Pre-operative prediction of BCR-free survival with mRNA variables in prostate cancer.

Technological innovation yielded opportunities to obtain mRNA expression data for prostate cancer (PCa) patients even prior to biopsy, which can be used in a precision medicine approach to treatment decision-making. This can apply in particular to predict the risk of, and time to biochemical recurrence (BCR). Most mRNA-based models currently proposed to this end are designed for risk classification and post-operative prediction. Effective pre-operative prediction would facilitate early treatment decision-making, in particular by indicating more appropriate therapeutic pathways for patient profiles who would likely not benefit from a systematic prostatectomy regime. The aim of this study is to investigate the possibility to leverage mRNA information pre-operatively for BCR-free survival prediction. To do this, we considered time-to-event machine learning (ML) methodologies, rather than classification models at a specific survival horizon. We retrospectively analysed a cohort of 135 patients with clinical follow-up data and mRNA information comprising over 26,000 features (data accessible at NCBI GEO database, accession GSE21032). The performance of ML models including random survival forest, boosted and regularised Cox models were assessed, in terms of model discrimination, calibration, and predictive accuracy for overall, 3-year and 5-year survival, aligning with common clinical endpoints. Results showed that the inclusion of mRNA information could yield a gain in performance for pre-operative BCR prediction. ML-based time-to-event models significantly outperformed reference nomograms that used only routine clinical information with respect to all metrics considered. We believe this is the first study proposing pre-operative transcriptomics models for BCR prediction in PCa. External validation of these findings, including confirmation of the mRNA variables identified as potential key predictors in this study, could pave the way for pre-operative precision nomograms to facilitate timely personalised clinical decision-making.

Mid-level data fusion strategy based on urinary nucleosides SERS spectra and blood CEA levels for enhanced preoperative detection of lymph node metastasis in colorectal cancer

BackgroundPreoperative prediction of lymph node metastasis (LNM) plays a crucial role in the treatment and prognosis of colorectal cancer (CRC). The traditional histopathological examination is invasive and time-consuming, providing pathological features only postoperatively. Preoperative serum carcinoembryonic antigen (CEA) is strongly correlated with postoperative LN status. However, the detection accuracy of LNM based on a single preoperative CEA level is low. Therefore, developing a more powerful and sensitive diagnostic tool would be of great clinical value for improving the accurate preoperative prediction of LNM in CRC patients. ResultsThis study aimed to develop a mid-level fusion approach using urinary nucleosides Raman spectra and blood CEA data to enhance the preoperative discrimination of CRC patients with and without LNM. Surface-enhanced Raman scattering (SERS) spectra of urinary modified nucleosides, isolated by affinity chromatography, were first acquired from 48 patients with LNM and 49 patients without LNM. The principal component analysis (PCA) scores obtained from the SERS spectra were then combined with preoperative blood CEA values to create a fused data array. The discriminant accuracy based on either dataset alone or the fused data was evaluated using three machine learning algorithms: linear discriminant analysis, k-nearest neighbors, and support vector machine. Results showed that the fused data could discriminate between the two groups with an accuracy of up to 91 %, outperforming SERS alone (86 %) and CEA alone (69 %). SignificanceTo our knowledge, this is the first report of mid-level data fusion of urinary nucleosides SERS spectra with blood CEA levels for the preoperative prediction of LNM in CRC. This work demonstrates that the mid-level data fusion strategy aided by SVM algorithm can greatly improve the preoperative prediction accuracy of LNM. This is crucial for therapeutic decision-making and prognostic assessment in CRC.

Machine learning−derived multivariable predictors of postcardiotomy cardiogenic shock in high-risk cardiac surgery patients

ObjectiveTo develop a model for preoperatively predicting postcardiotomy cardiogenic shock (PCCS) in patients with poor left ventricular (LV) function undergoing cardiac surgery. MethodsFrom the Society of Thoracic Surgeons Adult Cardiac Database, 11,493 patients with LV ejection fraction ≤35% underwent isolated on-pump surgery from 2018 through 2019, of whom 3428 experienced PCCS. In total, 68 preoperative clinical variables were considered in machine-learning algorithms trained and optimized using scikit-learn software. ResultsCompared with patients with ideal recovery, those that did were younger (65 vs 67 years), more likely female, Black, with low LV ejection fraction (26.5 vs 28.9%), previous myocardial infarction, chronic lung disease, diabetes, reoperation, or advanced heart failure. Among those with PCCS versus ideal recovery, operative mortality was 27% (925/3428) versus 0.1% (5/8065). PCCS occurred more often after coronary artery bypass grafting with concomitant mitral valve repair or after longer perfusion and clamp times. Reliable preoperative PCCS predictors were more advanced cardiac, liver, and renal failure; frailty; and greater white cell count. Out of sample test set receiver operating curve achieved an area under the curve of 0.74 with acceptable calibration Hosmer-Lemeshow statistic χ2 = 1.33, P = .25. ConclusionsIn patients with severe LV dysfunction undergoing cardiac surgery, risk of PCCS is elevated by preoperative failure of other organ systems and complexity of the planned operation that prolongs myocardial ischemia and cardiopulmonary bypass. This risk calculator could serve as an important tool to preoperatively identify patients in need of advanced levels of support.

Visualization analysis of research hotspots and trends in MRI-based artificial intelligence in rectal cancer

BackgroundRectal cancer (RC) is one of the most common types of cancer worldwide. With the development of artificial intelligence (AI), the application of AI in preoperative evaluation and follow-up treatment of RC based on magnetic resonance imaging (MRI) has been the focus of research in this field. This review was conducted to develop comprehensive insight into the current research progress, hotspots, and future trends in AI based on MRI in RC, which remains to be studied. MethodsLiterature related to AI based on MRI and RC, as of November 2023, was obtained from the Web of Science Core Collection database. Visualization and bibliometric analyses of publication quantity and content were conducted to explore temporal trends, spatial distribution, collaborative networks, influential articles, keyword co-occurrence, and research directions. ResultsA total of 177 papers (152 original articles and 25 reviews) were identified from 24 countries/regions, 351 institutions, and 81 journals. Since 2019, the number of studies on this topic has rapidly increased. China and the United States have contributed the highest number of publications and institutions, cultivating the most intimate collaborative relationship. The highest number of articles derive from Sun Yat-sen University, while Frontiers in Oncology has published the highest number of relevant articles. Research on MRI-based AI in this field has mainly focused on preoperative diagnosis and prediction of treatment efficacy and prognosis. ConclusionsThis study provides an objective and comprehensive overview of the publications on MRI-based AI in RC and identifies the present research landscape, hotspots, and prospective trends in this field, which can provide valuable guidance for scholars worldwide.

Pre-operative evaluation of spontaneous portosystemic shunts as a predictor of post-hepatectomy liver failure in patients undergoing liver resection for hepatocellular carcinoma

BackgroundPost-hepatectomy liver failure (PHLF) can significantly compromise outcomes, especially in cirrhotic patients. The identification of accurate and non-invasive pre-operative predictors is of paramount importance to appropriately stratify patients according to their estimated risk and select the best treatment strategy. Materials and methodsConsecutive patients undergoing liver resection for HCC on cirrhosis between 1-2015 and 12–2020 at 10 international Institutions were enrolled and their pre-operative CT scans were evaluated for the presence of spontaneous portosystemic shunts (SPSS) to identify predictors of PHLF and develop a nomogram. ResultsThe analysis of the CT scans identified SPSS in 74 patients (17.4 %). PHLF was developed in 27 out of 425 cases (6.4 %), with grades B/C observed in 17 patients (4 %). At the multivariable analysis, the presence of SPSS resulted an independent risk factor for all-grades PHLF (OR 6.83, 95%CI 2.39–19.51, p < 0.001) and clinically significant PHLF development (OR 7.92, 95%CI 2.03–30.85, p = 0.003) alongside a patient's age ≥74 years, a pre-operative platelets count <106x103/μL, a multiple-segments liver resection, and an intraoperative blood loss ≥1200 mL. The 30- and 90-days mortality in patients with and without SPSS resulted 2.7 % vs 0.3 % (p = 0.024) and 5.4 % vs 1.1 % (p = 0.014). The accuracy of SPSS in predicting PHLF development was 0.847 (95%n CI 0.809–0.880). The internally validated nomogram showed excellent performance in predicting grades B/C PHLF (c-statistic = 0.933 (95%CI 0.888–0.979)). ConclusionThe pre-operative presence of SPSS assessed on the pre-operative imaging proved to be a valuable radiological biomarker able to predict PHLF development in patients undergoing liver resection for HCC.