Pediatric Hodgkin and non-Hodgkin lymphomas differ from adult cases in biology and management, yet there is a lack of survival analysis tailored to pediatric lymphoma. We analyzed lymphoma data from 1975 to 2018, comparing survival trends between 7,871 pediatric and 226,211 adult patients, identified key risk factors for pediatric lymphoma survival, developed a predictive nomogram, and utilized machine learning to predict long-term lymphoma-specific mortality risk. Between 1975 and 2018, we observed substantial increases in 1-year (19.3%), 5-year (41.9%), and 10-year (48.8%) overall survival rates in pediatric patients with lymphoma. Prognostic factors such as age, sex, race, Ann Arbor stage, lymphoma subtypes, and radiotherapy were incorporated into the nomogram. The nomogram exhibited excellent predictive performance with area under the curve (AUC) values of 0.766, 0.724, and 0.703 for one-year, five-year, and ten-year survival, respectively, in the training cohort, and AUC values of 0.776, 0.712, and 0.696 in the validation cohort. Importantly, the nomogram outperformed the Ann Arbor staging system in survival prediction. Machine learning models achieved AUC values of approximately 0.75, surpassing the conventional method (AUC =  ~ 0.70) in predicting the risk of lymphoma-specific death. We also observed that pediatric lymphoma survivors had a substantially reduced risk of lymphoma after ten years b,ut faced an increasing risk of non-lymphoma diseases. The study highlights substantial improvements in pediatric lymphoma survival, offers reliable predictive tools, and underscores the importance of long-term monitoring for non-lymphoma health issues in pediatric patients.

UNASSIGNED: This study proposed an outcome prediction method to improve the accuracy and efficacy of ischemic stroke outcome prediction based on the diversity of whole brain features, without using basic information about patients and image features in lesions.
UNASSIGNED: In this study, we directly extracted dynamic radiomics features (DRFs) from dynamic susceptibility contrast perfusion-weighted imaging (DSC-PWI) and further extracted static radiomics features (SRFs) and static encoding features (SEFs) from the minimum intensity projection (MinIP) map, which was generated from the time dimension of DSC-PWI images. After selecting whole brain features Ffuse from the combinations of DRFs, SRFs, and SEFs by the Lasso algorithm, various machine and deep learning models were used to evaluate the role of Ffuse in predicting stroke outcomes.
UNASSIGNED: The experimental results show that the feature Ffuse generated from DRFs, SRFs, and SEFs (Resnet 18) outperformed other single and combination features and achieved the best mean score of 0.971 both on machine learning models and deep learning models and the 95% CI were (0.703, 0.877) and (0.92, 0.983), respectively. Besides, the deep learning models generally performed better than the machine learning models.
UNASSIGNED: The method used in our study can achieve an accurate assessment of stroke outcomes without segmentation of ischemic lesions, which is of great significance for rapid, efficient, and accurate clinical stroke treatment.

The (re)hemorrhage in patients with sporadic cerebral cavernous malformations (CCM) was the primary aim for CCM management. However, accurately identifying the potential (re)hemorrhage among sporadic CCM patients in advance remains a challenge. This study aims to develop machine learning models to detect potential (re)hemorrhage in sporadic CCM patients. This study was based on a dataset of 731 sporadic CCM patients in open data platform Dryad. Sporadic CCM patients were followed up 5 years from January 2003 to December 2018. Support vector machine (SVM), stacked generalization, and extreme gradient boosting (XGBoost) were used to construct models. The performance of models was evaluated by area under receiver operating characteristic curves (AUROC), area under the precision-recall curve (PR-AUC) and other metrics. A total of 517 patients with sporadic CCM were included (330 female [63.8%], mean [SD] age at diagnosis, 42.1 [15.5] years). 76 (re)hemorrhage (14.7%) occurred during follow-up. Among 3 machine learning models, XGBoost model yielded the highest mean (SD) AUROC (0.87 [0.06]) in cross-validation. The top 4 features of XGBoost model were ranked with SHAP (SHapley Additive exPlanations). All-Elements XGBoost model achieved an AUROCs of 0.84 and PR-AUC of 0.49 in testing set, with a sensitivity of 0.86 and a specificity of 0.76. Importantly, 4-Elements XGBoost model developed using top 4 features got a AUROCs of 0.83 and PR-AUC of 0.40, a sensitivity of 0.79, and a specificity of 0.72 in testing set. Two machine learning-based models achieved accurate performance in identifying potential (re)hemorrhages within 5 years in sporadic CCM patients. These models may provide insights for clinical decision-making.

Chimeric antigen receptor (CAR) T cell therapy has made great progress in treating lymphoma, yet patient outcomes still vary greatly. The lymphoma microenvironment may be an important factor in the efficacy of CAR T therapy. In this study, we designed a highly multiplexed imaging mass cytometry (IMC) panel to simultaneously quantify 31 biomarkers from 13 patients with relapsed/refractory diffuse large B cell lymphoma (DLBCL) who received CAR19/22 T cell therapy. A total of 20 sections were sampled before CAR T cell infusion or after infusion when relapse occurred. A total of 35 cell clusters were identified, annotated, and subsequently redefined into 10 metaclusters. The CD4+ T cell fraction was positively associated with remission duration. Significantly higher Ki67, CD57, and TIM3 levels and lower CD69 levels in T cells, especially the CD8+/CD4+ Tem and Te cell subsets, were seen in patients with poor outcomes. Cellular neighborhood containing more immune cells was associated with longer remission. Fibroblasts and vascular endothelial cells resided much closer to tumor cells in patients with poor response and short remission after CAR T therapy. Our work comprehensively and systematically dissects the relationship between cell composition, state, and spatial arrangement in the DLBCL microenvironment and the outcomes of CAR T cell therapy, which is beneficial to predict CAR T therapy efficacy.

BACKGROUND: Forkhead-box protein P1 (FOXP1) has been proposed to have both oncogenic and tumor-suppressive properties, depending on tumor heterogeneity. However, the role of FOXP1 in intrahepatic cholangiocarcinoma (ICC) has not been previously reported.
METHODS: Immunohistochemistry was performed to detect FOXP1 expression in ICC and normal liver tissues. The relationship between FOXP1 levels and the clinicopathological characteristics of patients with ICC was evaluated. Finally, in vitro and in vivo experiments were conducted to examine the regulatory role of FOXP1 in ICC cells.
RESULTS: FOXP1 was significantly downregulated in the ICC compared to their peritumoral tissues (p < 0.01). The positive rates of FOXP1 were significantly lower in patients with poor differentiation, lymph node metastasis, invasion into surrounding organs, and advanced stages (p < 0.05). Notably, patients with FOXP1 positivity had better outcomes (overall survival) than those with FOXP1 negativity (p < 0.05), as revealed by Kaplan-Meier survival analysis. Moreover, Cox multivariate analysis showed that negative FOXP1 expression, advanced TNM stages, invasion, and lymph node metastasis were independent prognostic risk factors in patients with ICC. Lastly, overexpression of FOXP1 inhibited the proliferation, migration, and invasion of ICC cells and promoted apoptosis, whereas knockdown of FOXP1 had the opposite role.
CONCLUSIONS: Our findings suggest that FOXP1 may serve as a novel outcome predictor for ICC as well as a tumor suppressor that may contribute to cancer treatment.

Outcome prediction is essential for the administration and treatment of critically ill patients. For those patients, clinical measurements are continuously monitored and the time-varying data contains rich information for assessing the patients\' status. However, it is unclear how to capture the dynamic information effectively. In this work, multiple feature extraction methods, i.e. statistical feature classification methods and temporal modeling methods, such as recurrent neural network (RNN), were analyzed on a critical illness dataset with 18415 cases. The experimental results show when the dimension increases from 10 to 50, the RNN algorithm is gradually superior to the statistical feature classification methods with simple logic. The RNN model achieves the largest AUC value of 0.8463. Therefore, the temporal modeling methods are promising to capture temporal features which are predictive of the patients\' outcome and can be extended in more clinical applications.

Controversy exists regarding the superiority of the performance of prognostic tools based on advanced machine learning (ML) algorithms for patients with aneurysmal subarachnoid hemorrhage (aSAH). However, it is unclear whether ML prognostic models will benefit patients due to the lack of a comprehensive assessment. We aimed to develop and evaluate ML models for predicting unfavorable functional outcomes for aSAH patients and identify the model with the greatest performance.
In this retrospective study, a dataset of 955 patients with aSAH was used to construct and validate prognostic models for functional outcomes assessed using the modified Rankin scale during a follow-up period of 3-6 months. Clinical scores and clinical and radiological features on admission and secondary complications were used to construct models based on 5 ML algorithms (i.e., logistic regression [LR], k-nearest neighbor, extreme gradient boosting, random forest, and artificial neural network). For evaluation among the models, the area under the receiver operating characteristic curve, area under the precision-recall curve, calibration curve, and decision curve analysis were used.
Composite models had significantly higher area under the receiver operating characteristic curves than did simple models in predicting unfavorable functional outcomes. Compared with other composite models (random forest and extreme gradient boosting) with good calibration, LR had the highest area under the precision-recall score and showed the greatest benefit in decision curve analysis.
Of the 5 studied ML models, the conventional LR model outperformed the advanced algorithms in predicting the prognosis and could be a useful tool for health care professionals.

BACKGROUND: Aneurysmal subarachnoid hemorrhage (aSAH) causes long-term functional dependence and death. Early prediction of functional outcomes in aSAH patients with appropriate intervention strategies could lower the risk of poor prognosis. Therefore, we aimed to develop pre- and post-operative dynamic visualization nomograms to predict the 1-year functional outcomes of aSAH patients undergoing coil embolization.
METHODS: Data were obtained from 400 aSAH patients undergoing endovascular coiling admitted to the People\'s Hospital of Hunan Province in China (2015-2019). The key indicator was the modified Rankin Score (mRS), with 3-6 representing poor functional outcomes. Multivariate logistic regression (MLR)-based visual nomograms were developed to analyze baseline characteristics and post-operative complications. The evaluation of nomogram performance included discrimination (measured by C statistic), calibration (measured by the Hosmer-Lemeshow test and calibration curves), and clinical usefulness (measured by decision curve analysis).
RESULTS: Fifty-nine aSAH patients (14.8%) had poor outcomes. Both nomograms showed good discrimination, and the post-operative nomogram demonstrated superior discrimination to the pre-operative nomogram with a C statistic of 0.895 (95% CI: 0.844-0.945) vs. 0.801 (95% CI: 0.733-0.870). Each was well calibrated with a Hosmer-Lemeshow p-value of 0.498 vs. 0.276. Moreover, decision curve analysis showed that both nomograms were clinically useful, and the post-operative nomogram generated more net benefit than the pre-operative nomogram. Web-based online calculators have been developed to greatly improve the efficiency of clinical applications.
CONCLUSIONS: Pre- and post-operative dynamic nomograms could support pre-operative treatment decisions and post-operative management in aSAH patients, respectively. Moreover, this study indicates that integrating post-operative variables into the nomogram enhanced prediction accuracy for the poor outcome of aSAH patients.

To represent a patient record with both time-invariant and time-varying features as a single vector using an end-to-end deep learning model, and further to predict the kidney failure (KF) status and mortality of heart failure (HF) patients.
The time-invariant EMR data included demographic information and comorbidities, and the time-varying EMR data were lab tests. We used a Transformer encoder module to represent the time-invariant data, and refined a long short-term memory (LSTM) with a Transformer encoder attached to the top to represent the time-varying data, taking the original measured values and their corresponding embedding vectors, masking vectors, and two types of time intervals as inputs. The proposed representations of patients with time-invariant and time-varying data were used to predict KF status (949 out of 5268 HF patients diagnosed with KF) and mortality (463 in-hospital deaths) for HF patients. Comparative experiments were conducted between the proposed model and some representative machine learning models. Ablation experiments were also performed around the time-varying data representation, including replacing the refined LSTM with the standard LSTM, GRU-D and T-LSTM, respectively, and removing the Transformer encoder and the time-varying data representation module, respectively. The visualization of the attention weights of the time-invariant and time-varying features was used to clinically interpret the predictive performance. We used the area under the receiver operating characteristic curve (AUROC), the area under the precision-recall curve (AUPRC), and the F1-score to evaluate the predictive performance of the models.
The proposed model achieved superior performance, with average AUROCs, AUPRCs and F1-scores of 0.960, 0.610 and 0.759 for KF prediction and 0.937, 0.353 and 0.537 for mortality prediction, respectively. Predictive performance improved with the addition of time-varying data from longer time periods. The proposed model outperformed the comparison and ablation references in both prediction tasks.
Both time-invariant and time-varying EMR data of patients could be efficiently represented by the proposed unified deep learning model, which shows higher performance in clinical prediction tasks. The way to use time-varying data in the current study is hopeful to be used in other kinds of time-varying data and other clinical tasks.

BACKGROUND: Personalized treatment is increasingly required for oropharyngeal squamous cell carcinoma (OPSCC) patients due to emerging new cancer subtypes and treatment options. Outcome prediction model can help identify low or high-risk patients who may be suitable to receive de-escalation or intensified treatment approaches.
OBJECTIVE: To develop a deep learning (DL)-based model for predicting multiple and associated efficacy endpoints in OPSCC patients based on computed tomography (CT).
METHODS: Two patient cohorts were used in this study: a development cohort consisting of 524 OPSCC patients (70% for training and 30% for independent testing) and an external test cohort of 396 patients. Pre-treatment CT-scans with the gross primary tumor volume contours (GTVt) and clinical parameters were available to predict endpoints, including 2-year local control (LC), regional control (RC), locoregional control (LRC), distant metastasis-free survival (DMFS), disease-specific survival (DSS), overall survival (OS), and disease-free survival (DFS). We proposed DL outcome prediction models with the multi-label learning (MLL) strategy that integrates the associations of different endpoints based on clinical factors and CT-scans.
RESULTS: The multi-label learning models outperformed the models that were developed based on a single endpoint for all endpoints especially with high AUCs ≥ 0.80 for 2-year RC, DMFS, DSS, OS, and DFS in the internal independent test set and for all endpoints except 2-year LRC in the external test set. Furthermore, with the models developed, patients could be stratified into high and low-risk groups that were significantly different for all endpoints in the internal test set and for all endpoints except DMFS in the external test set.
CONCLUSIONS: MLL models demonstrated better discriminative ability for all 2-year efficacy endpoints than single outcome models in the internal test and for all endpoints except LRC in the external set.