A time-averaged serum bicarbonate-based nomogram to predict the probability of residual kidney function preservation for patients undergoing peritoneal dialysis.

OBJECTIVE: Residual kidney function (RKF) is an important prognostic indicator in peritoneal dialysis (PD) patients. So far, there are no prediction tools available for RKF, and the association between serum bicarbonate and RKF has received little attention in patients with PD. We aimed to develop a nomogram for the preservation of RKF based on the time-averaged serum bicarbonate (TA-Bic) levels. PATIENTS AND METHODS: A prediction model was established by conducting a retrospective cohort study of 151 PD patients who had been treated at the First Affiliated Hospital of Anhui Medical University. The nomogram was developed using a multivariate Cox regression model. The discrimination, calibration, and clinical utility of the model were evaluated by the C-index, receiver operating curve (ROC) curve, calibration curve, and decision curve analysis. RESULTS: In the elderly PD onset, higher baseline values of residual glomerular filtration rate, total Kt/V and higher TA-Bic levels were identified as protective predictors of RKF loss. The nomogram was conducted on the basis of the minimum value of the Akaike Information Criterion and Bayesian Information Criterion with a reasonable C-index of 0.766, showing great discrimination, proper calibration, and high potential for clinical practice. Through the total score of the nomogram, the patients were classified into the high-risk group and low-risk group, and a higher cumulative incidence of complete RRF loss was found in the high-risk group compared with the patients in the low-risk group. CONCLUSIONS: The novel predictive nomogram model can predict the probability of RKF preservation in long-term PD patients with high accuracy. Future studies are needed to externally validate the current nomogram before clinical application.

Hepatitis E virus infection increases the risk of obstetric complications and perinatal adverse outcomes in pregnant women with chronic hepatitis B virus infection.

OBJECTIVE: Hepatitis E virus (HEV) infection may occur in pregnant women who had chronic hepatitis B virus (HBV) infection. This study aimed to evaluate whether HEV-HBV co-infection increases the risk of obstetric complications and perinatal adverse outcomes in pregnant women. PATIENTS AND METHODS: We investigated the clinical data of 3,251 pregnant women with chronic HBV infection. The obstetric complications and perinatal adverse outcomes were compared between patients with HEV-HBV co-infection and patients who had pure chronic HBV infection. RESULTS: Of the 3,251 pregnant women with chronic HBV infection, 98 patients (3%) had HEV-HBV co-infection. Compared with healthy controls, there is an increased risk of obstetric complications in pregnant women with pure HEV infection [odds ratio (OR)= 3.99, p < 0.001], pure chronic HBV infection (OR = 2.76, p < 0.001), and HEV-HBV co-infection (OR = 5.41,p < 0.001). The rate of obstetric complications and perinatal adverse outcomes is significantly higher in pregnant women with HEV-HBV co-infection compared with those with pure chronic HBV infection or those with pure HEV infection (all p< 0.05). The HEV-HBV co-infection is the most significant risk factor for perinatal adverse outcomes (OR = 15.47, p < 0.001), followed by pure HEV infection (OR = 10.22, p < 0.001), and pure HBV infection (OR = 5.82, p < 0.001). CONCLUSIONS: HEV infection increases the risk of obstetric complications and perinatal adverse outcomes in pregnant women with chronic HBV infection.

Terahertz in vivo imaging of human skin: Toward detection of abnormal skin pathologies.

Terahertz (THz) imaging has long held promise for skin cancer detection but has been hampered by the lack of practical technological implementation. In this article, we introduce a technique for discriminating several skin pathologies using a coherent THz confocal system based on a THz quantum cascade laser. High resolution in vivo THz images (with diffraction limited to the order of 100 µm) of several different lesion types were acquired and compared against one another using the amplitude and phase values. Our system successfully separated pathologies using a combination of phase and amplitude information and their respective surface textures. The large scan field (50 × 40 mm) of the system allows macroscopic visualization of several skin lesions in a single frame. Utilizing THz imaging for dermatological assessment of skin lesions offers substantial additional diagnostic value for clinicians. THz images contain information complementary to the information contained in the conventional digital images.

[HVPG minimally invasive era: exploration based on forearm venous approach].

Objective: The transjugular or transfemoral approach is used as a common method for hepatic venous pressure gradient (HVPG) measurement in current practice. This study aims to confirm the safety and effectiveness of measuring HVPG via the forearm venous approach. Methods: Prospective recruitment was conducted for patients with cirrhosis who underwent HVPG measurement via the forearm venous approach at six hospitals in China and Japan from September 2020 to December 2020. Patients' clinical baseline information and HVPG measurement data were collected. The right median cubital vein or basilic vein approach for all enrolled patients was selected. The HVPG standard process was used to measure pressure. Research data were analyzed using SPSS 22.0 statistical software. Quantitative data were used to represent medians (interquartile ranges), while qualitative data were used to represent frequency and rates. The correlation between two sets of data was analyzed using Pearson correlation analysis. Results: A total of 43 cases were enrolled in this study. Of these, 41 (95.3%) successfully underwent HVPG measurement via the forearm venous approach. None of the patients had any serious complications. The median operation time for HVPG detection via forearm vein was 18.0 minutes (12.3~38.8 minutes). This study confirmed that HVPG was positively closely related to Child-Pugh score (r = 0.47, P = 0.002), albumin-bilirubin score (r = 0.37, P = 0.001), Lok index (r = 0.36, P = 0.02), liver stiffness (r = 0.58, P = 0.01), and spleen stiffness (r = 0.77, P = 0.01), while negatively correlated with albumin (r = -0.42, P = 0.006). Conclusion: The results of this multi-centre retrospective study suggest that HVPG measurement via the forearm venous approach is safe and feasible.

Global trends in coronary artery disease and artificial intelligence relevant studies: a bibliometric analysis.

OBJECTIVE: Coronary artery disease (CAD) is a major global cause of death, greatly affecting life expectancy and quality of life for populations. With the advent of artificial intelligence (AI), there is new hope for accurately managing CAD. While recent studies have shown remarkable progress in AI and CAD research, there is a gap in comprehensive bibliometric analysis in this field. Therefore, this study aims to provide a thorough analysis of trends and hotspots in AI and CAD-related research utilizing bibliometrics. MATERIALS AND METHODS: Publications on AI and CAD relevant research from 2009 to 2023 were searched through the WoS core database (WoSCC). CiteSpace, VOSviewer and Excel 365 were used to conduct the bibliometric analysis. RESULTS: The bibliometric analysis included 1,248 publications, indicating a steady increase in AI and CAD-related publications annually. The United States of America (USA), China, and Germany were identified as the most influential countries in this field. Research institutions such as Cedars Sinai Med Ctr, Med Univ South Carolina, Harvard Med Sch and Capital Med Univ were the main contributors to research production. FRONT CARDIOVASC MED is the top-ranked journal, while J AM COLL CARDIOL emerged as the most cited journal. Schoepf, U. Joseph, Slomka, Piotr J., Berman, Daniel S. and Dey, Damini were the most prolific authors, while U. Rajendra Acharya was the most frequently co-cited author. Research related to the AI calculation of coronary flow reserve fraction and coronary artery calcification, based on coronary CT to identify CAD and cardiovascular risk, was a key research topic in this field. The potential link between cardiovascular risk stratification and radiomics is currently at the forefront of the field. CONCLUSIONS: This study is the first to use a bibliometric approach to visualize and analyze AI and CAD-related research. The findings provide insights into recent research trends and hotspots in the field and can serve as a reference for scholars to identify critical issues in this field.

AI's Role in Improving Social Connection and Oral Health for Older Adults: A Synergistic Approach.

KNOWLEDGE TRANSFER STATEMENT: This study explored how artificial intelligence (AI) can revolutionize geriatric care by improving oral health and alleviating social disconnection among isolated older adults. The findings can guide clinicians in integrating AI tools into practices, assist policymakers in developing AI-inclusive health policies, and inform patients about the potential benefits of AI in enhancing their health outcomes and social connection.

Bioinformatics screening of gene expression profile and diagnostic application of meningeal carcinoma.

OBJECTIVE: The aim of this study was to research gene expression profiles and diagnostic applications of meningeal carcinoma based on bioinformatics. MATERIALS AND METHODS: We used the Gene Expression Omnibus (GEO) database to obtain the GSE43290 dataset based on the expression data of normal meninges and meningiomas consisting of 51 samples divided into two groups (47 samples of meningioma tumors and four samples of normal meninges). We used the GEO2R tool to identify differentially expressed genes (DEGs) by setting the log2 fold change as greater than two and an adjusted p-value lower than 0.05. We used the database for annotation, visualization and integrated discovery (DAVID) to perform gene ontology, biological pathways and functional annotation of the DEGs. A search Tool for the Retrieval of Interacting Gene database (STRING) was used to obtain Protein-Protein Interaction (PPI) and modular networks based on the Markov clustering algorithm. RESULTS: Our study identified 358 significant DEGs, of which 343 were downregulated genes while 15 were upregulated. Five significant hub genes (CXCL8, AGT, CXCR4, CXCL12 and CXCL2) were associated with various biological pathways, molecular functions and Kyoto Encyclopedia of Genes and Genomes (KEGG) pathways. The DEGs were enriched in biological pathways of chemokine-mediated signaling, positive regulation of leukocyte chemotaxis, second messenger-mediated signaling, induction of positive chemotaxis, CXCR chemokine receptor binding and activities of cytokines. CONCLUSIONS: These hub genes and pathways could be targeted in clinical research to discover new treatments for meningeal carcinoma.

Prediction of Radiation Treatment Response for Locally Advanced Rectal Cancer via a Longitudinal Trend Analysis Framework on Cone-Beam CT.

Locally advanced rectal cancer (LARC) presents a significant challenge in terms of treatment management, particularly with regards to identifying patients who are likely to respond to radiation therapy (RT) at an individualized level. Patients respond to the same radiation treatment course differently due to inter- and intra-patient variability in radiosensitivity. In-room volumetric cone-beam computed tomography (CBCT) is widely used to ensure proper alignment, but also allows us to assess tumor response during the treatment course. In this work, we proposed a longitudinal radiomic trend (LRT) framework for accurate and robust treatment response assessment using daily CBCT scans for early detection of patient response. The LRT framework consists of four modules: (1) Automated registration and evaluation of CBCT scans to planning CT; (2) Feature extraction and normalization; (3) Longitudinal trending analyses; and (4) Feature reduction and model creation. The effectiveness of the framework was validated via leave-one-out cross-validation (LOOCV), using a total of 840 CBCT scans for a retrospective cohort of LARC patients. The trending model demonstrates significant differences between the responder vs. non-responder groups with an Area Under the Curve (AUC) of 0.98, which allows for systematic monitoring and early prediction of patient response during the RT treatment course for potential adaptive management.

The effect of repeated transcranial magnetic stimulation combined with cognitive rehabilitation training on post-stroke cognitive impairment.

OBJECTIVE: The aim of this study was to explore the effect of repetitive transcranial magnetic stimulation (rTMS) combined with cognitive rehabilitation training on post-stroke cognitive impairment (PSCI). PATIENTS AND METHODS: We retrospectively reviewed clinical data from 119 patients with PSCI admitted to our hospital from December 2021 to April 2023, of which 58 received pure cognitive rehabilitation training (control group) and 61 received rTMS combined with cognitive rehabilitation training (observation group). We calculated measures of cognitive function rehabilitation, daily living activity abilities, latency and amplitude of P300 wave of evoked potential, and serum biochemical index levels before and after the intervention in the two groups. RESULTS: After the intervention, the scores of the Montreal Cognitive Assessment (MoCA) scale and Rivermead behavioral memory test (RBMT) had improved in the two groups. Also, the Modified Barthel Index (MBI) scores of the two groups increased after the intervention. The P300 wave latencies in both groups decreased and their amplitudes increased after the intervention. The levels of serum neurotrophin-3 (NT-3) and brain-derived neurotrophic factor (BDNF) in the two groups were higher, and the levels of brain glial fibrillary acidic protein (GFAP) were lower after the intervention. All these improvements were more marked in the observation group than in the control group (all p<0.05). CONCLUSIONS: Compared with simple cognitive rehabilitation training, the training combined with rTMS was more effective at restoring cognitive function, improving daily living activity abilities, and improving the treatment outcome of patients with PSCI.

Feature selection based on unsupervised clustering evaluation for predicting neoadjuvant chemoradiation response for patients with locally advanced rectal cancer.

Accurate response prediction allows for personalized cancer treatment of locally advanced rectal cancer (LARC) with neoadjuvant chemoradiation. In this work, we designed a convolutional neural network (CNN) feature extractor with switchable 3D and 2D convolutional kernels to extract deep learning features for response prediction. Compared with radiomics features, convolutional kernels may adaptively extract local or global image features from multi-modal MR sequences without the need of feature predefinition. We then developed an unsupervised clustering based evaluation method to improve the feature selection operation in the feature space formed by the combination of CNN features and radiomics features. While normal process of feature selection generally includes the operations of classifier training and classification execution, the process needs to be repeated many times after new feature combinations were found to evaluate the model performance, which incurs a significant time cost. To address this issue, we proposed a cost effective process to use a constructed unsupervised clustering analysis indicator to replace the classifier training process by indirectly evaluating the quality of new found feature combinations in feature selection process. We evaluated the proposed method using 43 LARC patients underwent neoadjuvant chemoradiation. Our prediction model achieved accuracy, area-under-curve (AUC), sensitivity and specificity of 0.852, 0.871, 0.868, and 0.735 respectively. Compared with traditional radiomics methods, the prediction models (AUC = 0.846) based on deep learning-based feature sets are significantly better than traditional radiomics methods (AUC = 0.714). The experiments also showed following findings: (1) the features with higher predictive power are mainly from high-order abstract features extracted by CNN on ADC images and T2 images; (2) both ADC_Radiomics and ADC_CNN features are more advantageous for predicting treatment responses than the radiomics and CNN features extracted from T2 images; (3) 3D CNN features are more effective than 2D CNN features in the treatment response prediction. The proposed unsupervised clustering indicator is feasible with low computational cost, which facilitates the discovery of valuable solutions by highlighting the correlation and complementarity between different types of features.

NRG Oncology Assessment of Artificial Intelligence Deep Learning-Based Auto-segmentation for Radiation Therapy: Current Developments, Clinical Considerations, and Future Directions.

Deep learning neural networks (DLNN) in Artificial intelligence (AI) have been extensively explored for automatic segmentation in radiotherapy (RT). In contrast to traditional model-based methods, data-driven AI-based models for auto-segmentation have shown high accuracy in early studies in research settings and controlled environment (single institution). Vendor-provided commercial AI models are made available as part of the integrated treatment planning system (TPS) or as a stand-alone tool that provides streamlined workflow interacting with the main TPS. These commercial tools have drawn clinics' attention thanks to their significant benefit in reducing the workload from manual contouring and shortening the duration of treatment planning. However, challenges occur when applying these commercial AI-based segmentation models to diverse clinical scenarios, particularly in uncontrolled environments. Contouring nomenclature and guideline standardization has been the main task undertaken by the NRG Oncology. AI auto-segmentation holds the potential clinical trial participants to reduce interobserver variations, nomenclature non-compliance, and contouring guideline deviations. Meanwhile, trial reviewers could use AI tools to verify contour accuracy and compliance of those submitted datasets. In recognizing the growing clinical utilization and potential of these commercial AI auto-segmentation tools, NRG Oncology has formed a working group to evaluate the clinical utilization and potential of commercial AI auto-segmentation tools. The group will assess in-house and commercially available AI models, evaluation metrics, clinical challenges, and limitations, as well as future developments in addressing these challenges. General recommendations are made in terms of the implementation of these commercial AI models, as well as precautions in recognizing the challenges and limitations.

[Analysis on the current situation and influencing factors of residents' satisfaction with the built environment of China's Hygienic City Initiative].

Objective: To understand the current situation and the main influencing factors of residents' satisfaction with the built environment of China's Hygienic City Initiative. Methods: From the list of China's hygienic cities (excluding county-level cities), 61 cities were randomly selected in equal proportion and the eligible respondents were randomly selected by using the "Questionnaire Star" network platform to carry out the online questionnaire survey. A self-made satisfaction evaluation scale was used to investigate the satisfaction of the included respondents with the urban built environment and search for relevant data on the city level. The two-level multi-factor mixed effect model was constructed to analyze the influencing factors of residents' satisfaction with the built environment of China's Hygienic City Initiative. Results: The age range of 2 465 respondents was mainly between 18 and 40 years old (79.9%), with males being the main group (45.8%). The total score of residents' satisfaction with the built environment of China's hygienic cities was (69.14±13.24) points. Based on four standardized dimensions of sense of gain, the result showed that the satisfaction of urban governance had the highest score (65.08 points), followed by urban environmental sanitation (63.68 points), urban lifestyle (59.97 points) and urban basic function (59.02 points). The analysis results of the two-level multi-factor mixed effect model showed that compared with residents with an annual average concentration of inhalable fine particles in the environment>48 micrograms/cubic meter, residents with an average concentration between 38 and 48 micrograms/cubic meter [ß (95%CI): 1.65 (0.08, 3.21)] and≤37 micrograms/cubic meter or less [ß (95%CI): 1.98 (0.53, 3.43)] had higher satisfaction. Compared with residents whose proportion of the secondary industry to GDP was≤40.9%, residents in cities with a larger proportion had a lower satisfaction level [residents with a proportion of 40.9%-48.03%, ß (95%CI):-2.21 (-3.93, -0.49); residents with a proportion greater than 48.03%, ß (95%CI):-2.58 (-4.58, -0.59)]. Compared with residents with a junior high school or lower education level, residents with a higher education level had a lower satisfaction level [ß (95%CI):-2.37 (-4.57, -0.17)]. Residents of universities and above [ß (95%CI):-3.82 (-6.05, -1.60)], regularly participate in physical exercise [ß (95%CI): 5.78 (4.71, 6.84)] and self-rated good health status [ß (95%CI): 6.39 (5.33, 7.45)] had a higher satisfaction level. Conclusion: The satisfaction of residents with the built environment of China's hygienic cities is still acceptable. Satisfaction is related to individual characteristics such as residents' cultural level, type of residence, frequent participation in physical exercise, and self-rated good health status, as well as urban-level factors such as green coverage rate in built-up areas, annual average concentration of inhalable fine particles, and the proportion of GDP in the secondary industry.

[Plurihormonal PIT1-lineage pituitary neuroendocrine tumors: a clinicopathological study].

Objective: To investigate the clinicopathological characteristics of plurihormonal PIT1-lineage pituitary neuroendocrine tumors. Methods: Forty-eight plurihormonal PIT1-lineage tumors were collected between January 2018 and April 2022 from the pathological database of Sanbo Brain Hospital, Capital Medical University. The related clinical and imaging data were retrieved. H&E, immunohistochemical and special stains were performed. Results: Out of the 48 plurihormonal PIT1-lineage tumors included, 13 cases were mature PIT1-lineage tumors and 35 cases were immature PIT1-lineage tumors. There were some obvious clinicopathological differences between the two groups. Clinically, the mature plurihormonal PIT1-lineage tumor mostly had endocrine symptoms due to increased hormone production, while a small number of immature PIT1-lineage tumors had endocrine symptoms accompanied by low-level increased serum pituitary hormone; patients with the immature PIT1-lineage tumors were younger than the mature PIT1-lineage tumors; the immature PIT1-lineage tumors were larger in size and more likely invasive in imaging. Histopathologically, the mature PIT1-lineage tumors were composed of large eosinophilic cells with high proportion of growth hormone expression, while the immature PIT1-lineage tumors consisted of chromophobe cells with a relatively higher expression of prolactin; the mature PIT1-lineage tumors had consistently diffuse cytoplasmic positive staining for keratin, while the immature PIT1-lineage tumors had various expression for keratin; the immature PIT1-lineage tumors showed more mitotic figures and higher Ki-67 proliferation index; in addition, 25.0% (12/48) of PIT1-positive plurihormonal tumors showed abnormal positive staining for gonadotropin hormones. There was no significant difference in the progression-free survival between the two groups (P=0.648) by Kaplan-Meier analysis. Conclusions: Plurihormonal PIT1-lineage tumor belongs to a rare type of PIT1-lineage pituitary neuroendocrine tumors, most of which are of immature lineage. Clinically increased symptoms owing to pituitary hormone secretion, histopathologically increased number of eosinophilic tumor cells with high proportion of growth hormone expression, diffusely cytoplasmic keratin staining and low proliferative activity can help differentiate the mature plurihormonal PIT1-lineage tumors from the immature PIT1-lineage tumors. The immature PIT1-lineage tumors have more complicated clinicopathological characteristics.

[Application of intraoperative optical coherence tomography in deep lamellar keratoplasty].

Objective: To evaluate the clinical application value of intraoperative optical coherence tomography (iOCT) in deep anterior lamellar keratoplasty (DALK) using the big-bubble technique to bare Descemet's membrane. Methods: Retrospective case series. Clinical data of 92 patients (92 eyes) with monocular stromal corneal diseases who underwent big-bubble DALK in the Eye Hospital of Shandong First Medical University from January 2020 to August 2021 were collected. There were 53 males and 39 females. The average age was (53.2±16.0) years old. All patients underwent iOCT scanning to determine the location and depth of the injection needle after initial removal of the corneal lesion, to observe the integrity of the recipient bed, Descemet's membrane, after complete lesion removal, and to observe the adhesion between the corneal graft and the recipient bed and check folds on the recipient bed after suturing of the corneal graft. The intraoperative perforation of Descemet's membrane, postoperative thickness of the cornea and the recipient bed, visual acuity, and corneal astigmatism were recorded. Results: By iOCT, the thickness of the recipient bed was found to be about 1/2 of the corneal thickness and relatively uniform in all directions in 62 eyes (67.4%), so the sterile air was injected from the center of the recipient bed to separate it from the stromal layer. In 30 eyes (32.6%) with an uneven thickness of the recipient bed, the sterile air was injected from the paracentral area of the recipient bed. Under the guidance of iOCT scanning, 89 eyes (96.7%) did not experience any perforation of Descemet's membrane during surgery. The Descemet's membrane folds in the central 5-mm area of the recipient bed was observed and flattened in 20 eyes with the assistance of iOCT scanning. The postoperative corneal thickness was (578.95±108.26) µm, and the recipient bed thickness was (36.06±23.11) µm. The best corrected visual acuity of all patients at 6 months after surgery was 0.57±0.25 logMAR, which was significantly better than that before surgery (1.61±1.27 logMAR; P<0.001). The average corneal astigmatism at 6 months after surgery was (2.72±2.44) diopters. Conclusions: The application of iOCT scanning in DALK surgery assisted by the big-bubble method can provide safe guidance for surgeons to adopt correct surgical procedures, decrease the risk of Descemet's membrane perforation, reduce the recipient bed folds, and facilitate corneal interlayer adhesion, thereby improving the visual prognosis.

MRI-Guided Radiation Therapy for Prostate Cancer: The Next Frontier in Ultrahypofractionation.

Technological advances in MRI-guided radiation therapy (MRIgRT) have improved real-time visualization of the prostate and its surrounding structures over CT-guided radiation therapy. Seminal studies have demonstrated safe dose escalation achieved through ultrahypofractionation with MRIgRT due to planning target volume (PTV) margin reduction and treatment gating. On-table adaptation with MRI-based technologies can also incorporate real-time changes in target shape and volume and can reduce high doses of radiation to sensitive surrounding structures that may move into the treatment field. Ongoing clinical trials seek to refine ultrahypofractionated radiotherapy treatments for prostate cancer using MRIgRT. Though these studies have the potential to demonstrate improved biochemical control and reduced side effects, limitations concerning patient treatment times and operational workflows may preclude wide adoption of this technology outside of centers of excellence. In this review, we discuss the advantages and limitations of MRIgRT for prostate cancer, as well as clinical trials testing the efficacy and toxicity of ultrafractionation in patients with localized or post-prostatectomy recurrent prostate cancer.

Predicting Overall Survival for Patients with Malignant Mesothelioma Following Radiotherapy via Interpretable Machine Learning.

PURPOSE/OBJECTIVES: Malignant pleural mesothelioma (MPM) is a rare but aggressive cancer arising from the cells of the thoracic pleura with a poor prognosis. We aimed to develop a model, via interpretable machine learning (ML) methods, predicting overall survival for MPM following radiotherapy based on dosimetric metrics as well as patient characteristics. MATERIALS/METHODS: Sixty MPM (37 right, 23 left) patients treated on a Tomotherapy unit between 2013 and 2018 were retrospectively analyzed. All patients received 45 Gy (25 fractions). The multivariable Cox regression (Cox PH) model and Survival Support Vector Machine (sSVM) were applied to build predictive models of overall survival (OS) based on clinical, dosimetric, and combined variables. RESULTS: Significant differences in dosimetric endpoints for critical structures, i.e., the lung, heart, liver, kidney, and stomach, were observed according to target laterality. The OS was found to be insignificantly different (p = 0.18) between MPM patients who tested left- and right-sided, with 1-year OS of 77.3% and 75.0%, respectively. With Cox PH regression, considering dosimetric variables for right-sided patients alone, an increase in PTV_Min, Total_Lung_PTV_Mean, Contra_Lung_Volume, Contra_Lung_V20, Esophagus_Mean, and Heart_Volume had a greater hazard to all-cause death, while an increase in Total_Lung_PTV_V20, Contra_Lung_V5, and Esophagus_Max had a lower hazard to all-cause death. Considering clinical variables alone, males and increases in N stage had greater hazard to all-cause death; considering both clinical and dosimetric variables, increases in N stage, PTV_Mean, PTV_Min, and esophagus_Mean had greater hazard to all-cause death, while increases in T stage and Heart_V30 had lower hazard to all-cause-death. In terms of C-index, the Cox PH model and sSVM performed similarly and fairly well when considering clinical and dosimetric variables independently or jointly. CONCLUSIONS: Clinical and dosimetric variables may predict the overall survival of mesothelioma patients, which could guide personalized treatment planning towards a better treatment response. The identified predictors and their impact on survival offered additional value for translational application in clinical practice.