Prognostic System Research Articles

Machine learning-based integration reveals immunological heterogeneity and the clinical potential of T cell receptor (TCR) gene pattern in hepatocellular carcinoma.

The T Cell Receptor (TCR) significantly contributes to tumor immunity, whereas the intricate interplay with the Hepatocellular Carcinoma (HCC) microenvironment and clinical significance remains largely unexplored. Here, we aimed to examine the function of TCR signaling in tumor immunity and its clinical significance in HCC. Our objective was to employ TCR signaling genes and a machine learning-based integrative methodology to construct a prognostic prediction system termed the TCR score. Herein, we revealed that the TCR score serves as an independent risk factor for overall survival in HCC patients, demonstrating stable and robust performance. The accuracy of the TCR score significantly exceeds that of traditional clinical variables and published signatures. Additionally, the immune infiltration was abundant in patients with low TCR scores. Single-cell cohort analysis further demonstrates that patients with low TCR scores possess an immune-active tumor microenvironment (TME), with T/NK cells enhancing interactions with myeloid cells through signaling networks such as MIF, MK, and SPP1. In response to these changes in the TME, patients with high TCR scores exhibit poorer outcomes and shorter survival in immunotherapy cohorts. In vitro experiments demonstrated that the key TCR signaling biomarker SOS1 knockdown significantly suppresses the HCC cells' capability to proliferate, invade, and migrate while enhancing tumor cell apoptosis. The TCR score could function as a robust and potential tool to predict immune activity and improve clinical outcomes for HCC patients.

A multimodal deep learning approach for the prognostic stratification of patients with colorectal cancer (CRC).

287 Background: Traditional prognostic systems like the AJCC TNM staging for colorectal cancer (CRC) often fall short in predicting long-term patient outcomes. These systems often rely on limited pathologic features, leading to generalized approaches to treatment despite diverse tumor heterogeneity, such as the complex interaction between the tumor-host microenvironment. There is therefore a pressing need for more accurate, scalable tools to enhance decision-making and predict outcomes for patients with CRC. Methods: Tumor sections from 191 CRC patients were comprehensively stained for CD8 to examine CD8-positive tumor-infiltrating lymphocytes (TILs). To account for tumor heterogeneity, multiple areas of the tumor were evaluated to include intertumoral and peritumoral areas. Slides were digitized and quantitatively analyzed using a cloud-based platform (SpatialX Diagnostics, Inc. USA). Additionally, clinicopathologic features including patient demographics, 8th edition AJCC staging, lymphovascular invasion (LVI), perineural invasion (PNI), mismatch repair (MMR) protein status, tumor location, presence/development of distant metastases, and patient follow-up were collected. Merging CD8 AI findings with clinicopathologic features, a complete data set was available for 175 patients. Cases were randomly assigned into 70% training and 30% validation. In the training set, unsupervised artificial intelligence (AI) models integrated clinicopathologic data and CD8-positive TIL counts using vision transformer models. The final model combined spatially resolved pathologic features with clinical variables to statistically predict overall survival (OS) and distant metastasis risk (DMR). Results: In the validation cohort, the model stratified patients into two groups based on a deep learning-derived risk score, with statistically significant differences between low-risk and high-risk groups for OS (p<0.02) and DMR prediction (p<0.0001), For OS prediction, the model selected tumor site, PNI, MMR status, epithelial and stromal CD8-positive TILs, and 5 deep vision features as the top 10 clinically significant features. For DMR prediction, the age, T- and N-stage, PNI, and 6 deep vision-derived features as key predictors. Conclusions: As captured by vision transformers, the distribution and spatial arrangement of CD8-positive TILs are critical factors in patient stratification for OS and DMR. AI-driven models like the one herein offer the potential for more personalized management strategies, advancing CRC management and improving patient outcomes beyond traditional prognostic staging systems and parameters.

Prognostic value of gene expression profiling in melanoma: a systematic literature review

Introduction. Skin melanoma, despite having similar clinical and histological characteristics, can have different prognoses. Gene expression profiling potentially allows for more accurate risk stratification of patients.Aim. To study prognostic test systems for assessing outcomes in patients with skin melanoma based on the analysis of primary tumors.Materials and methods. A systematic literature review (scoping review) was conducted in accordance with PRISMA-ScR principles. The search was performed in PubMed (2008–2024). Two independent reviewers conducted the study selection and data analysis to assess concordance. The data were presented descriptively.Results. Out of 149 identified publications, 31 studies were included in the review. The effectiveness of four test systems was evaluated, with the most frequently used being DecisionDx-Melanoma (19/31, 61.3%). This test stratifies patients by molecular classes: patients at high risk were found to have a 5.33 (±1.25) times higher likelihood of disease progression and poorer survival rates compared to lower-risk patients. No studies included data on the Russian population.Conclusions. Gene expression profiling demonstrates high accuracy in predicting outcomes for patients with skin melanoma.

P-467. The clinical prognostic risk stratification system for HIV infected hepatocellular carcinoma

Abstract Background Patients with human immunodeficiency virus (HIV) are more susceptible to liver cancer because of their compromised immune system. There is no specific prognostic model for HIV-infected hepatocellular carcinoma (HCC) patients. Methods Clinical data of 85 patients with HIV-infected HCC was divided into a 7:3 ratio for training and internal validation sets, while the data of 23 patients with HIV-infected HCC was served as the external validation set. Data of 275 HIV-negative HCC patients was considered as external HIV-negative validation set. Variables associated with overall survival (OS) in the training set were used to develop the HIV-infected HCC prognosis (HIHP) model. The model was tested in the internal and external validation sets. The predictive accuracy of the model was assessed with conventional HIV-negative HCC prognostic scoring systems. Results The HIHP model demonstrated a significant association with OS in the training set, with a median OS of 13 months for low risk, 7 months for medium risk, and 3 months for high risk (p < 0.001). The HIHP model showed a significant association with OS, and exhibited greater discriminative abilities compared to conventional HIV-negative HCC prognostic models both in the internal and external validation sets. In the external HIV-negative validation set, the HIHP model did not show better discrimination than conventional HIV-negative HCC scores. Conclusion The new model presented in the work provided a more accurate prognostic prediction of OS in HIV-infected HCC patients. However, the model is not applicable to patients with HIV-negative HCC. Disclosures All Authors: No reported disclosures

Future directions in the evaluation and management of newly diagnosed metastatic cancer.

There is a much debate regarding optimal selection in patients with metastatic cancer who should undergo local treatment (surgery or radiation treatment) to the primary tumor and/or metastases. Additionally, the optimal treatment of newly diagnosed metastatic cancer is largely unclear. Current prognostication systems to best inform these clinical scenarios are limited, as all metastatic patients are grouped together as having Stage IV disease without further incorporation of patient and disease-specific covariates that significantly impact patient outcomes. Therefore, improving current prognostic scoring systems and incorporation of these covariates is essential to best individualize treatment for patients with metastatic cancer. In this narrative review article, we provide a detailed review of prognostication systems that can be used for both the site of metastasis and primary site to best tailor treatment in these patients. Additionally, we discuss the incorporation and ongoing developments in radiographic, genomic, and biostatistical techniques that can be used as prognostication tools.

Unravelling ATTR Cardiac Amyloidosis in Iceland: A Nationwide Epidemiological Study

Introduction: Cardiac amyloidosis (CA) arises from the deposition of misfolded amyloid proteins in the heart's extracellular matrix, leading to significant cardiac disease. Recent data suggest that CA is under recognised and advances in treatment have increased focus on this condition with the intention of implementing treatment earlier to improve prognosis. There is limited knowledge regarding the prevalence of Transthyretin-CA (ATTR-CA) on a national level, particularly in Iceland. Therefore, this study represents the first nationwide effort to evaluate the baseline characteristics, diagnostics, and treatment of ATTR-CA in Iceland. Methods: A retrospective study of all patients diagnosed with ATTR-CA in Iceland from 6 May 2013 to 11 March 2024 were identified in the Icelandic Cardiac Amyloid Registry (ICE-CAR) created in 2023 by heart failure (HF) specialists at Landspitali University Hospital in Reykjavik, Iceland. Diagnosis was based on different combinations of transthoracic echocardiography (TTE), an elevated Perugini score on bone scintigraphy and heart biopsies, as well measurements of free light chains, M-component measurements in blood and urine. Patients were grouped according to the National Amyloidosis Centre (NAC) prognostic staging system for ATTR-CA. Results: In total, 65 patients with ATTR-CA were identified (males n=60, females n=5, median age 81.4 years [IQR 75.5-85.5 years]), all wild-type and no mutant variant. Diagnosis was made with myocardial biopsy in 7 cases. Upon diagnosis, 83% of the patients had an interventricular septum thickness of ≥15mm and 92% showed a posterior wall thickness of ≥12mm. Approximately 57% of patients belonged to New York Heart Association (NYHA) functional class I-II. The HF phenotypes according to left ventricular ejection fraction (LVEF) were distributed as follows: reduced (HFrEF) n=24 (37%), mildly reduced (HFmrEF) n=9 (14%), preserved (HFpEF) n=29 (44.5%), and unknown LVEF n=3 (4.5%). A total of 54 patients had reported NAC stage: Stage I 23 (35.4%), Stage II 20 (30.8%), Stage III 11 (16.9%). Around 32% received disease modifying treatment. Conclusion Despite the low NYHA class observed in the study population, our findings in Iceland's nationwide assessment of ATTR-CA indicate more advanced age and lower LVEF at diagnosis compared to other studies. This highlights the critical need for early detection and appropriate therapeutic interventions in managing ATTR-CA.

Development and validation of a novel artificial intelligence algorithm for precise prediction the postoperative prognosis of esophageal squamous cell carcinoma

BackgroundEsophageal squamous cell carcinoma (ESCC) is a highly aggressive malignancy, and current postoperative prognostic assessment methods remain unsatisfactory, underlining the urgent to develop a reliable approach for precision medicine. Given the similarities with gametogenesis, cancer/testis genes (CTGs) are acknowledged for regulation unrestrained multiplication and immune microenvironment during oncogenic processes. These processes are associated with advanced disease and poorer prognosis, indicating that CTGs could serve as ideal prognostic biomarkers in ESCC. The purpose of this study is to develop a novel clinically prognostic prediction system to facilitate the individualized postoperative care.MethodsWe conducted LASSO regression analysis of protein-coding CTGs and clinical characteristics from 119 pathologically confirmed ESCC patients to recognize powerful predictive variables. We employed nine supervised machine learning classifiers and integrated best predictive machine learning classifiers by weighted voting method to construct an ensemble model called PPMESCC. Additionally, functional assay was conducted to examine the potential effect of top-ranking CTG HENMT1 in ESCC.ResultsLASSO regression identified five CTGs and TNM stage as optimized prognostic features. Six machine learning classifiers were integrated to construct an ensemble model, PPMESCC, which exhibited outstanding performance in ESCC prediction. The AUC for PPMESCC was 0.9828 (95% confidence interval: 0.9608 to 0.9926), with an accuracy of 98.32% (95% CI: 96.64–99.16%) in the discovery cohort and 0.9057 (95% CI: 0.8897 to 0.9583) of AUC with an accuracy of 90% (95% CI: 89.08–93.28%) in validation cohort. In addition, the top-ranking CTG HENMT1 encodes 2’-O-methyltransferase of piRNAs that was confirmed positively correlated with the proliferation capacity of ESCC cells. Then we systematically screen piRNAs associated with esophageal carcinoma based on GWAS, eQTL-piRNA, and i2OM databases, and successfully discovered 8 piRNAs potentially regulated by HENMT1.ConclusionThe study highlights the clinical utility of PPMESCC algorithm in prognostic prediction that may facilitate to establish the personalized screening and management strategies for postoperative ESCC patients.

Accuracy of Established Prognostic Staging Systems for Cardiac Transthyretin Amyloidosis in the Tafamidis Era.

Biomarker-based prognostic staging systems, including the National Amyloidosis Centre (NAC) and the Mayo staging systems, are widely-used but have only been validated for treatment-naive patients with cardiac transthyretin amyloidosis (ATTR-CA). The purpose of this study was to assess the accuracy of the NAC and Mayo staging systems in patients with ATTR-CA treated with tafamidis. A retrospective observational study following patients with ATTR-CA from initiation of tafamidis (baseline) to time of all-cause death was conducted. Patients were stratified according to the NAC and an adapted Mayo staging system incorporating high-sensitivity cardiac troponin T. Agreement was assessed using weighted Cohen's kappa. The staging systems' ability to identify subgroups with distinct overall survival was assessed using Kaplan-Meier analyses and pairwise log-rank tests. A total of 251 patients with wild-type ATTR-CA treated with tafamidis were followed for a median of 521 (IQR: 262-842) days. There was substantial agreement (weighted kappa=0.661; P<0.001) between the NAC and the adapted Mayo staging system. Significant differences in estimated overall survival were observed across all disease stages of the adapted Mayo staging system (I vs II: P=0.032; I vs III: P<0.001; II vs III: P=0.036). Accordingly, estimated overall survival was significantly lower in NAC III compared to NAC I (P<0.001) and NAC II (P=0.015). However, there was no significant difference between NAC I and NAC II (P=0.340). Both staging systems identified a distinct group of patients with ATTR-CA at the highest risk of death but only the adapted Mayo staging system could accurately distinguish between low- and intermediate-risk patients in the setting of disease-modifying treatment with tafamidis.

Evaluation of Ki67 in pathological prognostic staging of breast cancer: a tertiary care center study

ABSTRACT Background The rising global burden of breast cancer demands early detection and effective treatment, with a focus on prognostic and predictive markers. The eighth edition of the American Joint Committee on Cancer staging manual introduced a new prognostic staging system to increase the predictive power of the existing anatomical staging system of breast cancer. The current study aimed to establish the correlation between Ki67 expression with molecular subtypes and with the pathological prognostic stage of invasive ductal carcinoma. Materials and Methods A total of 40 patients were included in the study with samples from 32 modified radical mastectomies and 8 biopsies. Hematoxylin and Eosin staining, histopathological analysis and Ki67 immunostaining were conducted. Descriptive and inferential statistical analyses were performed. Results Bloom Richardson Grade II was the predominant histological grade. In Grade II cases, 15 of 24 had a Ki67 labeling index of 26–45%, while 6 exceeded 45% (p = 0.001). Pathological prognostic staging reclassified 27 cases, with 24 (75%) downstaged, 3 (9.38%) upstaged, and 5 (15.63%) retaining their clinical stage. Conclusions Ki67 immunohistochemistry is an effective tool for assessing proliferative activity of invasive ductal carcinoma, aiding in pathological prognostic stage stratification and offering insights into tumor biology.

Role of belgium outcome of burn injury (BOBI) score in the assessment of mortality in scald burns

Burn injuries are a significant public health concern in developing countries like India, where limited healthcare resources contribute to high mortality rates. Prognostic scoring systems, such as the Belgium Outcome of Burn Injury (BOBI) score, have been developed to predict mortality and guide clinical decision-making. However, their applicability in resource-constrained settings remains underexplored. This study evaluates the effectiveness of the BOBI score in predicting mortality among burn patients in such contexts.To assess the reliability of the BOBI score and other burn prognostic systems in predicting mortality among burn patients in resource-limited settings, focusing on bedside risk assessment, patient counselling, and resource optimization. This case study was conducted in a tertiary care hospital in South India after obtaining ethical committee approval. A 7-year-old male patient with a 7% total body surface area (TBSA) scald burn involving the genitalia, bilateral thighs, and lower abdomen was assessed using the BOBI scoring system. Mortality predictions were based on parameters such as age, TBSA affected, and the presence of inhalation injury.The patient's BOBI score indicated a mortality risk of 0.1%. This low risk was attributed to favorable parameters, including age (&amp;#60;50 years), limited TBSA involvement (&amp;#60;20%), and the absence of inhalation injury. The BOBI score demonstrates potential as a practical tool for predicting mortality in pediatric burn patients and guiding care prioritization in settings with limited resources. However, variability in patient demographics and resource constraints in developing regions necessitate the standardization of scoring systems to enhance their predictive accuracy and applicability. Further studies are recommended to validate BOBI and similar scoring systems for broader use in diverse populations.

Epidemiological Characteristics and Prognostic Scoring in Toxic Epidermal Necrolysis and Stevens-Johnson Syndrome: Insights from a 17-Year Burn Center Experience.

Background and Objectives: Toxic epidermal necrolysis (TEN) and Stevens-Johnson syndrome (SJS) are rare yet life-threatening dermatologic conditions characterized by severe skin and mucous membrane involvement. Accurate prognostic systems are crucial for clinical management to assess disease severity and predict outcomes. The primary objective of this study was to assess the epidemiological characteristics and clinical outcomes of patients with Stevens-Johnson syndrome (SJS), toxic epidermal necrolysis (TEN), and SJS/TEN overlap over a 17-year period at a specialized burn center. The secondary objectives were to evaluate the performance of existing prognostic scoring systems (SCORTEN, Re-SCORTEN, and ABCD-10) in predicting mortality and to propose a novel classification tree model to improve mortality prediction. Materials and Methods: A 17-year retrospective study at a burn center included 68 patients with SJS, SJS/TEN overlap, or TEN. Demographic, clinical, laboratory data, and prognostic scores (SCORTEN, Re-SCORTEN, ABCD-10) were collected and analyzed for associations with mortality. A classification tree was created to detect unknown determinants of SJS/TEN mortality. Results: The drug most frequently associated with the occurrence of SJS/TEN was metamizole. The mortality rate was 51%. Affected body surface area, platelet count, and serum blood urea nitrogen differed significantly between survivors and non-survivors. Regarding the scoring systems, only the Re-SCORTEN showed reliable differentiation for these groups. A classification tree model achieved an accuracy of 89% in predicting the mortality risk. In the ROC curve analysis, the AUC values were 0.88 for the classification tree, 0.66 for Re-SCORTEN, 0.61 for SCORTEN, and 0.56 for ABCD-10. Conclusions: This study explores mortality predictors in SJS/TEN via a classification tree model, highlighting potential factors for further investigation. While cautioning against immediate clinical application due to data constraints, the findings underscore the need for larger studies to validate and refine prediction models in this context.

Comprehensive Characterization of Overt Myelofibrosis in an Asian Cohort: Phenotype, Mutation Landscape and Discordance Among Scoring Systems.

Various prognostic scoring systems in myelofibrosis (MF) have been developed to guide clinical decision-making in MF. However, discrepancies between different scoring systems for individual patients remain poorly understood, which can result in conflicting treatment recommendations. Moreover, data regarding there applicability in Asian populations remain scarce. We conducted a retrospective analysis of patients with overt MF at National Taiwan University Hospital from November 1, 2006, to November 30, 2023. This study evaluates the distribution, concordance, and prognostic value of various scoring systems (IPSS, DIPSS, DIPSS+, MYSEC-PM, MIPSS70, MIPSS70+v2, GIPSS), focusing on the mutational landscape, particularly TP53 mutations, and cytopenic phenotypes in an Asian MF cohort. All prognostic systems effectively stratified patients by risk (p<0.005); however, concordance between systems was low (Cohen's κ<0.4, except for IPSS vs. DIPSS+). GIPSS demonstrated superior performance with a comparable C-index but lower Akaike and Bayesian information criterion values. Besides high-molecular risk mutations, TP53 mutations (5.2%) were associated with worse overall survival (OS) (5-year: 30% vs. 68%, p<0.001) and a trend toward higher leukemic transformation (5-year: 22% vs. 10%, p=0.055). Cytopenic phenotype (59%) was associated with a higher incidence of ASXL1 mutations (44% vs. 28%, p=0.04). In multivariable analysis, elderly patients, higher-risk GIPSS, TP53 mutation and cytopenic phenotype were associated with a poorer OS. This study validated multiple prognostic scoring systems in an Asian MF cohort, with GIPSS showing superior risk stratification. Further, cytopenic phenotype and TP53 mutations were identified as independent factors linked to poorer survival.

Refining High-Risk Multiple Myeloma: Advancements in Genomic, Clinical, and Prognostic Criteria.

Multiple myeloma (MM) is a heterogeneous disease, with MM patients experiencing different clinical outcomes depending on the disease's biological features. Novel insights into the molecular mechanisms of MM have led to the introduction of sophisticated drugs, which dramatically improved patient treatment and survival. To date, young patients with newly diagnosed MM could experience a median overall survival (OS) of 10 years. Nevertheless, a small proportion of patients still undergoes early disease progression and death. Indeed, cases defined as ultra-high-risk MM (uHRMM) and high-risk MM (HRMM) are destined for a worse outcome, with an OS of 2-3 and 3-5 years, respectively. In this regard, current risk stratification systems failed to identify this subset of patients better. The application of existing risk models has led to the identification of extremely heterogeneous categories of patients, and they have not taken into account biological and clinical differences. The concept of HRMM was initially formalised in 2015. Since then, a great effort has been made to identify those parameters whose presence pone MM patients at higher risk of developing an early relapse. The simultaneous presence of 2 or more unfavourable cytogenetic abnormalities, the identification of an extramedullary disease or the detection of circulating plasma cells, as well as high-risk gene expression profiling (GEP) signature, have shown to be well related to a worse outcome and are going to be incorporated into new prognostic systems. The introduction of the Individualised Risk Model for Multiple Myeloma (IRMMa) marks a significant advancement in the management of HRMM by integrating genomic and clinical data to tailor treatment strategies. This model demonstrates improved prognostic accuracy compared to traditional staging systems and emphasises the importance of personalised treatment approaches. The implementation of these advanced tools is essential for enhancing precision medicine in MM and improving outcomes for patients in high-risk categories.

Integrating Muscle Depletion with Barcelona Clinic Liver Cancer Staging to Predict Overall Survival in Hepatocellular Carcinoma

Background: Muscle depletion (MD) is a critical factor that influences clinical outcomes in patients with hepatocellular carcinoma (HCC). Although its role in cancer prognosis is recognized, its integration into widely used prognostic systems remains underexplored. This study aimed to evaluate the prognostic impact of MD on overall survival (OS) in HCC patients and to improve existing noninvasive prognostic models by incorporating MD-related metrics. Methods: A retrospective analysis was conducted on 1072 HCC patients treated at Taipei Tzu Chi Hospital between January 2006 and December 2016. All patients had follow-up data and computed tomography (CT) scans at vertebral level L3 for MD evaluation. Independent prognostic factors for OS were identified using Cox proportional hazards models, and the predictive performance of various prognostic models was assessed through the area under the receiver operating characteristic curve (AUROC). Results: The key independent predictors of OS in HCC patients included hepatitis B virus infection, hepatitis C virus infection, liver cirrhosis, tumor size, serum alpha-fetoprotein levels, and MD-related metrics (psoas muscle-to-spine ratio, psoas muscle-to-vertebral ratio, and myosteatosis). Among existing models, the Barcelona Clinic Liver Cancer (BCLC) stage, the Child–Turcotte–Pugh (CTP) class, and the albumin–bilirubin (ALBI) grade demonstrated robust predictive performance for OS. However, incorporating MD significantly improved the predictive accuracy of these models, with the MD–BCLC model showing the highest AUROC (0.804, 95% CI: 0.777–0.832, p &lt; 0.001). Conclusions: MD is an independent and significant prognostic predictor for patients with HCC. Integrating MD metrics into established systems, particularly the BCLC staging system, markedly improves OS prediction, providing a more comprehensive tool for clinical decision-making in the management of HCC.

Analysis and reflections on the current status of diagnosis and treatment of marginal zone lymphoma

The current study aimed to understand the current status and problems of marginal zone lymphoma (MZL) in the diagnosis and treatment of hospitals at all levels in China. A multi-center questionnaire survey was conducted in a number of medical institutions across the country. A combination of online questionnaire survey and face-to-face interview was adopted. (1)Pathologists paid more attention than clinicians to distinguish MALT from chronic inflammation (86.3% vs 32.1%, P<0.01) and plasma cell tumor (51.8% vs 23.1%, P<0.01). A total of 21% pathologists never performed B-cell gene rearrangement, 67.6% of clinicians and 69.0% of pathologists would not recommend splenic puncture to diagnose SMZL.(2)In terms of treatment indications, 40.0% of clinicians mistakenly believed that stage Ⅲ-Ⅳ was also a treatment indication. Seventy percent of clinicians reported confusion about treatment indications. (3) In staging and efficacy evaluation, 63.3% of physicians performed PET-CT testing for patients, mainly for resolving clinical staging (89.0%), identifying histologically transformation (79.6%), and determining the site of radiotherapy or biopsy (66.2%). (4) In terms of treatment choice, only 32.2% of patients with indications were recommended for radiotherapy, and the proportion of hematologists choosing radiotherapy was significantly lower than that of oncologists (42.6% vs 71.7%, P<0.01); In the anti-HP indications, 53.1% of physicians will perform anti-HP therapy regardless of Hp positive or not; For advanced MZL, first-line immunochemotherapy was selected by 62.7% of clinicians, compared with 37.3% for targeted therapy. (5)15.3% of clinicians believed that the current prognostic evaluation system could not guide the selection of treatment options after initial treatment and recurrence. At present, there are still some cognitive deviations in the disease cognition and treatment indication of MZL among clinicians at all levels of hospitals in China. Likewise, there are still many unmet needs in MZL staging, efficacy evaluation, treatment selection and prognosis evaluation.

Machine Learning-based Prognostic Subgrouping of Glioblastoma: A Multi-center Study.

Glioblastoma is the most aggressive adult primary brain cancer, characterized by significant heterogeneity, posing challenges for patient management, treatment planning, and clinical trial stratification. We developed a highly reproducible, personalized prognostication and clinical subgrouping system using machine learning (ML) on routine clinical data, MRI, and molecular measures from 2,838 demographically diverse patients across 22 institutions and 3 continents. Patients were stratified into favorable, intermediate, and poor prognostic subgroups (I, II, III) using Kaplan-Meier analysis (Cox proportional model and hazard ratios [HR]). The ML model stratified patients into distinct prognostic subgroups with HRs between subgroups I-II and I-III of 1.62 (95%CI: 1.43-1.84, p<0.001) and 3.48 (95%CI: 2.94-4.11, p<0.001), respectively. Analysis of imaging features revealed several tumor properties contributing unique prognostic value, supporting the feasibility of a generalizable prognostic classification system in a diverse cohort. Our ML model demonstrates extensive reproducibility and online accessibility, utilizing routine imaging data rather than complex imaging protocols. This platform offers a unique approach for personalized patient management and clinical trial stratification in glioblastoma.

Validation of SAPS 3 for predicting in-hospital mortality in patients with haematological malignancy requiring ICU management

Prognostic systems predicting death risk may vary for patients with haematological malignancies needing ICU care. This study externally validated SAPS 3 using a retrospective cohort of adults with these conditions in the ICU. The score was calculated at admission using the general and South America-adjusted formulas. Mortality discrimination was assessed via AUC-ROC, and calibration by Hosmer-Lemeshow goodness-of-fit and graphical analysis with a calibration belt. The analysis included 273 admissions, with 119 deaths. Discriminative capacity was low (AUC-ROC 0.56, CI 95% 0.49–0.63). There was a poor correlation between expected and observed events across all risk deciles (Hosmer-Lemeshow 10.45, p = 0.0635). Similar results were found with the South America-adjusted formula. SAPS 3 does not effectively discriminate between survivors and non-survivors, underestimating risk in low-risk groups and overestimating it in high-risk groups. Mortality risk estimation in this scenario should rely on clinical judgment.

Advancing cancer diagnosis and prognostication through deep learning mastery in breast, colon, and lung histopathology with ResoMergeNet

Cancer, a global health threat, demands effective diagnostic solutions to combat its impact on public health, particularly for breast, colon, and lung cancers. Early and accurate diagnosis is essential for successful treatment, prompting the rise of Computer-Aided Diagnosis Systems as reliable and cost-effective tools. Histopathology, renowned for its precision in cancer imaging, has become pivotal in the diagnostic landscape of breast, colon, and lung cancers. However, while deep learning models have been widely explored in this domain, they often face challenges in generalizing to diverse clinical settings and in efficiently capturing both local and global feature representations, particularly for multi-class tasks. This underscores the need for models that can reduce biases, improve diagnostic accuracy, and minimize error susceptibility in cancer classification tasks. To this end, we introduce ResoMergeNet (RMN), an advanced deep-learning model designed for both multi-class and binary cancer classification using histopathological images of breast, colon, and lung. ResoMergeNet integrates the Resboost mechanism which enhances feature representation, and the ConvmergeNet mechanism which optimizes feature extraction, leading to improved diagnostic accuracy. Comparative evaluations against state-of-the-art models show ResoMergeNet’s superior performance. Validated on the LC-25000 and BreakHis (400× and 40× magnifications) datasets, ResoMergeNet demonstrates outstanding performance, achieving perfect scores of 100 % in accuracy, sensitivity, precision, and F1 score for binary classification. For multi-class classification with five classes from the LC25000 dataset, it maintains an impressive 99.96 % across all performance metrics. When applied to the BreakHis dataset, ResoMergeNet achieved 99.87 % accuracy, 99.75 % sensitivity, 99.78 % precision, and 99.77 % F1 score at 400× magnification. At 40× magnification, it still delivered robust results with 98.85 % accuracy, sensitivity, precision, and F1 score. These results emphasize the efficacy of ResoMergeNet, marking a substantial advancement in diagnostic and prognostic systems for breast, colon, and lung cancers. ResoMergeNet’s superior diagnostic accuracy can significantly reduce diagnostic errors, minimize human biases, and expedite clinical workflows, making it a valuable tool for enhancing cancer diagnosis and treatment outcomes.

Pretransplant Chromosome Genomic Array Testing Improves Prognosis for Myelofibrosis Patients Undergoing Transplantation.

Despite its known superior diagnostic yield for chromosomal anomalies compared with karyotype and fluorescence in situ hybridization (FISH) studies, chromosome genomic array testing (CGAT) is not used as a routine clinical test for myelofibrosis. Although many prognostic systems exist that risk stratify patients at diagnosis, limited tools are available to prognosticate transplant outcome. The current study aimed at testing whether CGAT results obtained before transplantation improves prognosis of post-transplant outcome in patients with myelofibrosis compared with current risk categorization systems, for example, DIPSS plus (Dynamic International Prognostic Scoring System). We studied patients with myelofibrosis who underwent hematopoietic cell transplantation between 2000 and 2017 at our center (N = 44). We assessed the prognostic significance of CGAT, DIPSS plus, and the total count of gene mutations for post-transplant clinical outcomes, including relapse-free survival (RFS), overall survival (OS), and graft-versus-host-disease (GVHD). Abnormal CGAT results were seen in 24 patients (55%), including 18 with copy-neutral loss of heterozygosity (cnLOH, 41%). With a median follow-up of 91 (range 2-258) months starting from the CGAT sample date, RFS was 59% and OS was 68%. The outcome analysis showed significant prognostic implication from CGAT (normal vs. abnormal), specifically for patients with intermediate risk by DIPSS-plus scores and those with 0∼2 mutations. CGAT alone significantly stratified the patients' RFS outcome (P = .03). The addition of CGAT to DIPSS-plus improved the significance from a P value of .08 to .003, whereas the addition of CGAT to mutation count improved the P value from .02 to .01. The best stratification system for RFS was achieved when CGAT, DIPSS-plus, and mutation count were all considered (P = 1e-08). The current study also confirmed individual anomalies that are prognostically significant, including U2AF1 mutation (n = 5, P = .03) and 1q gain (n = 3, P = .01), which were associated with worse RFS. ASXL1 mutations (n = 14) appeared to associate with a later onset of chronic GVHD (P =.03). Pretransplant CGAT analysis augments the existing risk stratification tools and may be considered as routine clinical testing for myelofibrosis.

Comparison Between AJCC 8th Edition Gastric and Esophageal ypTNM Classification System in Siewert II Esophagogastric Junction Adenocarcinomas: A Retrospective Study Based on Eastern and Western Data

Multimodal therapy has become the standard treatment for curable upper gastrointestinal cancers. However, it remains unclear which 8th edition AJCC post-neoadjuvant therapy pathological classification system, esophageal (ypTNM-EC) or gastric (ypTNM-GC), can predict the overall survival (OS) of patients with Siewert II adenocarcinomas better. Patients diagnosed with Siewert II adenocarcinomas receiving neoadjuvant therapy plus curative resection at the University Medical Center Utrecht (UMC Utrecht) and the Peking University Cancer Hospital (PUCH) between the 2001 and 2022 were included in this study. The patients from two institutions were analyzed separately. Predictive univariable and multivariable Cox models based on ypTNM-EC and ypTNM-GC were constructed. The C-index and calibration curves were used to compare the predictive abilities of ypTNM-EC and ypTNM-GC Cox models. A total of 125 patients from UMCU and 145 from PUCH were included. There was no significant difference in the C-index between the ypTNM-EC and the ypTNM-GC univariable and multivariable Cox models in the UMC Utrecht (p-value=0.883; p-value=0.681) and PUCH (p-value=0.808; p-value=0.548) cohorts, and no significant difference was observed between their calibration curves in the two cohorts. The AJCC 8th edition ypTNM prognostic classification systems for esophageal and gastric cancer demonstrated no difference in predicting OS for patients with Siewert II adenocarcinomas both in the Western and Eastern data. The ypTNM-GC, with fewer stage groups, may offer greater convenience for clinical application.