Explore the vast range of titles available.

Community-acquired pneumonia (CAP) is a significant global health issue, leading to high morbidity and mortality rates. Despite the existence of various severity scoring systems, accurately predicting patient outcomes remains challenging. The CAP-PIRO (Predisposition, Insult, Response, and Organ dysfunction) scoring system offers a comprehensive approach to evaluating CAP severity and prognosis. This study aimed to assess the effectiveness of the CAP-PIRO scoring system in predicting the prognosis and severity of CAP patients, focusing on the development of acute respiratory distress syndrome (ARDS) and 28-day mortality. A total of 875 CAP patients were prospectively enrolled from the emergency department of Beijing Chao-yang Hospital between November 2017 and December 2023. Clinical data, including patient demographics, medical history, vital signs, and laboratory findings, were collected within 6 hours of admission. CAP-PIRO, CURB-65, and PSI scores were calculated. Patients were stratified based on ARDS development, 28-day mortality, and PaO2/FiO2 categories (≤100 mmHg, 100-200 mmHg, 200-300 mmHg). Significant differences were observed in PCT, blood lactate (Lac), CURB-65, PSI, and CAP-PIRO scores between patients with and without ARDS, as well as between survivors and non-survivors at 28 days (P<0.05). CAP-PIRO and Lac were identified as independent predictors for ARDS development and 28-day mortality. The area under the ROC curve (AUC) for CAP-PIRO was higher than that for CURB-65 and PSI in predicting 28-day mortality. The combination of CAP-PIRO and Lac demonstrated improved predictive accuracy for ARDS. Notably, significant differences in CAP-PIRO scores were observed across different PaO2/FiO2 groups. CAP-PIRO demonstrates strong predictive ability for adverse outcomes and, when combined with lactate, shows enhanced predictive power. These findings underscore the value of CAP-PIRO for clinical risk stratification in CAP patients.

Deep learning has been applied to many areas in health care, including imaging diagnosis, digital pathology, prediction of hospital admission, drug design, classification of cancer and stromal cells, doctor assistance, etc. Cancer prognosis is to estimate the fate of cancer, probabilities of cancer recurrence and progression, and to provide survival estimation to the patients. The accuracy of cancer prognosis prediction will greatly benefit clinical management of cancer patients. The improvement of biomedical translational research and the application of advanced statistical analysis and machine learning methods are the driving forces to improve cancer prognosis prediction. Recent years, there is a significant increase of computational power and rapid advancement in the technology of artificial intelligence, particularly in deep learning. In addition, the cost reduction in large scale next-generation sequencing, and the availability of such data through open source databases (e.g., TCGA and GEO databases) offer us opportunities to possibly build more powerful and accurate models to predict cancer prognosis more accurately. In this review, we reviewed the most recent published works that used deep learning to build models for cancer prognosis prediction. Deep learning has been suggested to be a more generic model, requires less data engineering, and achieves more accurate prediction when working with large amounts of data. The application of deep learning in cancer prognosis has been shown to be equivalent or better than current approaches, such as Cox-PH. With the burst of multi-omics data, including genomics data, transcriptomics data and clinical information in cancer studies, we believe that deep learning would potentially improve cancer prognosis.

Background Predicting prognosis in patients from large-scale genomic data is a fundamentally challenging problem in genomic medicine. However, the prognosis still remains poor in many diseases. The poor prognosis may be caused by high complexity of biological systems, where multiple biological components and their hierarchical relationships are involved. Moreover, it is challenging to develop robust computational solutions with high-dimension, low-sample size data. Results In this study, we propose a Pathway-Associated Sparse Deep Neural Network (PASNet) that not only predicts patients’ prognoses but also describes complex biological processes regarding biological pathways for prognosis. PASNet models a multilayered, hierarchical biological system of genes and pathways to predict clinical outcomes by leveraging deep learning. The sparse solution of PASNet provides the capability of model interpretability that most conventional fully-connected neural networks lack. We applied PASNet for long-term survival prediction in Glioblastoma multiforme (GBM), which is a primary brain cancer that shows poor prognostic performance. The predictive performance of PASNet was evaluated with multiple cross-validation experiments. PASNet showed a higher Area Under the Curve (AUC) and F1-score than previous long-term survival prediction classifiers, and the significance of PASNet’s performance was assessed by Wilcoxon signed-rank test. Furthermore, the biological pathways, found in PASNet, were referred to as significant pathways in GBM in previous biology and medicine research. Conclusions PASNet can describe the different biological systems of clinical outcomes for prognostic prediction as well as predicting prognosis more accurately than the current state-of-the-art methods. PASNet is the first pathway-based deep neural network that represents hierarchical representations of genes and pathways and their nonlinear effects, to the best of our knowledge. Additionally, PASNet would be promising due to its flexible model representation and interpretability, embodying the strengths of deep learning. The open-source code of PASNet is available at https://github.com/DataX-JieHao/PASNet .

There is no effective method to predict chemotherapy response and postoperative prognosis of colorectal cancer liver metastasis (CRLM) patients. Patient‐derived organoid (PDO) has become an important preclinical model. Herein, a living biobank with 50 CRLM organoids derived from primary tumors and paired liver metastatic lesions is successfully constructed. CRLM PDOs from the multiomics levels (histopathology, genome, transcriptome and single‐cell sequencing) are comprehensively analyzed and confirmed that this organoid platform for CRLM could capture intra‐ and interpatient heterogeneity. The chemosensitivity data in vitro reveal the potential value of clinical application for PDOs to predict chemotherapy response (FOLFOX or FOLFIRI) and clinical prognosis of CRLM patients. Taken together, CRLM PDOs can be utilized to deliver a potential application for personalized medicine. A living biobank of patient‐derived organoid (PDO) is derived from primary colorectal cancer and paired liver metastatic lesions, which captures intra‐ and interpatient molecular fingerprint heterogeneity. PDO chemosensitivity measured in vitro may be used as a predictive tool for clinical chemotherapeutic efficacy, and guide the formulation of precise treatment strategies for colorectal cancer patients with liver metastases.

Background Localized C3 deposition is a well-known factor of inflammation. However, its role in oncoprogression of gastric cancer (GC) remains obscured. This study aims to explore the prognostic value of C3 deposition and to elucidate the mechanism of C3-related oncoprogression for GC. Methods From August to December 2013, 106 GC patients were prospectively included. The regional expression of C3 and other effectors in gastric tissues were detected by WB, IHC, qRT-PCR and other tests. The correlation of localized C3 deposition and oncologic outcomes was determined by 5-year survival significance. Human GC and normal epithelial cell lines were employed to detect a relationship between C3 and STAT3 signaling pathway in vitro experiments. Results C3 and C3a expression were markedly enhanced in GC tissues at both mRNA and protein levels compared with those in paired nontumorous tissues. According to IHC C3 score, 65 (61.3%) and 41 (38.7%) patients had high and low C3 deposition, respectively. C3 deposition was negatively correlated with plasma levels of C3 and C3a (both P <  0.001) and positively correlated with pathological T and TNM stages (both P <  0.001). High C3 deposition was identified as an independent prognostic factor of poor 5-year overall survival ( P  = 0.045). In vitro C3 administration remarkably enhanced p-JAK2/p-STAT3 expression in GC cell lines but caused a reduction of such activation when pre-incubated with a C3 blocker. Importantly, C3 failed to activate such signaling in cells pre-treated with a JAK2 inhibitor. Conclusions Localized C3 deposition in the tumor microenvironment is a relevant immune signature for predicting prognosis of GC. It may aberrantly activate JAK2/STAT3 pathway allowing oncoprogression. Trial registration ClinicalTrials.gov , NCT02425930, Registered 1st August 2013.

Background N6-methyladenosine (m6A) related long noncoding RNAs (lncRNAs) may have prognostic value in bladder cancer for their key role in tumorigenesis and innate immunity. Methods Bladder cancer transcriptome data and the corresponding clinical data were acquired from the Cancer Genome Atlas (TCGA) database. The m6A-immune-related lncRNAs were identified using univariate Cox regression analysis and Pearson correlation analysis. A risk model was established using least absolute shrinkage and selection operator (LASSO) Cox regression analyses, and analyzed using nomogram, time-dependent receiver operating characteristics (ROC) and Kaplan–Meier survival analysis. The differences in infiltration scores, clinical features, and sensitivity to Talazoparib of various immune cells between low- and high-risk groups were investigated. Results Totally 618 m6A-immune-related lncRNAs and 490 immune-related lncRNAs were identified from TCGA, and 47 lncRNAs of their intersection demonstrated prognostic values. A risk model with 11 lncRNAs was established by Lasso Cox regression, and can predict the prognosis of bladder cancer patients as demonstrated by time-dependent ROC and Kaplan–Meier analysis. Significant correlations were determined between risk score and tumor malignancy or immune cell infiltration. Meanwhile, significant differences were observed in tumor mutation burden and stemness-score between the low-risk group and high-risk group. Moreover, high-risk group patients were more responsive to Talazoparib. Conclusions An m6A-immune-related lncRNA risk model was established in this study, which can be applied to predict prognosis, immune landscape and chemotherapeutic response in bladder cancer.

Background Diagnostic criteria for sarcopenia have not been established in Chinese. This study established criteria based on the L3‐skeletal muscle index (L3‐SMI) and assessed its value for outcomes predicting in cirrhotic Chinese patients. Methods Totally 911 subjects who underwent a CT scan at two centres were enrolled in Cohort 1 (394 male and 417 female subjects, aged 20–80 years). The data of those subjects younger than 60 years (365 male and 296 female subjects) were used to determine the reference intervals of the L3‐SMI and its influencing factors. Cohort 2 consisted of 480 patients (286 male and 184 female patients) from three centres, and their data were used to investigate the prevalence of sarcopenia and evaluate the value of L3‐SMI for predicting the prognosis and complications of cirrhosis. Results Age and sex had the greatest effects on the L3‐SMI (P < 0.001). The L3‐SMI scores were clearly higher in male patients than in female patients (52.94 ± 8.41 vs. 38.91 ± 5.65 cm2/m2, P < 0.001) and sharply declined in subjects aged ≥ 60 years. Based on the mean −1.28 × SD among adults aged < 60 years, the L3‐SMI cut‐off value for sarcopenia was 44.77 cm2/m2 in male patients and 32.50 cm2/m2 in female patients. Using these values, 22.5% of the cirrhotic patients (28.7% of male patients and 11.9% of female patients) were diagnosed with sarcopenia. Compared with non‐sarcopenia individuals, sarcopenia patients had lower body mass index (21.28 ± 3.01 vs. 24.09 ± 3.39 kg/m2, P < 0.001) and serum albumin levels (31.54 ± 5.93 vs. 32.93 ± 5.95 g/L, P = 0.032), longer prothrombin times (16.39 ± 3.05 vs. 15.71 ± 3.20 s, P = 0.049), higher total bilirubin concentrations (41.33 ± 57.38 vs. 32.52 ± 31.48 μmol/L, P = 0.039), worse liver function (Child–Pugh score, 8.05 ± 2.11 vs. 7.32 ± 2.05, P = 0.001), higher prevalence of cirrhosis‐related complications (81.82% vs. 62.24%, P < 0.001) and mortality (30.68% vs. 11.22%, P < 0.001). Overall survival was significantly lower in the sarcopenia group [risk ratio (RR) = 2.643, 95% confidence interval (CI) 1.646–4.244, P < 0.001], accompanied with an increased cumulative incidence of ascites (RR = 1.827, 95% CI 1.259–2.651, P = 0.002), spontaneous bacterial peritonitis (RR = 3.331, 95% CI 1.404–7.903, P = 0.006), hepatic encephalopathy (RR = 1.962, 95% CI 1.070–3.600, P = 0.029), and upper gastrointestinal varices (RR = 2.138, 95% CI 1.319–3.466, P = 0.002). Subgroup analysis showed sarcopenia shortened the survival of the patients with Model For End‐Stage Liver Disease score > 14 (RR = 4.310, 95% CI 2.091–8.882, P < 0.001) or Child–Pugh C (RR = 3.081, 95% CI 1.516–6.260, P = 0.002). Conclusions Sarcopenia is a common comorbidity of cirrhosis and can be used to predict cirrhosis‐related complications and the prognosis.

This study is to identify potential multiomics biomarkers for the early detection of the prognostic recurrence of PC patients. A total of 494 prostate adenocarcinoma (PRAD) patients (60-recurrent included) from the Cancer Genome Atlas (TCGA) portal were analyzed using the autoencoder model and similarity network fusion. Then, multiomics panels were constructed according to the intersected omics biomarkers identified from the two models. Six intersected omics biomarkers, TELO2, ZMYND19, miR-143, miR-378a, cg00687383 (MED4), and cg02318866 (JMJD6; METTL23), were collected for multiomics panel construction. The difference between the Kaplan–Meier curves of high and low recurrence-risk groups generated from the multiomics panel achieved p-value = 5.33 × 10−9, which is better than the former study (p-value = 5 × 10−7). Additionally, when evaluating the selected multiomics biomarkers with clinical information (Gleason score, age, and cancer stage), a high-performance prediction model was generated with C-index = 0.713, p-value = 2.97 × 10−15, and AUC = 0.789. The risk score generated from the selected multiomics biomarkers worked as an effective indicator for the prediction of PRAD recurrence. This study helps us to understand the etiology and pathways of PRAD and further benefits both patients and physicians with potential prognostic biomarkers when making clinical decisions after surgical treatment.