Predictor Of Progression-free Survival Research Articles

Peritumoral Adipose Tissue Features Derived from [18F]fluoro-2-deoxy-2-d-glucose Positron Emission Tomography/Computed Tomography as Predictors for Response to Neoadjuvant Chemotherapy in Breast Cancer Patients.

This study investigated whether the textural features of peritumoral adipose tissue (AT) on [18F]fluoro-2-deoxy-2-d-glucose (FDG) positron emission tomography/computed tomography (PET/CT) can predict the pathological response to neoadjuvant chemotherapy (NAC) and progression-free survival (PFS) in breast cancer patients. We retrospectively enrolled 147 female breast cancer patients who underwent staging FDG PET/CT and completed NAC and underwent curative surgery. We extracted 10 first-order features, 6 gray-level co-occurrence matrix (GLCM) features, and 3 neighborhood gray-level difference matrix (NGLDM) features of peritumoral AT and evaluated the predictive value of those imaging features for pathological complete response (pCR) and PFS. The results of our study demonstrated that GLCM homogeneity showed the highest predictability for pCR among the peritumoral AT imaging features in the receiver operating characteristic curve analysis. In multivariate logistic regression analysis, the mean standardized uptake value (SUV), 50th percentile SUV, 75th percentile SUV, SUV histogram entropy, GLCM entropy, and GLCM homogeneity of the peritumoral AT were independent predictors for pCR. In multivariate survival analysis, SUV histogram entropy and GLCM correlation of peritumoral AT were independent predictors of PFS. Textural features of peritumoral AT on FDG PET/CT could be potential imaging biomarkers for predicting the response to NAC and disease progression in breast cancer patients.

A Single Institution Experience in the Management of Localized Neuroendocrine Carcinoma of the Bladder

BackgroundNeuroendocrine carcinoma of the bladder (NEC-bladder) is a rare disease with poor outcomes and variable treatment approaches. Materials and MethodsPatients with localized NEC-bladder treated with surgery or radiation between 2001-2021 were retrospectively identified. Rates of pathologic complete response (pCR) and downstaging were evaluated following NAC in surgically-treated patients. Progression-free survival (PFS) and overall survival (OS) were analyzed with univariable (log-rank) and multivariable (MVA; Cox regression) methods. ResultsSixty-five patients were identified having a median age of 73. The tumor histology distribution was small cell (64.6%) or urothelial with NE differentiation (35.4%). Most patients (69.2%) received NAC. Patients received local therapy by surgery (78.5%) or chemoradiation (21.5%). The majority (62.7%) of surgical patients had ≥ pT2 with 37.3% having nodal involvement (pN+). The pCR and downstaging rates were 21.6% and 35.1%, respectively. At a median follow-up of 60 months (m), the median PFS and OS were 16.4m and 25.9m, respectively. NAC improved PFS (p=0.04) and downstaging improved PFS (p=0.012) and OS (p<0.001). Patients receiving NAC with ypN0 vs. ypN+ had median OS of 69.9m vs 15.3m, respectively (p<0.001). MVA identified receipt of NAC and pN as predictors of PFS; pN was predictive of OS. No differences in PFS or OS were seen between histology of primary tumor. The brain metastasis rate was 10.8% with all patients having small cell histology. ConclusionsOptimized therapy in NEC-bladder includes NAC followed by local consolidation. Ascertainment of ypN0 is associated with long term survival, while pN+ remains associated with poor outcomes.

Sintilimab (anti-PD-1 antibody) combined with high-dose methotrexate, temozolomide, and rituximab (anti-CD20 antibody) in primary central nervous system lymphoma: a phase 2 study

Primary central nervous system lymphoma (PCNSL) is a rare and frequently fatal lymphoma subtype. The programmed death-1 (PD-1) pathway has emerged as a potential therapeutic target, but the effectiveness of PD-1 antibody sintilimab in combination with immunochemotherapy as a frontline treatment for PCNSL remains to be determined. In this phase 2 trial (ChiCTR1900027433) with a safety run-in, we included patients aged 18–70 with newly diagnosed PCNSL. Participants underwent six 21-day cycles of a SMTR regimen, which includes sintilimab (200 mg, Day 0), rituximab (375 mg/m2, Day 0), methotrexate (3.0 g/m2, Day 1 or 1.0 g/m2 for patients aged ≥65 years), and temozolomide (150 mg/m2/d, Days 1–5). Among 27 evaluable patients, the overall response rate (ORR) was 96.3% (95% confidence interval: 81–99.9%), with 25 complete responses. At a median follow-up of 24.4 months, the medians for duration of response, progression-free survival (PFS), and overall survival were not reached. The most common grade 3–4 treatment-related toxicities were increased levels of alanine aminotransferase (17.9%) and aspartate aminotransferase (14.3%). Additionally, baseline levels of interferon-α and the IL10/IL6 ratio in cerebrospinal fluid emerged as potential predictors of PFS, achieving areas under the curve of 0.88 and 0.84, respectively, at 2 years. Whole-exome sequencing revealed a higher prevalence of RTK-RAS and PI3K pathway mutations in the durable clinical benefit group, while a greater frequency of Notch and Hippo pathway mutations in the no durable benefit group. These findings suggest the SMTR regimen is highly efficacious and tolerable for newly diagnosed PCNSL, warranting further investigation.

1449P Recurrent patient-reported outcome (PRO)-based symptomatic deterioration predicts progression-free survival (PFS): Results from RATIONALE-305

1449P Recurrent patient-reported outcome (PRO)-based symptomatic deterioration predicts progression-free survival (PFS): Results from RATIONALE-305

Can serum tumor marker densities according to tumor volume and testicle size be used to predict progression in patients with testicular cancer?

The objective of this study is to determine the role of tumor marker density (TMD) values such as alpha-fetoprotein tumor volume ratio (ATVR), beta-human chorionic gonadotropin tumor volume ratio (βTVR), alpha-fetoprotein testicle size ratio (ATSR), beta-human chorionic gonadotropin testicle size ratio (βTSR), lactate dehydrogenase tumor volume ratio (LTVR), and lactate dehydrogenase testicle size ratio (LTSR) in the determination of progression-free survival (PFS) in patients with testicular cancer. A retrospective study was conducted of 95 patients followed-up in our clinic with a diagnosis of testicular cancer between January 2015 and August 2022. Patients were grouped according to clinical stage, as either early stage (n = 50) or advanced stage (n = 45). Clinical and pathological data and TMD values for all patients were recorded. The median age of patients was 35 years (21-63 years). All TMDs except LTVR in advanced stage patients were found to be significantly higher than those of early stage patients (p < 0.05). Median ATVR (2.58 vs. 0.0), ATSR (0.63 vs. 0.03), βTVR (0.9 vs. 0.009), and βTSR (0.18 vs. 0.007) of the nonseminoma patients were found to be significantly higher than those of the seminoma patients, respectively (p < 0.001). Progression-free survival (months) was decreased in seminoma patients with high values of βTVR (11.3 ± 1.9 vs. 35.2 ± 0.7), βTSR (16.2 ± 3.4 vs. 35.2 ± 0.75), LTVR (17.7 ± 3.4 vs. 35.2 ± 0.7), and LTSR (21.5 ± 3.13 vs. 35.09 ± 0.8) (p < 0.001). Decreased PFS (months) was associated with higher values of ATVR (5.37 ± 0.7 vs. 35.05 ± 0.93), βTVR (7.4 ± 1.5 vs. 34.6 ± 1.3), ATSR (5.37 ± 0.75 vs. 35.05 ± 0.9), βTSR (7 ± 1.5 vs. 34.6 ± 1.3), and LTSR (7.9 ± 1.2 vs. 34.3 ± 1.5) in nonseminoma patients (p < 0.001). Based on multivariate analysis, βTVR-LTVR and ATVR-ATSR were determined to be independent risk factors for reduced PFS in seminoma and nonseminoma patients, respectively (p < 0.05). The results of this study suggest that the calculation of TMDs could be a promising and simple method for prediction of PFS among testicular cancer patients.

Potential of Nutritional Markers as Predictors After Immunotherapy in Advanced Head and Neck Squamous Cell Carcinoma.

Immune checkpoint inhibitors (ICIs) are the standard treatment for advanced head and neck squamous cell carcinoma (HNSCC). Programmed death-ligand 1 (PD-L1) is clinically assessed before initiating ICIs; however, there are no established biomarkers for predicting the response to immunotherapy. In this study, inflammatory and nutritional parameters were examined to determine the therapeutic outcomes of ICIs for HNSCC. Sixty-five patients with metastatic or recurrent HNSCC who received programmed death-1 (PD-1) blockade were enrolled. Inflammatory and nutritional indices were correlated with patient outcomes, including the neutrophil-to-lymphocyte ratio (NLR), platelet-to-lymphocyte ratio (PLR), systemic immune-inflammation index (SII), and prognostic nutritional index (PNI). Patients aged <70 years were significantly associated with a high NLR, whereas those with a performance status of 2 or 3 were closely related to a high NLR, high SII, and low PNI. Although all patients achieved an objective response rate of 24.6% and a disease control rate of 36.9%, the NLR, PLR, SII, and PNI values were not significantly different between responders and non-responders. Univariate analysis showed that the NLR, PLR, SII, and PNI were significant predictors of progression-free survival (PFS) and overall survival (OS). Multivariate analysis identified PNI as an independent predictor of PFS and OS. PNI, as a nutritional marker, was identified as a significant predictor of outcomes following PD-1 blockade administration in patients with advanced HNSCC, compared to inflammatory markers, such as NLR, PLR, and SII.

Effect of Chemoradiotherapy on Locoregional Recurrence After Pancreatectomy for Pancreatic Cancer.

The study aimed to investigate the efficacy of radiotherapy or chemoradiotherapy for isolated locoregional recurrence after pancreatectomy for pancreatic cancer. Twenty-eight patients who had isolated locoregional recurrence after pancreatectomy for pancreatic cancer between 2007 and 2021 were retrospectively analyzed. We investigated the effect of the treatment method [radiotherapy or chemoradiotherapy (radiotherapy with concurrent chemotherapy)] on progression-free survival (PFS) and post-recurrence survival (PRS). The median disease-free survival was 16.1 months (range=4.7-47.1 months). Five patients received radiotherapy and 21 patients received chemoradiotherapy [radiotherapy concurrent with gemcitabine (GEM) or S-1] for locoregional recurrence. All patients except one patient with interstitial pneumonia were treated with salvage chemotherapy after irradiation. The median PFS rates of the radiotherapy group and the chemoradiotherapy group were 2.8 months (range=1.5-5.4 months) and 16.8 months (range=2.7-42.8 months), respectively. The median PRS rates were 23.7 months (range=8.1-26.4 months) for the radiotherapy group and 26.2 months (range=6.0-64.7 months) for the chemoradiotherapy group. Multivariate analysis identified radiotherapy [hazard ratio (HR)=12.2, 95% confidence interval (CI)=3.29-45.6, p<0.001] and serum DUPAN-2 >150 U/ml (HR=2.90, 95%CI=1.22-6.93, p=0.02) as independent predictors of PFS, and UICC TNM Stage ≥III (HR=3.23, 95%CI=1.17-8.96, p=0.02) and modified Glasgow prognostic score before the treatment for the recurrence 1 or 2 (HR=3.05, 95%CI=1.15-8.08, p=0.03) as independent predictors of PRS. Chemoradiotherapy for isolated locoregional recurrence after pancreatectomy for pancreatic cancer could suppress re-recurrence more effectively than radiotherapy.

Oncogenic pathway signatures predict the risk of progression and recurrence in well-differentiated pancreatic neuroendocrine tumors.

Pancreatic neuroendocrine tumors (pNETs) are genomically diverse tumors. The management of newly diagnosed well-differentiated pNETs is limited by a lack of sensitivity of existing biomarkers for prognostication. Our goal was to investigate the potential utility of genetic markers as a predictor of progression-free survival (PFS) and recurrence-free survival (RFS). Whole-exome sequencing of resected well-differentiated, low and intermediate-grade (G1 and G2) pNETs and normal adjacent tissue from patients who underwent resection from 2005 to 2015 was performed. Genetic alterations were classified using pan-genomic and oncogenic pathway classifications. Additional samples with genetic and clinicopathologic data available were obtained from the publicly available International Cancer Genome Consortium (ICGC) database and included in the analysis. The prognostic relevance of these genomic signatures on PFS and RFS was analyzed. Thirty-one patients who underwent resection for pNET were identified. Genomic analysis of mutational, copy number, cytogenetic, and complex phenomena revealed similar patterns to prior studies of pNETs with relatively few somatic gene mutations but numerous instances of copy number changes. Analysis of genomic and clinicopathologic outcomes using the combined data from our study as well as the ICGC pNET cohort (n = 124 patients) revealed that the recurrent pattern of whole chromosome loss (RPCL) and metastatic disease were independently associated with disease progression. When evaluating patients with local disease at the time of resection, RPCL and alterations in the TGFβ oncogenic pathway were independently associated with the risk of recurrence. Well-differentiated pNETs are genomically diverse tumors. Pathway signatures may be prognostic for predicting disease progression and recurrence.

Lachnoclostridium intestinal flora is associated with immunotherapy efficacy in nasopharyngeal carcinoma.

Effective biomarkers for assessing anti-PD-1/PD-L1 therapy efficacy in patients with nasopharyngeal carcinoma (NPC) are still lacking. The human gut microbiota has been shown to influence clinical response to anti-PD-1/PD-L1 therapy in many cancers. However, the relationship between the gut microbiota and the efficacy of immunotherapy in patients with nasopharyngeal carcinoma has not been determined. We conducted a prospective study in which fecal and blood samples from patients with NPC were subjected to 16S rDNA sequencing and survival analysis. To investigate potential differences in the gut microbiome between these groups and to identify potential biomarkers indicative of immunotherapy efficacy, patients were categorized into two groups according to their clinical response to immunotherapy, the responder group (R group) and the non-responder group (NR group). Progression-free survival (PFS) between these subgroups was analyzed using Kaplan-Meier survival analysis with the log-rank test. Additionally, we performed univariate and multivariate analyses to evaluate prognostic factors. Finally, we carried out non-targeted metabolomics to examine the metabolic effects associated with the identified microbiome. Our 16S rDNA sequencing results showed that the abundance of Lachnoclostridium was higher in the NR group than in the R group (p = 0.003), and alpha diversity analysis showed that the abundance of microbiota in the NR group was higher than that in the R group (p = 0.050). Patients with a lower abundance of Lachnoclostridium had better PFS (p = 0.048). Univariate (p = 0.017) and multivariate analysis (p = 0.040) showed that Lachnoclostridium was a predictor of PFS. Non-targeted metabolomics analysis revealed that Lachnoclostridium affects the efficacy of immunotherapy through the usnic acid. High abundance of Lachnoclostridium predicts poor prognosis in patients with NPC receiving immunotherapy.

Delta magnetic resonance imaging radiomics features‑based nomogram predicts long‑term efficacy after induction chemotherapy in locoregionally advanced nasopharyngeal carcinoma

PurposeTo establish and validate a delta-radiomics-based model for predicting progression-free survival (PFS) in patients with locoregionally advanced nasopharyngeal carcinoma (LA-NPC) following induction chemotherapy (IC). Methods and MaterialsA total of 250 LA-NPC patients (training cohort: n = 145; validation cohort: n = 105) were enrolled. Radiomic features were extracted from MRI scans taken before and after IC, and changes in these features were calculated. Following feature selection, a delta-radiomics signature was constructed using LASSO-Cox regression analysis. A prognostic nomogram incorporating independent clinical indicators and the delta-radiomics signature was developed and assessed for calibration and discrimination. Risk stratification by the nomogram was evaluated using Kaplan-Meier methods. ResultsThe delta-radiomics signature, consisting of 12 features, was independently associated with prognosis. The nomogram, integrating the delta-radiomics signature and clinical factors demonstrated excellent calibration and discrimination. The model achieved a Harrell’s concordance index (C-index) of 0.848 in the training cohort and 0.820 in the validation cohort. Risk stratification identified two groups with significantly different PFS rates. The three-year PFS for high-risk patients who received concurrent chemoradiotherapy (CCRT) or radiotherapy plus adjuvant chemotherapy (RT+AC) after IC was significantly higher than for those who received RT alone, reaching statistical significance. In contrast, for low-risk patients, the three-year PFS after IC was slightly higher for those who received CCRT or RT+AC compared to those who received RT alone; however, this difference did not reach statistical significance. ConclusionsOur delta MRI-based radiomics model could be useful for predicting PFS and may guide subsequent treatment decisions after IC in LA-NPC.

Retrospective evaluation of the predictive value of tumour burden at baseline [68 Ga]Ga-DOTA-TOC or -TATE PET/CT and tumour dosimetry in GEP-NET patients treated with PRRT

PurposeThere is a lack of validated imaging biomarkers for prediction of response to peptide receptor radionuclide therapy (PRRT). The primary objective was to evaluate if tumour burden at baseline PET/CT could predict treatment outcomes to PRRT with [177Lu]Lu-DOTA-TATE. Secondary objectives were to evaluate if there was a correlation between tumour burden and mean tumour absorbed dose (AD) during first cycle, and if mean tumour AD or the relative change of tumour burden at first follow-up PET/CT could predict progression free survival (PFS) or overall survival (OS).MethodsPatients with gastroenteropancreatic neuroendocrine tumour (GEP-NET) treated with [177Lu]Lu-DOTA-TATE PRRT were retrospectively included. Tumour burden was quantified from [68 Ga]Ga-DOTA-TOC/TATE PET/CT-images at baseline and first follow-up and expressed as; whole-body somatostatin receptor expressing tumour volume (SRETVwb), total lesion somatostatin receptor expression (TLSREwb), largest tumour lesion diameter and highest SUVmax. The relative change of tumour burden was evaluated in three categories. Mean tumour AD was estimated from the first cycle of PRRT. PFS was defined as time from start of PRRT to radiological or clinical progression. OS was evaluated as time to death. Kaplan Meier survival curves and log-rank test were used to compare PFS and OS between different groups.ResultsThirty-one patients had a baseline PET/CT < 6 months before treatment and 25 had a follow-up examination. Median tumour burden was 132 ml (IQR 61–302) at baseline and 71 ml (IQR 36–278) at follow-up. Twenty-two patients had disease progression (median time to progression 17.2 months) and 9 patients had no disease progression (median follow-up 28.7 months). SRETVwb dichotomized by the median at baseline was not associated with longer PFS (p = 0.861) or OS (p = 0.937). Neither TLSREwb, largest tumour lesion or SUVmax showed significant predictive value. There was a moderately strong correlation, however, between SUVmax and mean tumour AD r = 0.705, p < 0.001, but no significant correlation between SRETVwb nor TLSREwb and mean tumour AD. An increase of SRETVwb, TLSREwb or largest tumour lesion at first follow-up PET/CT was significantly correlated with shorter PFS/OS.ConclusionTumour burden at baseline showed no predictive value of PFS/OS after PRRT in this small retrospective study. An increase of tumour burden was predictive of worse outcome.

Confirming the efficacy and safety of CDK4/6 inhibitors in the first-line treatment of HR+ advanced breast cancer: a systematic review and meta-analysis.

Objective: Cyclin-dependent kinase (CDK) 4 and 6 inhibitors (abemaciclib, palbociclib and ribociclib) have been recommended in the first-line treatment of hormone receptor-positive (HR+) breast cancer in China. Our study aims to evaluate the efficacy and safety of CDK4/6 inhibitors by processing survival data using fractional polynomial modeling methods. Methods: Phase II or III randomized controlled trials in treatment-naive HR + patients with advanced breast cancer were systematically searched through the preset search strategy. The fractional polynomial (FP) model was used to relax the proportional hazard assumption and obtain time-varying hazard ratio (HR). Progression-free life years (PFLYs) and life years (LYs) were calculated from the area under curve (AUC) of the predicted progression-free survival (PFS) and overall survival (OS) curves to evaluate the long-term efficacy benefit. Odds ratio (OR) of grade≥3 adverse events were analyzed for safety outcomes. Results: 6 randomized controlled trials with 2,638 patients were included. The first-order FP model (p = -1) and the first-order FP model (p = 1) were used to calculate the time-varying HR of PFS and OS, respectively. Extrapolating to 240 months, abemaciclib obtained a PFS benefit of 3.059 PFLYs and 6.275 LYs by calculating the AUC of the PFS and OS curves. Palbociclib obtained 2.302 PFLYs and 6.351 LYs. Ribociclib obtained 2.636 PFLYs and 6.543 LYs. In terms of safety, the use of CDK4/6 inhibitors resulted in a higher risk of adverse events (OR = 9.84, 95% CI: 8.13-11.95), especially for palbociclib (OR = 14.04, 95% CI: 10.52-18.90). Conclusion: The use of CDK4/6 inhibitors in treatment-naive patients with HR + advanced breast cancer significantly improves survival, but also increases the risk of adverse events. Abemaciclib and ribociclib may be the best options for prolonging PFS and OS in treatment-naïve patients, respectively.

Volumetric and textural analysis of PET/CT in patients with diffuse large B-cell lymphoma highlights the importance of novel MTVrate feature.

To investigate the prognostic value of clinical, volumetric, and radiomics-based textural parameters in baseline [18F]FDG-PET/CT scans of diffuse large B-cell lymphoma (DLBCL) patients. We retrospectively investigated baseline PET/CT scans and collected clinical data of fifty DLBCL patients. PET images were segmented semiautomatically to determine metabolic tumor volume (MTV), then the largest segmented lymphoma volume of interest (VOI) was used to extract first-, second-, and high-order textural features. A novel value, MTVrate was introduced as the quotient of the largest lesion's volume and total body MTV. Receiver operating characteristics (ROC) analyses were performed and 24-months progression-free survival (PFS) of low- and high-risk cohorts were compared by log-rank analyses. A machine learning algorithm was used to build a prognostic model from the available clinical, volumetric, and textural data based on logistic regression. The area-under-the-curve (AUC) on ROC analysis was the highest of MTVrate at 0.74, followed by lactate-dehydrogenase, MTV, and skewness, with AUCs of 0.68, 0.63, and 0.55, respectively which parameters were also able to differentiate the PFS. A combined survival analysis including MTV and MTVrate identified a subgroup with particularly low PFS at 38%. In the machine learning-based model had an AUC of 0.83 and the highest relative importance was attributed to three textural features and both MTV and MTVrate as important predictors of PFS. Individual evaluation of different biomarkers yielded only limited prognostic data, whereas a machine learning-based combined analysis had higher effectivity. MTVrate had the highest prognostic ability on individual analysis and, combined with MTV, it identified a patient group with particularly poor prognosis.

Untapping the Prognostic Value of Patient-Generated Health Data in Locally Advanced Non-small Cell Lung Cancer

BackgroundPatient-generated health data (PGHD), which includes patient-reported outcomes (PROs) and wearable device data, may have prognostic value for cancer patients. We tested that hypothesis using data from several prospective trials where patients with locally advanced non-small cell lung cancer (LA-NSCLC) were treated with definitive chemoradiotherapy. MethodsCox proportional hazards models were utilized to identify the baseline patient-reported symptom that best predicted progression-free survival (PFS) duration in a trial that involved PRO-CTCAE collection (Cohort 1). Using data from trials that included EORTC QLQ-C30 questionnaires and wearable devices (Cohort 2), the same symptom was tested as a predictor of PFS. Baseline physical inactivity was also tested as a predictor of PFS. A simple risk stratification tool utilizing PROs and physical activity was proposed. ResultsIn Cohort 1 (n = 50), anorexia was the only pretreatment PRO that was significantly associated with PFS after Bonferroni correction (HR = 3.94, P = .002). In Cohort 2 (n = 58), baseline anorexia was also significantly associated with PFS (HR = 2.48, P = .018), as was physical inactivity (HR = 3.11, P < .001). Median PFS duration for patients in Cohort 2 with anorexia or physical inactivity was 6 months, compared to 18 months for other patients (HR = 3.08, P < .001). Median overall survival duration for patients with anorexia or physical inactivity was 19 months, compared to 65 months for other patients (HR = 2.44, P = .021). ConclusionPGHD, including PROs and wearable device data, can provide valuable prognostic information for LA-NSCLC patients treated with definitive chemoradiotherapy. These findings should be validated using larger datasets.

Machine learning-derived prognostic signature for progression-free survival in non-metastatic nasopharyngeal carcinoma.

Early detection of high-risk nasopharyngeal carcinoma (NPC) recurrence is essential. We created a machine learning-derived prognostic signature (MLDPS) by combining three machine learning (ML) models to predict progression-free survival (PFS) in patients with non-metastatic NPC. A cohort of 653 patients with non-metastatic NPC was divided into a training (n = 457) and validation (n = 196) dataset (7:3 ratio). The study included clinicopathological characteristics, hematologic markers, and MRI findings in three machine learning models-random forest (RF), extreme gradient boosting (XGBoost), and least absolute shrinkage and selection operator (LASSO)-to predict progression-free survival (PFS). A Venn diagram identified the overlapping signatures from the three ML algorithms. Cox proportional hazard analysis determined the MLDPS for PFS. The RF, XGBoost, and LASSO algorithms identified six consensus factors from the 33 signatures. Cox proportional hazards analysis showed that the MLDPS includes age, lymphocyte count, number of positive lymph nodes, and regional lymph node density. Additionally, MLDPS effectively stratified prognosis, with low-risk individuals showing better PFS than high-risk individuals (p < 0.001). MLDPS, based on clinicopathological characteristics, hematologic markers, and MRI findings, is crucial for guiding clinical management and personalizing treatments for patients with non-metastatic NPC.

Predict progression free survival and overall survival using objective response rate for anti—PD1/PDL1 therapy development

In oncology anti—PD1 / PDL1 therapy development for solid tumors, objective response rate (ORR) is commonly used clinical endpoint for early phase study decision making, while progression free survival (PFS) and overall survival (OS) are widely used for late phase study decision making. Developing predictive models to late phase outcomes such as median PFS (mPFS) and median OS (mOS) based on early phase clinical outcome ORR could inform late phase study design optimization and probability of success (POS) evaluation. In existing literature, there are ORR / mPFS / mOS association and surrogacy investigations with limited number of included clinical trials. In this paper, without establishing surrogacy, we attempt to predict late phase survival (mPFS and mOS) based on early efficacy ORR and optimize late phase trial design for anti—PD1 / PDL1 therapy development. In order to include adequate number of eligible clinical trials, we built a comprehensive quantitative clinical trial landscape database (QLD) by combining information from different sources such as clinicaltrial.gov, publications, company press releases for relevant indications and therapies. We developed a generalizable algorithm to systematically extract structured data for scientific accuracy and completeness. Finally, more than 150 late phase clinical trials were identified for ORR / mPFS (ORR / mOS) predictive model development while existing literature included at most 50 trials. A tree-based machine learning regression model has been derived to account for ORR / mPFS (ORR / mOS) relationship heterogeneity across tumor type, stage, line of therapy, treatment class and borrow strength simultaneously when homogeneity persists. The proposed method ensures that the predictive model is robust and have explicit structure for clinical interpretation. Through cross validation, the average predictive mean square error of the proposed model is competitive to random forest and extreme gradient boosting methods and outperforms commonly used additive or interaction linear regression models. An example application of the proposed ORR / mPFS (ORR / mOS) predictive model on late phase trial POS evaluation for anti—PD1 / PDL1 combination therapy was illustrated.

Prognostic Role of Pre- and Post-Treatment [18F]FDG PET/CT in Squamous Cell Carcinoma of the Oropharynx in Patients Treated with Chemotherapy and Radiotherapy.

The prognostic role of imaging with [18F]fluorodeoxyglucose ([18F]FDG) positron emission tomography/computed tomography (PET/CT) in oropharynx cancer (OPC) has been demonstrated in the past. The aim of this study was to assess the prognostic impact of both baseline and post-treatment PET/CT in patients with OPC and treated with chemo- and/or radiotherapy. The PET/CT parameters of scans performed before and after therapy were collected and analyzed to find significant prognosticators for progression-free survival (PFS) and overall survival (OS). Human papillomavirus (HPV) infection's influence on the prognosis was also taken into account. A total of 66 patients were included in the study. The staging volumetric parameters of PET/CT were significant prognosticators for OS, while the same parameters were affordable predictors for PFS at the restaging evaluation. No significant correlations between HPV infection and PET/CT parameters were reported. The prognostic role of volumetric [18F]FDG PET/CT parameters in patients with OPC was reported.

Joint AI-driven event prediction and longitudinal modeling in newly diagnosed and relapsed multiple myeloma

Multiple myeloma management requires a balance between maximizing survival, minimizing adverse events to therapy, and monitoring disease progression. While previous work has proposed data-driven models for individual tasks, these approaches fail to provide a holistic view of a patient’s disease state, limiting their utility to assist physician decision-making. To address this limitation, we developed a transformer-based machine learning model that jointly (1) predicts progression-free survival (PFS), overall survival (OS), and adverse events (AE), (2) forecasts key disease biomarkers, and (3) assesses the effect of different treatment strategies, e.g., ixazomib, lenalidomide, dexamethasone (IRd) vs lenalidomide, dexamethasone (Rd). Using TOURMALINE trial data, we trained and internally validated our model on newly diagnosed myeloma patients (N = 703) and externally validated it on relapsed and refractory myeloma patients (N = 720). Our model achieved superior performance to a risk model based on the multiple myeloma international staging system (ISS) (p < 0.001, Bonferroni corrected) and comparable performance to survival models trained separately on each task, but unable to forecast biomarkers. Our approach outperformed state-of-the-art deep learning models, tailored towards forecasting, on predicting key disease biomarkers (p < 0.001, Bonferroni corrected). Finally, leveraging our model’s capacity to estimate individual-level treatment effects, we found that patients with IgA kappa myeloma appear to benefit the most from IRd. Our study suggests that a holistic assessment of a patient’s myeloma course is possible, potentially serving as the foundation for a personalized decision support system.

Metabolic tumour area: a novel prognostic indicator based on 18F-FDG PET/CT in patients with diffuse large B-cell lymphoma in the R-CHOP era

BackgroundThe metabolic tumour area (MTA) was found to be a promising predictor of prostate cancer. However, the role of MTA based on 18F-FDG PET/CT in diffuse large B-cell lymphoma (DLBCL) prognosis remains unclear. This study aimed to elucidate the prognostic significance of MTA and evaluate its incremental value to the National Comprehensive Cancer Network International Prognostic Index (NCCN-IPI) for DLBCL patients treated with first-line R-CHOP regimens.MethodsA total of 280 consecutive patients with newly diagnosed DLBCL and baseline 18F-FDG PET/CT data were retrospectively evaluated. Lesions were delineated via a semiautomated segmentation method based on a 41% SUVmax threshold to estimate semiquantitative metabolic parameters such as total metabolic tumour volume (TMTV) and MTA. Receiver operating characteristic (ROC) curve analysis was used to determine the optimal cut-off values. Progression-free survival (PFS) and overall survival (OS) were the endpoints that were used to evaluate the prognosis. PFS and OS were estimated via Kaplan‒Meier curves and compared via the log-rank test.ResultsUnivariate analysis revealed that patients with high MTA, high TMTV and NCCN-IPI ≥ 4 were associated with inferior PFS and OS (P < 0.0001 for all). Multivariate analysis indicated that MTA remained an independent predictor of PFS and OS [hazard ratio (HR), 2.506; 95% confidence interval (CI), 1.337–4.696; P = 0.004; and HR, 1.823; 95% CI, 1.005–3.310; P = 0.048], whereas TMTV was not. Further analysis using the NCCN-IPI model as a covariate revealed that MTA and NCCN-IPI were still independent predictors of PFS (HR, 2.617; 95% CI, 1.494–4.586; P = 0.001; and HR, 2.633; 95% CI, 1.650–4.203; P < 0.0001) and OS (HR, 2.021; 95% CI, 1.201–3.401; P = 0.008; and HR, 3.869; 95% CI, 1.959–7.640; P < 0.0001; respectively). Furthermore, MTA was used to separate patients with high NCCN-IPI risk scores into two groups with significantly different outcomes.ConclusionsPre-treatment MTA based on 18F-FDG PET/CT and NCCN-IPI were independent predictor of PFS and OS in DLBCL patients treated with R-CHOP. MTA has additional predictive value for the prognosis of patients with DLBCL, especially in high-risk patients with NCCN-IPI ≥ 4. In addition, the combination of MTA and NCCN-IPI may be helpful in further improving risk stratification and guiding individualised treatment options.Trial registrationThis research was retrospectively registered with the Ethics Committee of the Third Affiliated Hospital of Soochow University, and the registration number was approval No. 155 (approved date: 31 May 2022).

Fasting Blood Glucose-Based Novel Predictors in Detecting Metastases and Predicting Prognosis for Patients with PNENs.

To explore three novel fasting blood glucose (FBG)-based novel indicators, including the FBG-to-albumin ratio (FAR), FBG-to-lymphocytes ratio (FLR), and FBG-to-hemoglobin ratio (FHR), in predicting prognosis and detecting metastasis for patients with pancreatic neuroendocrine neoplasms (pNENs) after resection. A total of 178 pNENs patients who underwent surgical resection were included in this study. Receiver operating characteristic (ROC) curves were used to evaluate the diagnosis values of FAR, FLR, and FHR, and the cutoff values were obtained for further analyses. Univariate and multivariate analyses were conducted to determine the independent predictors. The Kaplan-Meier method was used to evaluate the progression-free survival (PFS) and overall survival (OS) of the pNENs patients. The optimal cutoff values of FAR, FLR, and FHR were 0.17, 2.85, and 0.028, respectively. As for PFS, the area under the curve (AUC) was 0.693 for FAR, 0.690 for FLR, and 0.661 for FHR, respectively. The AUC was 0.770, 0.692, and 0.715 accordingly for OS. The groups with lower FAR, FLR, and FHR were significantly associated with prolonged PFS and OS (p < 0.05). In patients with metastasis, the lower FAR group was correlated with significantly longer PFS and OS (p = 0.022 and 0.002, respectively). The FLR was an independent predictor of PFS in pNENs patients, and the FAR was a predictor of OS. FAR was an independent indicator of PFS in patients with metastasis. Preoperative FAR, FLR, and FHR are effective in predicting the prognosis of pNEN patients and detecting the synchronous metastases.