Inflammation-scores as prognostic markers of overall survival in lung cancer: a register-based study of 6,210 Danish lung cancer patients

Machine learning-based prediction of 5-year survival in elderly NSCLC patients using oxidative stress markers

Background

Oxidative stress plays a significant role in aging and cancer, yet there is currently a lack of research utilizing machine learning models to examine the relationship between oxidative stress and prognosis in elderly non-small cell lung cancer (NSCLC) patients.

Methods

This study included elderly NSCLC patients who underwent radical lung cancer resection from January 2012 to April 2018, exploring the relationship between Oxidative Stress Score (OSS) and prognosis. Machine learning techniques, including Decision Trees (DT), Random Forest (RF), and Support Vector Machine (SVM), were employed to develop predictive models for 5-year overall survival (OS).

Results

The datasets consisted of 1647 patients in the training set, 705 in the internal validation set, and 516 in the external validation set. An OSS was formulated from six systemic oxidative stress biomarkers, such as albumin, total bilirubin, and blood urea nitrogen, among others. Boruta variable importance analysis identified low OSS as a key indicator of poor prognosis. The OSS was subsequently integrated into the DT, RF, and SVM models for training. These models, optimized through hyperparameter tuning on the training set, were then evaluated on the internal and external validation sets. The RF model demonstrated the highest predictive performance, with an Area Under the Receiver Operating Characteristic Curve (AUC) of 0.794 in the internal validation set, compared to AUCs of 0.711 and 0.760 for the DT and SVM models, respectively. Similarly, in the external validation set, the RF model achieved an AUC of 0.784, outperforming the DT and SVM models, which had AUCs of 0.699 and 0.730, respectively. Calibration plots confirmed the RF model's superior calibration, followed by the SVM model, with the DT model performing the poorest.

Conclusion

The OSS-based clinical prediction model, constructed using machine learning methodologies, effectively predicts the prognosis of elderly NSCLC patients post-radical surgery.

A Retrospective Study of 291 Patients With Head and Neck Sarcomas: Treatment, Outcomes, and Prognostic Factors

AIMS

Sarcomas constitute a group of rare malignant neoplasms, commonly subcategorized into soft tissue sarcomas (STS) and bone sarcomas. This study aims to describe the treatment modalities and outcome of head and neck sarcoma (HNS) patients in western Denmark and to identify prognostic factors for overall survival and recurrence in HNS patients.

MATERIALS AND METHODS

The Aarhus sarcoma registry, The National Danish Sarcoma Database, and the Danish National Pathology Registry were used to identify HNS adult patients diagnosed between 1979 and 2022.

RESULTS

Altogether, 291 patients were included in this study. The prevalent histological subtypes were undifferentiated pleomorphic sarcoma (16%; 48/291) and leiomyosarcoma (15%; 44/291) for STS patients (n = 230) and chondrosarcoma (10%; 28/291) and osteosarcoma (7%; 19/291) for bone sarcoma patients (n = 61). Surgery with curative intent was performed in 71% (164/230) and 70% (43/61) of STS and bone sarcoma patients, respectively. Clear resection was achieved in 59% (97/164) of STS patients and 44% (19/43) of bone sarcoma patients. Eighty-nine patients relapsed (STS n = 66, bone sarcoma n = 23) after a median time of 2.7/5.5 years for STS/bone sarcoma patients. The five-year overall survival rates were 45% for STS patients and 66% for bone sarcoma patients. The following factors were significantly, negatively associated with overall survival in STS patients: Age (hazard ratio (HR)) = 1.02, p < 0.001), tumour size ≥5 cm (HR = 1.75, p = 0.003), metastatic disease (HR = 3.17, p < 0.001), high grade tumour (HR = 2.24, p = 0.004), previous cancer (HR = 2.84, p < 0.001), and high Aarhus composite biomarker score (ACBS) (HR = 4.56, p = 0.001). For relapse in STS patients, higher tumour grade (HR = 3.19, p = 0.014), intralesional margins (HR = 2.84, p < 0.001), ≥2 previous cancers (HR = 3.00, p = 0.004), and high ACBS (HR = 3.29, p = 0.047), were negatively associated. For bone sarcomas only higher age (HR = 1.02, p = 0.049) and intralesional margins (HR = 2.91, p = 0.042) were significant negative factors for overall survival.

CONCLUSION

Multiple prognostic factors for overall survival and relapse were identified, especially for STS patients.

Neutrophil-to-lymphocyte ratio for the prediction of soft tissue sarcomas response to pre-operative radiation therapy

PURPOSE/OBJECTIVE

This study aims to assess the prognostic value of the neutrophil-to-lymphocyte ratio (NLR) in soft tissue sarcomas (STS) treated with pre-operative hypofractionated radiotherapy (HFRT).

MATERIALS/METHODS

This retrospective analysis included patients treated with pre-operative HFRT of 30 Gy in 5 fractions between 2016 and 2023. Clinical, demographic, and complete blood count (CBC) data were collected. NLR was calculated by dividing the absolute neutrophil count by the absolute lymphocyte count. Only patients with CBCs conducted within 6 months after radiotherapy were included. Cox proportional-hazard regression models were used to assess the impact of NLR and different variables on outcomes. Kaplan Meier were used to illustrate survival curves. A p-value < 0.05 was considered significant, and 95 % confidence intervals (CI) were employed.

RESULTS

A total of 40 patients received HFRT and had CBCs within 6 months after radiotherapy. There were 17 (42.5 %) females and 23 (57.5 %) males with a mean age of 66 years. The mean largest tumor size dimension was 7.1 cm, and the mean NLR post-RT was 5.3. The most frequent histological subtypes were myxofibrosarcoma (17.5 %), pleomorphic spindle cell sarcoma (10 %), leiomyosarcoma (7.5 %), and myxoid liposarcoma (5 %). The median follow-up period was 15.4 months. From all patients, 14 patients had disease progression, 12 metastatic disease and 3 died of disease. Multivariable Cox proportional-hazards regression analysis displayed that a higher post-RT NLR was associated with worse disease-free survival (DFS) (HR: 1.303 [1.098-1.548], p = 0.003), and distant metastasis-free survival (DMFS) (HR: 1.38 [1.115-1.710], p = 0.003). Moreover, post-NLR ≥ 4 as a single variable was associated with worse DFS, DMFS, but not worse local recurrence or overall survival.

CONCLUSION

This study is the first to evaluate NLR as a prognostic biomarker in STS patients treated with pre-operative radiotherapy. A higher NLR after pre-operative radiotherapy was associated with increased disease progression.

Association between alteration of neutrophil to lymphocyte ratio, platelet to lymphocyte ratio, cancer antigen-125 and surgical outcomes in advanced stage ovarian cancer patient who received neoadjuvant chemotherapy

Introduction

Optimal resection significantly influences the prognosis of advanced-stage epithelial ovarian cancer (EOC) patients undergoing debulking surgery. In patients who received neoadjuvant chemotherapy (NACT) followed by interval debulking surgery (IDS), the determination of the ideal timing for surgery remains a challenge. Inflammatory markers, including the neutrophil-to-lymphocyte ratio (NLR), platelet-lymphocyte ratio (PLR), and CA-125 levels, have been recognized as potential predictive markers.

Objective

This study aims to evaluate the predictive value of changes in NLR, PLR, and CA-125 levels following NACT, specifically assessing their impact on surgical outcomes during IDS for advanced-stage EOC.

Methods

A retrospective cohort study enrolled advanced-stage EOC patients who underwent NACT followed by IDS at Vajira Hospital in Thailand from January 2009 to June 2023. Data on clinical, surgical, and inflammatory markers were collected, and the predictive value of these markers for suboptimal resection outcomes was assessed.

Results

Among the 65 patients, 98.5 % exhibited radiologic responses post-NACT, while 29.2 % experienced suboptimal resections. Univariate analysis did not reveal significant associations between suboptimal resection and NLR changes after the first NACT cycle or alterations in NLR, PLR, and CA-125 levels at the end of NACT. Subsequent analysis suggested that an NLR decrease exceeding 70 % after the first cycle and NACT completion might predict suboptimal resection, yet statistical analyses showed limited prognostic efficacy (AuROC = 0.608 and 0.597).

Conclusion

Our study does not support that changes in NLR, PLR, platelet count, and CA-125 levels after NACT reliably predict IDS outcomes. Additional prospective investigations using larger cohorts or a combination of evaluation methods, rather than relying solely on NLR, are recommended.

Relationship Between Preoperative Inflammation Ratios Derived From Preoperative Blood Cell Count and Postoperative Pulmonary Complications in Patients Undergoing Lobectomy: A Single-Center Observational Study

OBJECTIVE

Evaluation of the association of inflammatory cell ratios, especially neutrophil-to-lymphocyte ratio (NLR), based on preoperative complete blood counts, with postoperative complications in lobectomy surgery.

DESIGN

This was a retrospective monocentric cohort study.

SETTING

The study was conducted at Foch University Hospital in Suresnes, France.

PARTICIPANTS

Patients having undergone a scheduled lobectomy from January 2018 to September 2021.

INTERVENTIONS

There were no interventions.

MEASUREMENTS AND MAIN RESULTS

The authors studied 208 consecutive patients. Preoperative NLR, monocyte-to-lymphocyte ratio, platelet-to-lymphocyte ratio, systemic inflammation index, systemic inflammation response index, and aggregate inflammation systemic index were calculated. Median and (IQR) of NLR was 2.67 (1.92-3.69). No statistically significant association was observed between any index and the occurrence of at least one major postoperative complication, which occurred in 37% of the patients. Median postoperative length of stay was 7 (5-10) days. None of the ratios was associated with prolonged length of stay (LOS), defined as a LOS above the 75th percentile.

CONCLUSIONS

The results suggested that simple available inflammatory ratios are not useful for the preoperative identification of patients at risk of postoperative major complications in elective lobectomy surgery.

Response score-based protein structure analysis for cancer prediction aided by the Internet of Things

Medical diagnosis through prediction and analysis is par excellence in integrating modern technologies such as the Internet of Things (IoT). With the aid of such technologies, clinical assessments are eased with protracted computing. Specifically, cancer research through structure prediction and analysis is improved through human and machine interventions sustaining precision improvements. This article, therefore, introduces a Protein Structure Prediction Technique based on Three-Dimensional Sequence. This sequence is modeled using amino acids and their folds observed during the pre-initial cancer stages. The observed sequences and the inflammatory response score of the structure are used to predict the impact of cancer. In this process, ensemble learning is used to identify sequence and folding responses to improve inflammations. This score is correlated with the clinical data for structures and their folds independently for determining the structure changes. Such changes through different sequences are handled using repeated ensemble learning for matching and unmatching response scores. The introduced idea integrated with deep ensemble learning and IoT combination, notably employing stacking method for enhanced cancer prediction precision and interdisciplinary collaboration. The proposed technique improves prediction precision, data correlation, and change detection by 11.83%, 8.48%, and 13.23%, respectively. This technique reduces correlation time and complexity by 10.43% and 12.33%, respectively.

A collection of multiregistry data on patients at high risk of lung cancer-a Danish retrospective cohort study of nearly 40,000 patients

Background

Lung cancer (LC) is the leading cause of cancer related deaths, and several countries are implementing screening programs. Risk models have been introduced to refine the LC screening criteria, but the use of real-world data for this task demands a robust data infrastructure and quality. In this retrospective cohort study, we aim to address the different relevant risk factors in terms of data sources, descriptive statistics, completeness and quality.

Methods

Data on comorbidity, prescription medication, smoking history, consultations, symptoms, familial predispositions, exposures, laboratory data among others were collected for all patients examined on a risk of LC over a 10-year period in the Region of Southern Denmark. Data were delivered from the regional data warehouse as well as the Danish Lung Cancer Registry. Associations between LC and non-LC groups were examined through Chi-squared test (categorical variables) and Wilcoxon signed-rank test (continuous variables that were non-parametric). These associations were investigated on both the original datasets and the subset of patients with complete data.

Results

The number of examined individuals increased over the study period and more patients were diagnosed with LC in stage I-II, from 18% in 2009 to 31% in 2018. LC patients were more likely to be older, smoker, with a registered prescription of the included medication. They also exhibited differences in laboratory analysis indicating inflammation and hyponatremia. Weight loss, fatigue and pain were more prevalent in the LC group, while hemoptysis and fever were more common among the non-LC patients. Advanced-stage LC patients experienced a higher rate of symptoms compared to those in the low stages. Within the sub-cohort with complete dataset results, most observed trends persisted, although data on comorbidities were susceptibility to change.

Conclusions

This study provides key insights into LC risk assessment using a robust dataset of patients examined for suspected LC. A consistent positive trend in early-stage LC diagnosis was observed throughout the study period. LC patients exhibited distinct smoking behaviors, medication patterns, variations in lab results, and specific symptoms. These discoveries have the potential to enhance discrimination in machine learning-based prediction models, particularly those capable of handling complex distributions. Serving as a detailed account of real-world data collection and processing, the study establishes a foundation for future development of prediction models aimed at facilitating the early referral of LC patients.

Prognostic value of pretreatment modified Glasgow Prognostic Score in small cell lung cancer: A meta-analysis

BACKGROUND

The prognostic role of pretreatment modified Glasgow Prognostic Score (mGPS) in small cell lung cancer (SCLC) patients remains unclear now.

METHODS

The PubMed, EMBASE, Web of Science, and CNKI electronic databases were searched up to December 14, 2022. The primary and secondary outcomes were overall survival and progression-free survival, respectively. The hazard ratios (HRs) and 95% confidence intervals (CIs) were combined to assess the association between pretreatment mGPS and survival of SCLC patients. Subgroup analysis based on the country, tumor stage, treatment and comparison of mGPS were further conducted and all statistical analyses were performed by STATA 15.0 software.

RESULTS

A total of ten retrospective studies involving 2831 SCLC patients were included. The pooled results demonstrated that elevated pretreatment mGPS was significantly related to poorer overall survival (HR = 1.90, 95% CI: 1.36-2.63, P < .001) and progression-free survival (HR = 1.40, 95% CI: 1.13-1.74, P = .002). Subgroup analysis stratified by the country, tumor stage, treatment and comparison of mGPS also showed similar results.

CONCLUSION

Pretreatment mGPS was significantly associated with prognosis in SCLC and patients with elevated mGPS experienced obviously worse survival. Thus, pretreatment mGPS could serve as a novel and reliable prognostic indicator in SCLC patients.

Interpretations of the Role of Plasma Albumin in Prognostic Indices: A Literature Review

This review assesses how publications interpret factors that influence the serum or plasma albumin (PA) level in prognostic indices, focusing on inflammation and nutrition. On PubMed, a search for "albumin AND prognosis" yielded 23,919 results. From these records, prognostic indices were retrieved, and their names were used as search strings on PubMed. Indices found in 10 or more original research articles were included. The same search strings, restricted to "Review" or "Systematic review", retrieved yielded on the indices. The data comprised the 10 latest original research articles and up to 10 of the latest reviews. Thirty indices had 294 original research articles (6 covering two indices) and 131 reviews, most of which were from recent years. A total of 106 articles related the PA level to inflammation, and 136 related the PA level to nutrition. For the reviews, the equivalent numbers were 54 and 65. In conclusion, more publications mention the PA level as a marker of nutrition rather than inflammation. This is in contrast to several general reviews on albumin and nutritional guidelines, which state that the PA level is a marker of inflammation but not nutrition. Hypoalbuminemia should prompt clinicians to focus on the inflammatory aspects in their patients.

Effect of Microsatellite Status and Pan-Immune-Inflammation Score on Pathological Response in Patients with Clinical Stage III Stomach Cancer Treated with Perioperative Chemotherapy

Background and Objective: This study evaluated the relationship between microsatellite status (MSI) and pan-immune-inflammation score (PIV) in tumor response to neoadjuvant chemotherapy (NAC) in patients with clinical stage III gastric cancer (cStage III GC). Materials and Methods: Microsatellite instability (MSI) status was evaluated based on pathology preparations. Pan-immune-inflammation score (PIV) was obtained from pre-treatment blood tests. The relationship of both parameters with pathological complete response (pCR) was evaluated. Results: A total of 104 patients were included in this study. All the patients were stage III GC patients receiving perioperative treatment. There were 13 patients in total who achieved a pCR response. While CNS was detected in 11 of the patients who achieved a pCR, the MSI status of the other two patients was unknown. No pCR was observed in any patient with MSI-H. According to the cut-off value for PIV, 25 (24%) patients were in the PIV-low (≤53.9) group, while 79 (76%) were in the PIV-high (>53.9) group. Based on univariate analysis, a higher PIV was associated with worse outcomes for pathological response, disease recurrence, and survival (p < 0.05). Conclusions: In patients with clinically stage III GC, the presence of MSI-H may predict no benefit from perioperative treatment. Conversely, a pre-treatment PIV score using specific cut-off values may provide a positive prediction of pathological response and survival.

The potential of high-order features of routine blood test in predicting the prognosis of non-small cell lung cancer

BACKGROUND

Numerous studies have demonstrated that the high-order features (HOFs) of blood test data can be used to predict the prognosis of patients with different types of cancer. Although the majority of blood HOFs can be divided into inflammatory or nutritional markers, there are still numerous that have not been classified correctly, with the same feature being named differently. It is an urgent need to reclassify the blood HOFs and comprehensively assess their potential for cancer prognosis.

METHODS

Initially, a review of existing literature was conducted to identify the high-order features (HOFs) and classify them based on their calculation method. Subsequently, a cohort of patients diagnosed with non-small cell lung cancer (NSCLC) was established, and their clinical information prior to treatment was collected, including low-order features (LOFs) obtained from routine blood tests. The HOFs were then computed and their associations with clinical features were examined. Using the LOF and HOF data sets, a deep learning algorithm called DeepSurv was utilized to predict the prognostic risk values. The effectiveness of each data set's prediction was evaluated using the decision curve analysis (DCA). Finally, a prognostic model in the form of a nomogram was developed, and its accuracy was assessed using the calibration curve.

RESULTS

From 1210 documents, over 160 blood HOFs were obtained, arranged into 110, and divided into three distinct categories: 76 proportional features, 6 composition features, and 28 scoring features. Correlation analysis did not reveal a strong association between blood features and clinical features; however, the risk value predicted by the DeepSurv LOF- and HOF-models is significantly linked to the stage. Results from DCA showed that the HOF model was superior to the LOF model in terms of prediction, and that the risk value predicted by the blood data model could be employed as a complementary factor to enhance the prognosis of patients. A nomograph was created with a C-index value of 0.74, which is capable of providing a reasonably accurate prediction of 1-year and 3-year overall survival for patients.

CONCLUSIONS

This research initially explored the categorization and nomenclature of blood HOF, and proved its potential in lung cancer prognosis.

Pretreatment Platelet Count is a Prognostic Marker in Lung Cancer: A Danish Registry-based Cohort Study

BACKGROUND

Thrombocytosis has been associated with a poor prognosis in a wide range of malignancies. However, the results have been conflicting for lung cancer. Therefore, we evaluated the prognostic value of platelet count in a large cohort of lung cancer patients.

PATIENTS AND METHODS

All lung cancer patients diagnosed in The Central Denmark Region from 2009 to 2018 were included in the study. Data from the Danish Lung Cancer Registry were combined with data from the clinical laboratory information system on pretreatment platelet count. Platelet count was defined as low, normal, or high based on being below, within, or above the reference intervals. The prognostic value of platelet count was assessed by the Cox proportional hazard model. C-statistics were conducted to investigate if the platelet count added additional prognostic value to existing prognostic markers.

RESULTS

Totally, 6,758 patients with non-small-cell lung cancer (NSCLC) and 1150 patients with small-cell lung cancer (SCLC) were included. Low and high platelet count were significantly associated with decreased overall survival (OS) in NSCLC patients (low: adjusted hazard ratio (HR)=1.75 (95% confidence interval [CI]: 1.49-2.06); high: adjusted HR=1.24 (95% CI: 1.16-1.33)). In SCLC patients, only low platelet count was significantly associated with decreased OS (adjusted HR = 2.71 [95% CI: 2.02-3.65]). C-statistics showed that the prognostic models were significantly improved by the addition of platelet count for both NSCLC and SCLC patients (P < .0001).

CONCLUSION

Low and high platelet count were adverse prognostic factors in NSCLC patients, while only low platelet count was a prognostic marker in SCLC patients.

C-Reactive Protein Pretreatment-Level Evaluation for Ewing's Sarcoma Prognosis Assessment-A 15-Year Retrospective Single-Centre Study

Background: A pathological/inflamed cellular microenvironment state is an additional risk factor for any cancer type. The importance of a chronic inflammation state in most diffuse types of tumour has already been analysed, except for in Ewing’s sarcoma. It is a highly malignant blue round cell tumour, with 90% of cases occurring in patients aged between 5 and 25 years. Worldwide, 2.9 out of 1,000,000 children per year are affected by this malignancy. The aim of this retrospective study was to analyse the role of C-reactive protein (CRP) as a prognostic factor for Ewing’s sarcomas. Methods: This retrospective study at Klinikum rechts der Isar included 82 patients with a confirmed Ewing’s sarcoma diagnosis treated between 2004 and 2019. Preoperative CRP determination was assessed in mg/dL with a normal value established as below 0.5 mg/dL. Disease-free survival time was calculated as the time between the initial diagnosis and an event such as local recurrence or metastasis. Follow-up status was described as death of disease (DOD), no evidence of disease (NED) or alive with disease (AWD). The exclusion criteria of this study included insufficient laboratory values and a lack of information regarding the follow-up status or non-oncological resection. Results: Serum CRP levels were significantly different in patients with a poorer prognosis (DOD) and in patients who presented distant metastasis (p = 0.0016 and p = 0.009, respectively), whereas CRP levels were not significantly different in patients with local recurrence (p = 0.02). The optimal breakpoint that predicted prognosis was 0.5 mg/dL, with a sensitivity of 0.76 and a specificity of 0.74 (AUC 0.81). Univariate CRP analysis level >0.5 mg/dL revealed a hazard ratio of 9.5 (95% CI 3.5−25.5). Conclusions: In Ewing’s sarcoma cases, we consider a CRP pretreatment value >0.5 mg/dL as a sensitive prognostic risk factor indication for distant metastasis and poor prognosis. Further research with more data is required to determine more sensitive cutoff levels.

The Association between the Pan-Immune-Inflammation Value and Cancer Prognosis: A Systematic Review and Meta-Analysis

Background: Prognostic scores derived from the blood count have garnered significant interest as an indirect measure of the inflammatory pressure in cancer. The recently developed pan-immune-inflammation value (PIV), an equation including the neutrophil, platelet, monocyte, and lymphocyte levels, has been evaluated in several cohorts, although with variations in the tumor types, disease stages, cut-offs, and treatments. Therefore, we evaluated the association between survival and PIV in cancer, performing a systematic review and meta-analysis. Methods: We conducted a systematic review from the Pubmed, Medline, and Embase databases to filter the published studies until 17 May 2022. The meta-analyses were performed with the generic inverse-variance method with a random-effects model. Results: Fifteen studies encompassing 4942 patients were included. In the pooled analysis of fifteen studies, the patients with higher PIV levels had significantly increased risk of death than those with lower PIV levels (HR: 2.00, 95% CI: 1.51−2.64, p < 0.001) and increased risk of progression or death (HR: 1.80, 95% CI: 1.39−2.32, p < 0.001). Analyses were consistent across several clinical scenarios, including non-metastatic or metastatic disease, different cut-offs (500, 400, and 300), and treatment with targeted therapy or immunotherapy (p < 0.001 for each). Conclusion: The available evidence demonstrates that PIV could be a prognostic biomarker in cancer. However, further research is needed to explore the promise of PIV as a prognostic biomarker in patients with non-metastatic disease or patients treated without immunotherapy or targeted therapy.