Prognostic Value of Preoperative ICPI in Rectal Cancer: A Nomogram Based Approach

Prognostic Value of Preoperative ICPI in Rectal Cancer: A Nomogram Based Approach | Research Square window.SnipcartSettings = { analytics: { enabled: false } }; (function() { var accessVector = localStorage.getItem('access_vector') || ''; window.dataLayer = window.dataLayer || []; if (accessVector) { window.dataLayer.push({ user: { profile: { profileInfo: { snid: accessVector } } } }); } })(); (function(w,d,s,l,i){w[l]=w[l]||[];w[l].push({'gtm.start':new Date().getTime(),event:'gtm.js'});var f=d.getElementsByTagName(s)[0],j=d.createElement(s),dl=l!='dataLayer'?'&l='+l:'';j.async=true;j.src='https://www.googletagmanager.com/gtm.js?id='+i+dl;f.parentNode.insertBefore(j,f);})(window,document,'script','dataLayer','GTM-K279D39R'); Browse Preprints In Review Journals COVID-19 Preprints AJE Video Bytes Research Tools Research Promotion AJE Professional Editing AJE Rubriq About Preprint Platform In Review Editorial Policies Our Team Advisory Board Help Center Sign In Submit a Preprint Cite Share Download PDF Research Article Prognostic Value of Preoperative ICPI in Rectal Cancer: A Nomogram Based Approach Xiangyong Li, Yan Zhou, Xinmeng Chen, Xiaodong Yang, Chungen Xing, and 1 more This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-7234131/v1 This work is licensed under a CC BY 4.0 License Status: Under Review Version 1 posted 5 You are reading this latest preprint version Abstract Objective This study examines the prognostic significance of preoperative inflammatory combined prognostic index (ICPI) in patients having laparoscopic rectal cancer surgery and constructs a machine learning-derived nomogram to predict patient prognosis. Methods This study retrospectively collected patients who underwent laparoscopic rectal cancer surgery from January 2016 to January 2021. Patients receiving neoadjuvant therapy were excluded due to its alteration of inflammatory markers and pathology. The optimal cut-off values for neutrophil-to-lymphocyte ratio (NLR), platelet-to-lymphocyte ratio (PLR), monocyte-to-lymphocyte ratio (MLR), and ICPI were 3.0, 171.82, 0.32, and 4.3, respectively. Prognostic features were identified from the training cohort using three ML methods (Lasso Regression, XGBoost, Random Forest), with consensus features selected through intersection analysis. Cox regression was performed to establish a nomogram for predicting 1-year, 3-year, and 5-year overall survival (OS) in rectal cancer patients. The enhancement in predictive capability and clinical benefit were evaluated through the Concordance Index (C-index), Receiver Operating Characteristic (ROC) curves, calibration curves, and Decision Curve Analysis (DCA). Results A total of 357 patients were enrolled and randomly divided into a training cohort (70%, n = 249) and a validation cohort (30%, n = 108).Additionally, patients with high NLR, PLR, MLR, and ICPI had poorer OS (P < 0.001). After machine learning and multivariable Cox regression, pN stage, carcinoembryonic antigen (CEA), surgical time, ICPI, and age were identified as independent prognostic factors affecting OS. A nomogram was constructed, and the area under the curve (AUC) values in both the training and validation cohorts exceeded 0.80, with C-indices of 0.80 and 0.79, respectively. The calibration curves demonstrated good agreement between the predicted and actual outcomes, indicating high prediction accuracy. DCA revealed that the nomogram exhibited a higher net benefit. Conclusion ICPI integrates multiple inflammatory parameters to predict rectal cancer survival. We also developed a machine learning-based nomogram for predicting OS in laparoscopic rectal cancer surgery patients. ICPI machine learning rectal cancer overall survival prediction nomogram Figures Figure 1 Figure 2 Figure 3 Figure 4 Figure 5 Figure 6 Figure 7 Introduction Colorectal cancer (CRC) is the third most common cancer globally and the second leading cause of cancer-related deaths [ 1 ]. Rectal cancer accounts for approximately 30% of all newly diagnosed CRC cases [ 2 ]. GLOBOCAN further predicts that by 2040, the annual incidence of CRC will increase from 1.9 million new cases in 2020 to 3.6 million, with CRC-related deaths rising from 0.93 million to 1.6 million during the same period [ 3 ]. Radical resection surgery for rectal cancer is currently the primary treatment method, and with the widespread adoption of rectal cancer screening, significant improvements have been made in treatment outcomes and patient prognosis. Rectal cancer prognosis and treatment decisions currently depend on the TNM staging system [ 4 ], but its accuracy is lacking [ 5 , 6 ]. Thus, creating a simple, precise model to predict survival is crucial and complements the TNM system. The tumor microenvironment has garnered increasing attention [ 7 ], with various inflammatory cells and mediators constituting a vital component of this microenvironment. Consequently, inflammation is recognized as the seventh hallmark of cancer [ 8 ] and has been demonstrated to be associated with the initiation, progression, and development of several malignancies [ 9 , 10 , 11 ]. It represents a non-negligible factor influencing the clinical outcomes of cancer patients. Preoperative blood components, as simple, accurate, and easily accessible samples, have been studied for their prognostic value in various cancers, including gastric cancer, colorectal cancer, hepatocellular carcinoma, and lung cancer [ 12 , 13 , 14 ]. In the field of cancer treatment, biomarkers are typically categorized into three major groups: (1) those capable of definitively diagnosing cancer, (2) those serving as key indicators for assessing patient prognosis, and (3) those used to predict the effectiveness of treatment responses or the risk of potential side effects. The NLR, PLR, and MLR are commonly used as inflammatory biomarkers and play significant roles in cancer prognosis [ 15 , 16 ]. However, due to the diversity of peripheral blood inflammatory markers and their derivatives, the use of a single marker to predict the prognosis of rectal cancer patients has varying degrees of limitations. Consequently, there is an urgent need for a composite inflammatory index to address this issue. In recent years, the ICPI has demonstrated significant value in prognostic prediction for gastric cancer due to its comprehensive assessment of inflammatory and immune imbalance. The ICPI was validated for predicting postoperative recurrence in gastric cancer cohorts. However, its applicability in rectal cancer remains unexplored due to the inherent differences in immune microenvironment, metastatic patterns, and treatment responses between rectal cancer and gastric cancer[ 17 ]. The combination of machine learning (ML) and medical data analysis has been applied in multiple research studies and has demonstrated promising predictive performance. A key advantage of ML is its ability to correlate multiple variables and accurately predict outcomes [ 18 , 19 ]. Consequently, several ML prediction models have recently been employed for disease diagnosis, prognosis prediction, and clinical decision-making. The primary distinction from traditional rule-based algorithms is their capability to utilize vast amounts of new data and to improve and learn over time. This study aims to investigate the predictive role of the Inflammation-based ICPI on survival in rectal cancer patients, employ machine learning to screen variables, and ultimately construct a nomogram to assist medical professionals in devising more personalized treatment plans. Materials and methods Study populations This study retrospectively collected the clinicopathological data of patients who were diagnosed with rectal cancer and underwent laparoscopic surgery for rectal cancer at the Second Affiliated Hospital of Soochow University between January 2016 and January 2021. Inclusion criteria: (1) Histopathologically confirmed primary rectal adenocarcinoma both preoperatively and postoperatively; (2) Undergoing laparoscopic radical resection; (3) Availability of complete and verifiable clinicopathological records; (4) Absence of distant metastasis confirmed through preoperative imaging assessments ( T1–3/N0–1M0 ( I-III stage )). Exclusion criteria: (1) Bulky tumors precluding laparoscopic approach or necessitating open conversion; (2) Emergency interventions for tumor-induced intestinal obstruction; (3) Prior neoadjuvant radiotherapy or chemotherapy; (4) Metastatic rectal malignancies (non-primary lesions) (Fig. 1 ). Data collection and definition The following indicators were systematically and retrospectively collected: (1) Basic patient characteristics: gender, age, American Society of Anesthesiologists (ASA) score, and comorbidities (hypertension, diabetes). (2) Laboratory test data: neutrophil count (×109/L), monocyte count (×109/L), and CEA within two weeks before surgery. (3) Intraoperative and postoperative data: operation time, pathological results, postoperative hospital stay, and whether radiotherapy or chemotherapy was administered after surgery. (4) Calculation of relevant biomarkers: NLR = neutrophil count (×10^9/L) / lymphocyte count (×10^9/L). PLR = platelet count (×10^9/L) / lymphocyte count (×10^9/L). MLR = monocyte count (×10^9/L) / lymphocyte count (×10^9/L). ICPI = HR NLR *NLR + HR PLR *PLR + HR MLR *MLR. Follow-up visits This study implemented a dual-track follow-up protocol utilizing outpatient reviews and structured telephone interviews. Surveillance commenced at 1-month postoperative with escalating intervals: monthly-to-quarterly during year 1, biannually during year 2, and annually thereafter. Follow-up concluded at December 2023 or patient demise, whichever occurred first. The primary endpoint was overall survival (OS), calculated from surgery date until death or last confirmed follow-up. Statistical analysis All statistical analyses were conducted in R (v4.4.0; R Foundation). Cox proportional hazards regression modeling was implemented using the cph function (rms package), with subsequent nomogram construction via the nomogram function. Continuous variables were analyzed with Mann-Whitney U tests and reported as median, while categorical variables underwent χ² testing and were summarized as frequencies (percentages). Group survival differences were assessed through Kaplan-Meier curves with log-rank testing. Intergroup comparisons utilized t-tests or χ² tests as appropriate. Cox regression outcomes were expressed as hazard ratios (HR) with 95% confidence intervals. Statistical significance was defined as two-tailed p < 0.05. Results Patients' characteristics After exclusion, a total of 357 patients were enrolled, among which 118 patients had died, while 239 patients were still alive. Differences were observed between the two groups in terms of age, ASA grade, pN stage, TNM stage, differentiation type, nerve invasion, vascular invasion, CEA levels, surgical time, postoperative chemotherapy, neutrophil count, monocyte count, NLR, and MLR (P < 0.05) ( Supplementary Table S1 ). The median age of the enrolled patients was 65 years, including 218 males (61.06%) and 139 females (38.94%). Among the enrolled patients, 125 had hypertension and 43 had diabetes. No significant differences were observed between the baseline characteristics of the training cohort and the validation cohort ( Table 1 ), and no significant differences were noted in the Kaplan-Meier survival curves between the two cohorts ( Supplementary Figure S1 ). Determine the optimal cutoff values of ICPI In order to identify the optimal cutoff values for inflammatory markers such as NLR, PLR, MLR, and ICPI, we employed the maximum selected log-rank statistic ( Supplementary Figure S2A,B,C,D ). Significant differences in Kaplan-Meier curves were observed between the two groups at NLR = 3.0, PLR = 171.8, and MLR = 0.32 (P < 0.001) (Fig. 2A, B, C ). The ICPI was defined using the methodology proposed by Noriyuki Hirahara et al[ 17 ], where the formula was derived from hazard ratios. Binary scoring (1/0) was applied when MLR > 0.32, NLR ≥ 3.0, and PLR ≥ 171.8 respectively, with subsequent calculation using the formula: ICPI = 2.4NLR + 2.3PLR + 3.1MLR. At an ICPI value of 4.3, significant differences in Kaplan-Meier curves were observed between the two groups (P < 0.001) (Fig. 2D). When comparing the survival and death groups, statistically significant differences were noted for NLR and MLR (P < 0.05), whereas no significant difference was observed for PLR. Nevertheless, the ICPI, which was constructed using these three indicators, exhibited significant differences between the two groups ( Supplementary Table S1 ). Furthermore, patients belonging to the high NLR, PLR, MLR, and ICPI groups exhibited inferior OS outcomes (Fig. 2A, B, C ). Variable selection Lasso regression, XGBoost, and random forest were used for variable selection, and the intersection of important variables selected by the three machine learning methods was represented in a Venn diagram. Random forest provides variable importance measures through permutation. For random forest, we performed analysis through minimum depth variable selection and ultimately identified 7 variables as important (Fig. 3A). The LASSO regression model included 18 variables. The selection criterion was based on lambda. min and the model showed the best fit at lambda. min = 0.034 (Fig. 3B). Finally, 8 candidate variables with non-zero coefficients were selected (Fig. 3B). Currently, there is no consensus on the number of important variables selected by XGBoost. We selected the top 10 variables based on their importance (Fig. 3C). The important variables selected by machine learning were: Age, differentiation type, pN stage, CEA, surgical time, and ICPI (Fig. 3D). Subsequently, we included the selected important variables in a multivariate COX regression analysis, and the results showed that pN stage, CEA, surgical time, ICPI, and age were independent prognostic factors for patients undergoing laparoscopic rectal cancer surgery (P < 0.05) ( Table 2 ). Construction and verification of the nomogram prediction model for OS A nomogram model for predicting OS in rectal cancer was constructed based on independent prognostic factors selected from the training cohort using machine learning and multivariate Cox regression results. Each variable was assigned a score based on its HR. The total score of each variable was added, and its corresponding position on the total score scale was determined to obtain the probabilities of OS at 1, 3, and 5 years (Fig. 4 ). The ROC analysis of the nomogram showed AUCs of 0.848, 0.861, and 0.851 for 1-year, 3-year, and 5-year OS, respectively, in the training cohort ( Supplementary Figure S3 ); while in the validation cohort, the AUCs were 0.829, 0.857, and 0.824 (Fig. 5 ,A,B,C). The C-index was used to validate the nomogram constructed in the training set, with values of 0.809 (95% CI: 0.768–0.851) and 0.786 (95% CI: 0.722–0.849) in the training and validation cohorts, respectively. The time-dependent ROC curves in the validation cohort tended to stabilize over time ( Supplementary Figure S4 ). In both the training cohort ( Supplementary Figure S5 ) and the validation cohort (Fig. 6 ,A,B,C), the nomogram calibration curves demonstrate a high degree of agreement between the observed and predicted probabilities. Furthermore, DCA was employed to assess the clinical utility of the nomogram, revealing significant positive net benefits in both the training cohort ( Supplementary Figure S6 ) and the validation cohort (Fig. 7, A,B,C ), indicating its important clinical applicability in predicting OS among patients undergoing laparoscopic rectal cancer surgery. Discussion In this study, we have, for the first time, explored the relationship between ICPI and OS in patients undergoing laparoscopic rectal cancer surgery. We have discovered, for the first time, that patients with high ICPI have worse prognosis compared to those with low ICPI. Additionally, NLR, PLR, and MLR all exhibited a similar trend, indicating that patients with high inflammatory indices have a poorer prognosis. Conversely, patients with low inflammatory indices had a better prognosis. Furthermore, we utilized machine learning to screen variables, ultimately constructing a nomogram for predicting prognosis in rectal cancer patients. This nomogram exhibits high efficacy and clinical benefits. Our findings may contribute to a deeper understanding of the nature of the relationship between ICPI and survival in rectal cancer patients. While neoadjuvant therapy is increasingly used, upfront surgery persists in early-stage disease and resource-constrained settings. Our model addresses an unmet need in these scenarios. Consequently, they offer valuable references for prognostic assessment, treatment outcome prediction, and follow-up monitoring of rectal cancer patients. In the tumor-induced systemic environment, numerous inflammatory cytokines are involved in the development of colorectal cancer cell invasion and metastasis [ 20 ]. Tumors can also trigger local inflammatory responses and release proinflammatory cytokines, leading to the formation of an inflammatory microenvironment [ 21 , 22 , 23 ]. The role of lymphocytes in tumor immune surveillance and immune editing has been extensively studied [ 24 ]. Lymphocytes primarily play an antitumor defense role. They induce cytotoxic cell death and produce cytokines that inhibit cancer cell proliferation and metastatic activity [ 25 ]. Neutrophils may contribute to tumor progression. Neutrophils are the primary source of vascular endothelial growth factor (VEGF) [ 26 ] and release prostaglandin E2 to amplify inflammation and create a tumor microenvironment, thereby promoting colorectal tumorigenesis through the secretion of interleukin-1β and matrix metalloproteinases, inhibiting natural killer cell activity and increasing tumor cell infiltration [ 24 ]. Additionally, neutrophils can degrade the basement membrane, mediating local tumor invasion and the formation of distant metastases [ 27 ]. Studies have shown that platelets also play a role in tumor progression [ 28 , 29 ]. In the tumor microenvironment, platelets promote angiogenesis by releasing proangiogenic proteins such as VEGF and transforming growth factor-β. In the tumor microenvironment, platelets can promote angiogenesis by releasing angiogenic proteins (such as vascular endothelial growth factor and transforming growth factor-β), thereby promoting tumorigenesis. Platelet-derived growth factor produced by platelets also plays a crucial role in promoting tumor growth and invasion [ 30 ]. Furthermore, cytokines and chemokines produced by platelets can promote cancer-related inflammation [ 30 , 31 , 32 ]. This serves as one of the strong evidence for platelets' role in tumor progression. Monocytes may also act as "boosters" for tumor cells. Monocytes in the blood can produce reactive oxygen species, reactive nitrogen species, and other cytokines, inhibiting lymphocyte activation, which leads to DNA mutations and tumor progression [ 32 ]. Therefore, the calculation formulas for NLR, PLR, and MLR also indicate that a higher level of inflammatory status predicts a poorer survival outcome, which is consistent with our research findings. NLR, PLR, and MLR, each focusing on distinct aspects of host inflammation and immunity, have been consistently validated as valuable indicators across multiple studies [ 15 , 16 ]. Currently, various inflammatory indices have been utilized to predict the prognosis of colorectal cancer. In a large cohort study involving 1,260 colorectal cancer patients, the relationship between the C-reactive protein-albumin-lymphocyte (CALLY) score and the prognosis of colorectal cancer was explored. The study found that the C-index of the nomogram constructed based on the CALLY score was 0.784, which is lower than that of our study (0.809) [ 43 ]. Another study combined tumor markers with the systemic immune-inflammation index to predict the prognosis of colorectal cancer, and the C-index of their constructed nomogram was 0.723, which is also lower than that of our study. These findings demonstrate the excellent predictive performance of our study [ 44 ].In our research, each inflammatory biomarker exhibited significant differences in univariate analysis. The innovative ICPI, which ingeniously integrates these three inflammatory indicators, provides a more comprehensive assessment of patients' inflammatory and immune status, thereby enhancing the accuracy of cancer prognosis prediction. Notably, our concurrent application of three machine learning variable selection processes consistently identified ICPI as a pivotal variable, underlining its robustness within the model. Furthermore, after multivariate Cox regression analysis, pN stage, CEA, surgical time, and age were also recognized as critical variables influencing the prognosis of patients undergoing laparoscopic rectal cancer surgery, aligning with previous findings [ 33 , 34 , 35 ].Hence, for patients with a high ICPI level, preoperative intervention is highly necessary, and aggressive anti-inflammatory treatment should be administered. This includes:The use of medications such as antibiotics and glucocorticoids. However, it is important to note that anti-inflammatory treatment should be individualized based on the patient's specific condition to avoid overtreatment or undertreatment.Nutritional support: High inflammation levels often indicate high catabolism, thus nutritional support should be enhanced to improve the patient's nutritional status and immune function [ 36 ].Regular monitoring and assessment: During the course of treatment, the patient's ICPI indicators, as well as clinical manifestations and radiological findings, should be regularly monitored. Treatment plans should be adjusted promptly based on monitoring results to ensure the effectiveness and safety of the treatment. Given our consideration that neoadjuvant therapy may affect patients' inflammatory levels, our study did not enroll patients who had undergone neoadjuvant therapy. However, studies have also shown that even among patients who received neoadjuvant therapy, those with higher NLR, PLR, and MLR exhibited poorer prognoses[ 45 , 46 ]. Tumor location is also recognized as an important predictor of postoperative OS in rectal cancer patients [ 37 ]. Cheng et al [ 38 ] classified T3/T4 rectal cancer patients who underwent surgery into high and mid/low rectal cancer groups, and found that patients with stage III high rectal cancer had a better prognosis than those with mid/low rectal cancer, indicating that tumor location is an independent prognostic factor for long-term survival. However, other studies have reached different conclusions, suggesting that tumor location does not affect long-term outcomes. Bhangu et al [ 39 ]concluded that the tumor location in rectal cancer, whether high or low, does not result in worse survival rates after radical surgery, with low rectal cancer demonstrating comparable oncologic outcomes compared to mid/high rectal cancer. Similarly, Khan et al [ 40 ] found that although the level of rectal cancer affected the use of neoadjuvant therapy and R0 resection rates, it did not impact recurrence rates and long-term survival. Additionally, postoperative complications may also influence the prognosis of rectal cancer patients [ 41 ]. Several studies have shown an association between anastomotic leakage (AL) and disease recurrence, as well as OS, while other studies have not found adverse effects on tumor outcomes[ 42 ]. This may depend on the different definitions of AL used in various studies. It is noteworthy that in our study, ICPI and operative time were identified as more significant prognostic factors than adjuvant chemoradiotherapy. This may be associated with the preoperative systemic inflammatory response, which can directly facilitate metastasis by promoting angiogenesis and suppressing anti-tumour immunity [ 47 ]. Furthermore, recent studies suggest that an inflammatory microenvironment may reduce sensitivity to chemoradiotherapy[ 48 ]. Additionally, animal experiments indicate that prolonged mechanical manipulation during surgery might enhance the release of circulating tumour cells [ 49 ]. These mechanisms may collectively explain why operative time and ICPI emerged as independent prognostic determinants surpassing the impact of adjuvant therapy. However, it is crucial to note that the optimal combination and cut-off values may vary according to cancer types. Moreover, various anticancer treatments can differentially impact the systemic inflammatory state. Therefore, a tailored approach focusing on specific cancer types is imperative to accurately assess the prognostic implications of inflammation-related biomarkers. While ctDNA emerges as a sensitive prognostic tool, ICPI offers an economical alternative for settings lacking advanced molecular testing. Future studies should explore combining inflammatory indices with ctDNA for precision prognostication. Certainly, this study has several limitations. Firstly, this study was a retrospective study conducted at a single center, and the number of enrolled patients was relatively small, which may have increased bias in sample selection and analysis. Further validation with a larger sample size from multiple centers is needed. Secondly, this study only included patients in stages I-III, and we did not conduct subgroup analysis for patients with distant metastasis or postoperative adjuvant therapy. While generalizability to neoadjuvant-treated cohorts requires further validation, this study delivers prognostic decision support for patients undergoing upfront surgery. Moreover, the relatively high proportion of Stage I patients in our study has led to an imbalance in the staging of the included patient data. Additionally, we have only explored the relationship between ICPI and OS, and have not investigated the relationship between recurrence-free survival and ICPI. This represents a limitation of our study.Therefore, further investigation is needed to understand the prognostic significance of ICPI in rectal cancer patients with distant metastasis. Lastly, the results of peripheral blood cell analysis are susceptible to factors such as blood circulation, infection, and nutritional status, which may lead to changes in inflammatory indicators and thus affect the outcome. Nonetheless, our study is valuable as it is the first to discover a significant correlation between ICPI and OS in patients undergoing laparoscopic rectal cancer surgery. Furthermore, we have successfully developed a nomogram based on ICPI and three other independent prognostic parameters from multivariate analysis to predict OS in rectal cancer patients. Conclusions Through our research, preoperative ICPI is an effective indicator for assessing the prognosis of patients undergoing laparoscopic rectal cancer surgery and may provide assistance for anti-inflammatory therapy. Secondly, we developed and validated a nomogram using machine learning to predict the overall survival of patients undergoing laparoscopic rectal cancer surgery, and it demonstrated excellent predictive performance. Abbreviations ICPI, inflammatory combined prognostic index; NLR, neutrophil-to-lymphocyte ratio; PLR, platelet-to-lymphocyte ratio; MLR, monocyte-to-lymphocyte ratiol; RF random forest decision tree; BMI body mass index; RC rectal cancer; ML machine learning; ASA American Society of Anesthesiologists; AUC Area under the receiver operating characteristic curve; ROC Receiver operating characteristic curve; HR, hazard ratios Declarations Ethics approval and consent to participate It complies with the World Medical Association Declaration of Helsinki in 1964 and subsequently amended versions. The Ethics Committee of the Second Affiliated Hospital of Soochow University approved our retrospective study(JD-HG-2024-051). The Ethics Committee of the Second Affiliated Hospital of Soochow University waived the need for patient approval or informed consent. As this is a retrospective study, patient information has been anonymized prior to the use of these data, and all data have undergone encryption processing, with access restricted to authorized personnel only. Consent for publication Not applicable. Availability of data and materials The data sets analyzed during the current study are not publicly available for patient privacy purposes but are available from the corresponding author (Wu) upon reasonable request. Competing Interests The authors declare no competing interests. Funding The present study was supported by the Suzhou Science and Technology Bureau (No.SKY2022156). Author contributions Xiangyong Li and Yong Wu conceptualized and designed the work. Xiangyong Li and Yan Zhou collected all the data. Xiangyong Li and Yan Zhou drafted and analyzed the manuscript. Xiaodong Yang, Yong Wu and Chungen Xing reviewed and revised the manuscript. All authors have read and approved the final work. Acknowledgements Not applicable References Bray F, Laversanne M, Sung H, et al. Global cancer statistics 2022: GLOBOCAN estimates of incidence and mortality worldwide for 36 cancers in 185 countries. CA Cancer J Clin. 2024;74:229–63. Siegel RL, Wagle NS, Cercek A, Smith RA, Jemal A. Colorectal cancer statistics, 2023. CA Cancer J Clin. 2023;73:233–54. Morgan E, Arnold M, Gini A, et al. Global burden of colorectal cancer in 2020 and 2040: incidence and mortality estimates from GLOBOCAN. Gut. 2023;72:338–44. Amin MB, Greene FL, Edge SB, et al. The Eighth Edition AJCC Cancer Staging Manual: Continuing to build a bridge from a population-based to a more personalized approach to cancer staging. CA Cancer J Clin. 2017;67:93–9. Quirke P, Williams GT, Ectors N, Ensari A, Piard F, Nagtegaal I. The future of the TNM staging system in colorectal cancer: time for a debate? Lancet Oncol. 2007;8:651–7. Ueno H, Mochizuki H, Akagi Y, et al. Optimal colorectal cancer staging criteria in TNM classification. J Clin Oncol. 2012;30:1519–26. Quail DF, Joyce JA. Microenvironmental regulation of tumor progression and metastasis. Nat Med. 2013;19:1423–37. Diakos CI, Charles KA, McMillan DC, Clarke SJ. Cancer-related inflammation and treatment effectiveness. Lancet Oncol. 2014;15:e493–503. Johnson CE, Alberg AJ, Bandera EV, et al. Association of inflammation-related exposures and ovarian cancer survival in a multi-site cohort study of Black women. Br J Cancer. 2023;129:1119–25. Xie HL, Ruan GT, Wei L, et al. The prognostic value of the combination of body composition and systemic inflammation in patients with cancer cachexia. J Cachexia Sarcopenia Muscle. 2023;14:879–90. Wang P, Wang S, Sun Z, et al. Systemic inflammation influences the prognosis of patients with radically resected non-small cell lung cancer and correlates with the immunosuppressive microenvironment. Int J Cancer. 2023;153:826–42. Zhou D, Wu Y, Zhu Y, Lin Z, Yu D, Zhang T. The Prognostic Value of Neutrophil-to-lymphocyte Ratio and Monocyte-to-lymphocyte Ratio in Metastatic Gastric Cancer Treated with Systemic Chemotherapy. J Cancer. 2020;11:4205–12. Nost TH, Alcala K, Urbarova I, et al. Systemic inflammation markers and cancer incidence in the UK Biobank. Eur J Epidemiol. 2021;36:841–8. Song M, Zhang Q, Song C, et al. The advanced lung cancer inflammation index is the optimal inflammatory biomarker of overall survival in patients with lung cancer. J Cachexia Sarcopenia Muscle. 2022;13:2504–14. Diem S, Schmid S, Krapf M, et al. Neutrophil-to-Lymphocyte ratio (NLR) and Platelet-to-Lymphocyte ratio (PLR) as prognostic markers in patients with non-small cell lung cancer (NSCLC) treated with nivolumab. Lung Cancer. 2017;111:176–81. Yamamoto T, Kawada K, Obama K. Inflammation-Related Biomarkers for the Prediction of Prognosis in Colorectal Cancer Patients. Int J Mol Sci. 2021;22. Hirahara N, Matsubara T, Kaji S, et al. Novel inflammation-combined prognostic index to predict survival outcomes in patients with gastric cancer. Oncotarget. 2023;14:71–82. Painuli D, Bhardwaj S, Köse U. Recent advancement in cancer diagnosis using machine learning and deep learning techniques: A comprehensive review. Comput Biol Med. 2022;146:105580. El-Sherbini AH, Coroneos S, Zidan A, Othman M. Machine Learning as a Diagnostic and Prognostic Tool for Predicting Thrombosis in Cancer Patients: A Systematic Review. Semin Thromb Hemost. 2024;50:809–16. Crusz SM, Balkwill FR. Inflammation and cancer: advances and new agents. Nat Rev Clin Oncol. 2015;12:584–96. Greten FR, Grivennikov SI. Inflammation and Cancer: Triggers, Mechanisms, and Consequences. Immunity. 2019;51:27–41. Anderson NM, Simon MC. The tumor microenvironment. Curr Biol. 2020;30:R921–5. Hou J, Karin M, Sun B. Targeting cancer-promoting inflammation - have anti-inflammatory therapies come of age? Nat Rev Clin Oncol. 2021;18:261–79. Gubin MM, Vesely MD. Cancer Immunoediting in the Era of Immuno-oncology. Clin Cancer Res. 2022;28:3917–28. Kilincalp S, Çoban Ş, Akinci H, et al. Neutrophil/lymphocyte ratio, platelet/lymphocyte ratio, and mean platelet volume as potential biomarkers for early detection and monitoring of colorectal adenocarcinoma. Eur J Cancer Prev. 2015;24:328–33. McCourt M, Wang JH, Sookhai S, Redmond HP. Proinflammatory mediators stimulate neutrophil-directed angiogenesis. Arch Surg. 1999;134:1325–31. discussion 1331 – 1322. Huh SJ, Liang S, Sharma A, Dong C, Robertson GP. Transiently entrapped circulating tumor cells interact with neutrophils to facilitate lung metastasis development. Cancer Res. 2010;70:6071–82. Wojtukiewicz MZ, Sierko E, Hempel D, Tucker SC, Honn KV. Platelets and cancer angiogenesis nexus. Cancer Metastasis Rev. 2017;36:249–62. Stojkovic Lalosevic M, Pavlovic Markovic A, Stankovic S, et al. Combined Diagnostic Efficacy of Neutrophil-to-Lymphocyte Ratio (NLR), Platelet-to-Lymphocyte Ratio (PLR), and Mean Platelet Volume (MPV) as Biomarkers of Systemic Inflammation in the Diagnosis of Colorectal Cancer. Dis Markers. 2019;2019:6036979. Zhu X, Cao Y, Lu P, et al. Evaluation of platelet indices as diagnostic biomarkers for colorectal cancer. Sci Rep. 2018;8:11814. Karaman K, Bostanci EB, Aksoy E, et al. The predictive value of mean platelet volume in differential diagnosis of non-functional pancreatic neuroendocrine tumors from pancreatic adenocarcinomas. Eur J Intern Med. 2011;22:e95–98. Peterson JE, Zurakowski D, Italiano JE Jr., et al. VEGF, PF4 and PDGF are elevated in platelets of colorectal cancer patients. Angiogenesis. 2012;15:265–73. Jeon Y, Kim YJ, Jeon J, et al. Machine learning based prediction of recurrence after curative resection for rectal cancer. PLoS ONE. 2023;18:e0290141. Takeda Y, Sugano H, Okamoto A, et al. Prognostic usefulness of the C-reactive protein-albumin-lymphocyte (CALLY) index as a novel biomarker in patients undergoing colorectal cancer surgery. Asian J Surg. 2024;47:3492–8. Duffy MJ. Carcinoembryonic antigen as a marker for colorectal cancer: is it clinically useful? Clin Chem. 2001;47:624–30. Stumpf F, Keller B, Gressies C, Schuetz P. Inflammation and Nutrition: Friend or Foe? Nutrients. 2023; 15(5). Yang H, Yao Z, Cui M, et al. Influence of tumor location on short- and long-term outcomes after laparoscopic surgery for rectal cancer: a propensity score matched cohort study. BMC Cancer. 2020;20:761. Cheng LJ, Chen JH, Chen SY, et al. Distinct Prognosis of High Versus Mid/Low Rectal Cancer: a Propensity Score-Matched Cohort Study. J Gastrointest Surg. 2019;23:1474–84. Bhangu A, Rasheed S, Brown G, et al. Does rectal cancer height influence the oncological outcome? Colorectal Dis. 2014;16:801–8. Khan MAS, Ang CW, Hakeem AR, et al. The Impact of Tumour Distance From the Anal Verge on Clinical Management and Outcomes in Patients Having a Curative Resection for Rectal Cancer. J Gastrointest Surg. 2017;21:2056–65. Warps AK, Tollenaar R, Tanis PJ, et al. Postoperative complications after colorectal cancer surgery and the association with long-term survival. Eur J Surg Oncol. 2022;48:873–82. Espín E, Ciga MA, Pera M, et al. Oncological outcome following anastomotic leak in rectal surgery. Br J Surg. 2015;102:416–22. Yang M, Lin SQ, Liu XY, et al. Association between C-reactive protein-albumin-lymphocyte (CALLY) index and overall survival in patients with colorectal cancer: From the investigation on nutrition status and clinical outcome of common cancers study. Front Immunol. 2023;14:1131496. Xie H, Yuan G, Huang S, et al. The prognostic value of combined tumor markers and systemic immune-inflammation index in colorectal cancer patients. Langenbecks Arch Surg. 2020;405:1119–30. Huai Q, Luo C, Song P, et al. Peripheral blood inflammatory biomarkers dynamics reflect treatment response and predict prognosis in non-small cell lung cancer patients with neoadjuvant immunotherapy. Cancer Sci. 2023;114:4484–98. Hwang M, Canzoniero JV, Rosner S et al. Peripheral blood immune cell dynamics reflect antitumor immune responses and predict clinical response to immunotherapy. J Immunother Cancer. 2022; 10(6). Roxburgh CS, D, McMillan DC. Cancer and systemic inflammation: treat the tumour and treat the host. Br J Cancer 110,6 (2014): 1409–12. 10.1038/bjc.2014.90 Huang Y, et al. Improving immune-vascular crosstalk for cancer immunotherapy. Nat reviews Immunol vol. 2018;18(3):195–203. 10.1038/nri.2017.145 . Retsky M, et al. Surgery triggers outgrowth of latent distant disease in breast cancer: an inconvenient truth? Cancers 2,2 305 – 37. 30 Mar. 2010. 10.3390/cancers2020305 . Tables Tables 1 and 2 are available in the Supplementary Files section. Additional Declarations No competing interests reported. Supplementary Files Table1.xlsx Table2.xlsx SupplementaryMaterial.docx Cite Share Download PDF Status: Under Review Version 1 posted Reviewers invited by journal 03 Sep, 2025 Editor assigned by journal 28 Aug, 2025 Editor invited by journal 04 Aug, 2025 Submission checks completed at journal 31 Jul, 2025 First submitted to journal 31 Jul, 2025 You are reading this latest preprint version Research Square lets you share your work early, gain feedback from the community, and start making changes to your manuscript prior to peer review in a journal. As a division of Research Square Company, we’re committed to making research communication faster, fairer, and more useful. We do this by developing innovative software and high quality services for the global research community. Our growing team is made up of researchers and industry professionals working together to solve the most critical problems facing scientific publishing. Also discoverable on Platform About Our Team In Review Editorial Policies Advisory Board Help Center Resources Author Services Accessibility API Access RSS feed Manage Cookie Preferences © Research Square 2026 | ISSN 2693-5015 (online) Privacy Policy Terms of Service Do Not Sell My Personal Information {"props":{"pageProps":{"initialData":{"identity":"rs-7234131","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":510778412,"identity":"eb947830-0114-48e9-b703-612339dbc060","order_by":0,"name":"Xiangyong Li","email":"","orcid":"","institution":"the Second Affiliated Hospital of Soochow University","correspondingAuthor":false,"prefix":"","firstName":"Xiangyong","middleName":"","lastName":"Li","suffix":""},{"id":510778413,"identity":"31d57c87-642b-43ba-bdb4-4ee5a28448a9","order_by":1,"name":"Yan Zhou","email":"","orcid":"","institution":"the Second Affiliated Hospital of Soochow University","correspondingAuthor":false,"prefix":"","firstName":"Yan","middleName":"","lastName":"Zhou","suffix":""},{"id":510778414,"identity":"4c161cd0-2a61-4d3f-b70f-98eec7afa02e","order_by":2,"name":"Xinmeng Chen","email":"","orcid":"","institution":"the Second Affiliated Hospital of Soochow University","correspondingAuthor":false,"prefix":"","firstName":"Xinmeng","middleName":"","lastName":"Chen","suffix":""},{"id":510778415,"identity":"d8c04007-ec02-441f-9aaf-b7da4a5d854e","order_by":3,"name":"Xiaodong Yang","email":"","orcid":"","institution":"the Second Affiliated Hospital of Soochow University","correspondingAuthor":false,"prefix":"","firstName":"Xiaodong","middleName":"","lastName":"Yang","suffix":""},{"id":510778416,"identity":"82434355-59e5-48ea-8ac0-3b85b0468837","order_by":4,"name":"Chungen Xing","email":"","orcid":"","institution":"the Second Affiliated Hospital of Soochow University","correspondingAuthor":false,"prefix":"","firstName":"Chungen","middleName":"","lastName":"Xing","suffix":""},{"id":510778417,"identity":"52e37911-512c-4587-ad32-3fb503cc8242","order_by":5,"name":"Yong Wu","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA1ElEQVRIiWNgGAWjYPACGzs29uYDBz78IF5LWjI/z7HEgzN7iNdyiHHmjBzjwxxsRKg1uJFj+Ljg1wFmgwM5Hw4z8DDI84sdIKjF2Hhm3x0+gwNnNxwusGAwnDk7Ab8Wsxs5ZtK8Pc+YDQ72bjg8g4chweA2cVoOM244zPPgMA8bsVp4fhxmnNnGw0CcFvszz4qNeRtAgcxmAAxkCcJ+kWxP3viY5w8wKuUfP/7w4YeNPL80AS0MDBwGDIxtcJ4EIeUgwP6AgeEPMQpHwSgYBaNgxAIAdh9K0pKczyEAAAAASUVORK5CYII=","orcid":"","institution":"the Second Affiliated Hospital of Soochow University","correspondingAuthor":true,"prefix":"","firstName":"Yong","middleName":"","lastName":"Wu","suffix":""}],"badges":[],"createdAt":"2025-07-28 12:53:41","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-7234131/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-7234131/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":90929425,"identity":"770dda19-408c-4020-96f6-f534ac7f9188","added_by":"auto","created_at":"2025-09-09 16:05:03","extension":"png","order_by":1,"title":"Figure 1","display":"","copyAsset":false,"role":"figure","size":124402,"visible":true,"origin":"","legend":"\u003cp\u003eFlow chart of study design, N：Number.\u003c/p\u003e","description":"","filename":"1.png","url":"https://assets-eu.researchsquare.com/files/rs-7234131/v1/849797bf3221adadbffbecc3.png"},{"id":90930695,"identity":"0a4fcb14-4332-4912-82d5-2efdc216a6be","added_by":"auto","created_at":"2025-09-09 16:13:03","extension":"png","order_by":2,"title":"Figure 2","display":"","copyAsset":false,"role":"figure","size":119657,"visible":true,"origin":"","legend":"\u003cp\u003e(A) Kaplan-Meier survival curves for OS of rectal cancer patients classified according to NLR cut-off values (P \u0026lt; 0.001). (B) Kaplan-Meier survival curves for OS of rectal cancer patients classified according to PLR cut-off values (P \u0026lt; 0.001). (C) Kaplan-Meier survival curves for OS of rectal cancer patients classified according to MLR cut-off values (P \u0026lt; 0.001). (D) Kaplan-Meier survival curves for OS of rectal cancer patients classified according to ICPI cut-off values (P \u0026lt; 0.001).\u003c/p\u003e","description":"","filename":"2.png","url":"https://assets-eu.researchsquare.com/files/rs-7234131/v1/3ce3de2cd6264a202f043eef.png"},{"id":90929427,"identity":"37dea46a-5d07-4c7e-b12a-da4335c179b6","added_by":"auto","created_at":"2025-09-09 16:05:03","extension":"png","order_by":3,"title":"Figure 3","display":"","copyAsset":false,"role":"figure","size":64586,"visible":true,"origin":"","legend":"\u003cp\u003eThree important feature selection methods in ML are (A) Lasso regression;(B) Xgboost; and (C) Random Forest;(D) Venn diagram.\u003c/p\u003e","description":"","filename":"3.png","url":"https://assets-eu.researchsquare.com/files/rs-7234131/v1/a09eda5c0dbcd4826d556307.png"},{"id":90932540,"identity":"8d11e808-be77-43fa-8951-dd645eb8e3f2","added_by":"auto","created_at":"2025-09-09 16:29:03","extension":"png","order_by":4,"title":"Figure 4","display":"","copyAsset":false,"role":"figure","size":183102,"visible":true,"origin":"","legend":"\u003cp\u003eNomogram model predicting overall survival from the training cohort.\u003c/p\u003e","description":"","filename":"4.png","url":"https://assets-eu.researchsquare.com/files/rs-7234131/v1/3b4c45f160aa071475232913.png"},{"id":90929437,"identity":"429d9f64-b027-4fca-aa54-b2e9e45844dd","added_by":"auto","created_at":"2025-09-09 16:05:03","extension":"png","order_by":5,"title":"Figure 5","display":"","copyAsset":false,"role":"figure","size":25359,"visible":true,"origin":"","legend":"\u003cp\u003eThe nomogram ROC curves for predicting 1- (A), 3- (B), and 5 (C) OS in patients with rectal cancer in the validation cohort.\u003c/p\u003e","description":"","filename":"5.png","url":"https://assets-eu.researchsquare.com/files/rs-7234131/v1/fbcfefae09afed9029cf8ac3.png"},{"id":90930703,"identity":"6d4266cd-a69c-4553-9a81-919039c15f9e","added_by":"auto","created_at":"2025-09-09 16:13:03","extension":"png","order_by":6,"title":"Figure 6","display":"","copyAsset":false,"role":"figure","size":72197,"visible":true,"origin":"","legend":"\u003cp\u003eThe calibration curves for 1- (A), 3- (B), and 5-year (C) OS in the validation cohort. The solid line indicates the performance of the prediction model, and the closer to the diagonal dashed line, the more accurate the prediction.\u003c/p\u003e","description":"","filename":"6.png","url":"https://assets-eu.researchsquare.com/files/rs-7234131/v1/b1271aafb4b1443d760e4c45.png"},{"id":90929439,"identity":"40db93c2-6631-4e06-9936-92b8555d0208","added_by":"auto","created_at":"2025-09-09 16:05:03","extension":"png","order_by":7,"title":"Figure 7","display":"","copyAsset":false,"role":"figure","size":57661,"visible":true,"origin":"","legend":"\u003cp\u003eThe DCA curves for 1- (A), 3- (B), and 5-year (C) OS in the validation cohort.\u003c/p\u003e","description":"","filename":"7.png","url":"https://assets-eu.researchsquare.com/files/rs-7234131/v1/eb98b1b14b07ae78e07d28a2.png"},{"id":91149295,"identity":"9abd89fc-357e-48b4-b148-08795c72ee74","added_by":"auto","created_at":"2025-09-12 06:48:32","extension":"pdf","order_by":0,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":1215545,"visible":true,"origin":"","legend":"","description":"","filename":"manuscript.pdf","url":"https://assets-eu.researchsquare.com/files/rs-7234131/v1/33d5072d-9761-4639-a2b5-45b49c49a7fb.pdf"},{"id":90931577,"identity":"389ef4f3-cf13-4ab0-a435-f5b37f6aca35","added_by":"auto","created_at":"2025-09-09 16:21:03","extension":"xlsx","order_by":0,"title":"","display":"","copyAsset":false,"role":"supplement","size":13037,"visible":true,"origin":"","legend":"","description":"","filename":"Table1.xlsx","url":"https://assets-eu.researchsquare.com/files/rs-7234131/v1/fc7aeb6c4b999d64dd4e128f.xlsx"},{"id":90929429,"identity":"5e5bf72c-e392-46d8-bc52-3bdc8b356826","added_by":"auto","created_at":"2025-09-09 16:05:03","extension":"xlsx","order_by":1,"title":"","display":"","copyAsset":false,"role":"supplement","size":10470,"visible":true,"origin":"","legend":"","description":"","filename":"Table2.xlsx","url":"https://assets-eu.researchsquare.com/files/rs-7234131/v1/4417da54f90a2de4b2830cba.xlsx"},{"id":91148796,"identity":"41917454-59ba-4c99-8b52-c73448655713","added_by":"auto","created_at":"2025-09-12 06:45:39","extension":"docx","order_by":2,"title":"","display":"","copyAsset":false,"role":"supplement","size":1655538,"visible":true,"origin":"","legend":"","description":"","filename":"SupplementaryMaterial.docx","url":"https://assets-eu.researchsquare.com/files/rs-7234131/v1/ce976d3e3e7735b4028f4b9c.docx"}],"financialInterests":"No competing interests reported.","formattedTitle":"Prognostic Value of Preoperative ICPI in Rectal Cancer: A Nomogram Based Approach","fulltext":[{"header":"Introduction","content":"\u003cp\u003eColorectal cancer (CRC) is the third most common cancer globally and the second leading cause of cancer-related deaths [\u003cspan citationid=\"CR1\" class=\"CitationRef\"\u003e1\u003c/span\u003e]. Rectal cancer accounts for approximately 30% of all newly diagnosed CRC cases [\u003cspan citationid=\"CR2\" class=\"CitationRef\"\u003e2\u003c/span\u003e]. GLOBOCAN further predicts that by 2040, the annual incidence of CRC will increase from 1.9\u0026nbsp;million new cases in 2020 to 3.6\u0026nbsp;million, with CRC-related deaths rising from 0.93\u0026nbsp;million to 1.6\u0026nbsp;million during the same period [\u003cspan citationid=\"CR3\" class=\"CitationRef\"\u003e3\u003c/span\u003e]. Radical resection surgery for rectal cancer is currently the primary treatment method, and with the widespread adoption of rectal cancer screening, significant improvements have been made in treatment outcomes and patient prognosis. Rectal cancer prognosis and treatment decisions currently depend on the TNM staging system [\u003cspan citationid=\"CR4\" class=\"CitationRef\"\u003e4\u003c/span\u003e], but its accuracy is lacking [\u003cspan citationid=\"CR5\" class=\"CitationRef\"\u003e5\u003c/span\u003e, \u003cspan citationid=\"CR6\" class=\"CitationRef\"\u003e6\u003c/span\u003e]. Thus, creating a simple, precise model to predict survival is crucial and complements the TNM system.\u003c/p\u003e\u003cp\u003eThe tumor microenvironment has garnered increasing attention [\u003cspan citationid=\"CR7\" class=\"CitationRef\"\u003e7\u003c/span\u003e], with various inflammatory cells and mediators constituting a vital component of this microenvironment. Consequently, inflammation is recognized as the seventh hallmark of cancer [\u003cspan citationid=\"CR8\" class=\"CitationRef\"\u003e8\u003c/span\u003e] and has been demonstrated to be associated with the initiation, progression, and development of several malignancies [\u003cspan citationid=\"CR9\" class=\"CitationRef\"\u003e9\u003c/span\u003e, \u003cspan citationid=\"CR10\" class=\"CitationRef\"\u003e10\u003c/span\u003e, \u003cspan citationid=\"CR11\" class=\"CitationRef\"\u003e11\u003c/span\u003e]. It represents a non-negligible factor influencing the clinical outcomes of cancer patients. Preoperative blood components, as simple, accurate, and easily accessible samples, have been studied for their prognostic value in various cancers, including gastric cancer, colorectal cancer, hepatocellular carcinoma, and lung cancer [\u003cspan citationid=\"CR12\" class=\"CitationRef\"\u003e12\u003c/span\u003e, \u003cspan citationid=\"CR13\" class=\"CitationRef\"\u003e13\u003c/span\u003e, \u003cspan citationid=\"CR14\" class=\"CitationRef\"\u003e14\u003c/span\u003e]. In the field of cancer treatment, biomarkers are typically categorized into three major groups: (1) those capable of definitively diagnosing cancer, (2) those serving as key indicators for assessing patient prognosis, and (3) those used to predict the effectiveness of treatment responses or the risk of potential side effects. The NLR, PLR, and MLR are commonly used as inflammatory biomarkers and play significant roles in cancer prognosis [\u003cspan citationid=\"CR15\" class=\"CitationRef\"\u003e15\u003c/span\u003e, \u003cspan citationid=\"CR16\" class=\"CitationRef\"\u003e16\u003c/span\u003e]. However, due to the diversity of peripheral blood inflammatory markers and their derivatives, the use of a single marker to predict the prognosis of rectal cancer patients has varying degrees of limitations. Consequently, there is an urgent need for a composite inflammatory index to address this issue. In recent years, the ICPI has demonstrated significant value in prognostic prediction for gastric cancer due to its comprehensive assessment of inflammatory and immune imbalance. The ICPI was validated for predicting postoperative recurrence in gastric cancer cohorts. However, its applicability in rectal cancer remains unexplored due to the inherent differences in immune microenvironment, metastatic patterns, and treatment responses between rectal cancer and gastric cancer[\u003cspan citationid=\"CR17\" class=\"CitationRef\"\u003e17\u003c/span\u003e].\u003c/p\u003e\u003cp\u003eThe combination of machine learning (ML) and medical data analysis has been applied in multiple research studies and has demonstrated promising predictive performance. A key advantage of ML is its ability to correlate multiple variables and accurately predict outcomes [\u003cspan citationid=\"CR18\" class=\"CitationRef\"\u003e18\u003c/span\u003e, \u003cspan citationid=\"CR19\" class=\"CitationRef\"\u003e19\u003c/span\u003e]. Consequently, several ML prediction models have recently been employed for disease diagnosis, prognosis prediction, and clinical decision-making. The primary distinction from traditional rule-based algorithms is their capability to utilize vast amounts of new data and to improve and learn over time.\u003c/p\u003e\u003cp\u003eThis study aims to investigate the predictive role of the Inflammation-based ICPI on survival in rectal cancer patients, employ machine learning to screen variables, and ultimately construct a nomogram to assist medical professionals in devising more personalized treatment plans.\u003c/p\u003e"},{"header":"Materials and methods","content":"\u003cp\u003e\u003cb\u003eStudy populations\u003c/b\u003e\u003c/p\u003e\u003cp\u003eThis study retrospectively collected the clinicopathological data of patients who were diagnosed with rectal cancer and underwent laparoscopic surgery for rectal cancer at the Second Affiliated Hospital of Soochow University between January 2016 and January 2021.\u003c/p\u003e\u003cp\u003eInclusion criteria: (1) Histopathologically confirmed primary rectal adenocarcinoma both preoperatively and postoperatively; (2) Undergoing laparoscopic radical resection; (3) Availability of complete and verifiable clinicopathological records; (4) Absence of distant metastasis confirmed through preoperative imaging assessments ( T1\u0026ndash;3/N0\u0026ndash;1M0 ( I-III stage )).\u003c/p\u003e\u003cp\u003eExclusion criteria: (1) Bulky tumors precluding laparoscopic approach or necessitating open conversion; (2) Emergency interventions for tumor-induced intestinal obstruction; (3) Prior neoadjuvant radiotherapy or chemotherapy; (4) Metastatic rectal malignancies (non-primary lesions) (Fig.\u0026nbsp;\u003cspan refid=\"Fig1\" class=\"InternalRef\"\u003e1\u003c/span\u003e).\u003c/p\u003e\u003cp\u003e\u003c/p\u003e\u003cp\u003e\u003cb\u003eData collection and definition\u003c/b\u003e\u003c/p\u003e\u003cp\u003eThe following indicators were systematically and retrospectively collected: (1) Basic patient characteristics: gender, age, American Society of Anesthesiologists (ASA) score, and comorbidities (hypertension, diabetes). (2) Laboratory test data: neutrophil count (\u0026times;109/L), monocyte count (\u0026times;109/L), and CEA within two weeks before surgery. (3) Intraoperative and postoperative data: operation time, pathological results, postoperative hospital stay, and whether radiotherapy or chemotherapy was administered after surgery. (4) Calculation of relevant biomarkers: NLR\u0026thinsp;=\u0026thinsp;neutrophil count (\u0026times;10^9/L) / lymphocyte count (\u0026times;10^9/L). PLR\u0026thinsp;=\u0026thinsp;platelet count (\u0026times;10^9/L) / lymphocyte count (\u0026times;10^9/L). MLR\u0026thinsp;=\u0026thinsp;monocyte count (\u0026times;10^9/L) / lymphocyte count (\u0026times;10^9/L). ICPI\u0026thinsp;=\u0026thinsp;HR\u003csub\u003eNLR\u003c/sub\u003e*NLR\u0026thinsp;+\u0026thinsp;HR\u003csub\u003ePLR\u003c/sub\u003e*PLR\u0026thinsp;+\u0026thinsp;HR\u003csub\u003eMLR\u003c/sub\u003e*MLR.\u003c/p\u003e\u003cp\u003e\u003cb\u003eFollow-up visits\u003c/b\u003e\u003c/p\u003e\u003cp\u003eThis study implemented a dual-track follow-up protocol utilizing outpatient reviews and structured telephone interviews. Surveillance commenced at 1-month postoperative with escalating intervals: monthly-to-quarterly during year 1, biannually during year 2, and annually thereafter. Follow-up concluded at December 2023 or patient demise, whichever occurred first. The primary endpoint was overall survival (OS), calculated from surgery date until death or last confirmed follow-up.\u003c/p\u003e\u003cdiv id=\"Sec3\" class=\"Section2\"\u003e\u003ch2\u003eStatistical analysis\u003c/h2\u003e\u003cp\u003eAll statistical analyses were conducted in R (v4.4.0; R Foundation). Cox proportional hazards regression modeling was implemented using the cph function (rms package), with subsequent nomogram construction via the nomogram function. Continuous variables were analyzed with Mann-Whitney U tests and reported as median, while categorical variables underwent χ\u0026sup2; testing and were summarized as frequencies (percentages). Group survival differences were assessed through Kaplan-Meier curves with log-rank testing. Intergroup comparisons utilized t-tests or χ\u0026sup2; tests as appropriate. Cox regression outcomes were expressed as hazard ratios (HR) with 95% confidence intervals. Statistical significance was defined as two-tailed p\u0026thinsp;\u0026lt;\u0026thinsp;0.05.\u003c/p\u003e\u003c/div\u003e"},{"header":"Results","content":"\u003cp\u003e\u003cstrong\u003ePatients\u0026apos; characteristics\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eAfter exclusion, a total of 357 patients were enrolled, among which 118 patients had died, while 239 patients were still alive. Differences were observed between the two groups in terms of age, ASA grade, pN stage, TNM stage, differentiation type, nerve invasion, vascular invasion, CEA levels, surgical time, postoperative chemotherapy, neutrophil count, monocyte count, NLR, and MLR (P\u0026thinsp;\u0026lt;\u0026thinsp;0.05) (\u003cstrong\u003eSupplementary Table \u003cspan class=\"InternalRef\"\u003eS1\u003c/span\u003e\u003c/strong\u003e). The median age of the enrolled patients was 65 years, including 218 males (61.06%) and 139 females (38.94%). Among the enrolled patients, 125 had hypertension and 43 had diabetes. No significant differences were observed between the baseline characteristics of the training cohort and the validation cohort (\u003cstrong\u003eTable\u0026nbsp;1\u003c/strong\u003e), and no significant differences were noted in the Kaplan-Meier survival curves between the two cohorts (\u003cstrong\u003eSupplementary Figure \u003cspan class=\"InternalRef\"\u003eS1\u003c/span\u003e\u003c/strong\u003e).\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eDetermine the optimal cutoff values of ICPI\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eIn order to identify the optimal cutoff values for inflammatory markers such as NLR, PLR, MLR, and ICPI, we employed the maximum selected log-rank statistic (\u003cstrong\u003eSupplementary Figure S2A,B,C,D\u003c/strong\u003e). Significant differences in Kaplan-Meier curves were observed between the two groups at NLR\u0026thinsp;=\u0026thinsp;3.0, PLR\u0026thinsp;=\u0026thinsp;171.8, and MLR\u0026thinsp;=\u0026thinsp;0.32 (P\u0026thinsp;\u0026lt;\u0026thinsp;0.001) (Fig. 2A, \u003cstrong\u003eB, C\u003c/strong\u003e). The ICPI was defined using the methodology proposed by Noriyuki Hirahara et al[\u003cspan class=\"CitationRef\"\u003e17\u003c/span\u003e], where the formula was derived from hazard ratios. Binary scoring (1/0) was applied when MLR\u0026thinsp;\u0026gt;\u0026thinsp;0.32, NLR\u0026thinsp;\u0026ge;\u0026thinsp;3.0, and PLR\u0026thinsp;\u0026ge;\u0026thinsp;171.8 respectively, with subsequent calculation using the formula: ICPI\u0026thinsp;=\u0026thinsp;2.4NLR\u0026thinsp;+\u0026thinsp;2.3PLR\u0026thinsp;+\u0026thinsp;3.1MLR. At an ICPI value of 4.3, significant differences in Kaplan-Meier curves were observed between the two groups (P\u0026thinsp;\u0026lt;\u0026thinsp;0.001) (Fig.\u0026nbsp;2D). When comparing the survival and death groups, statistically significant differences were noted for NLR and MLR (P\u0026thinsp;\u0026lt;\u0026thinsp;0.05), whereas no significant difference was observed for PLR. Nevertheless, the ICPI, which was constructed using these three indicators, exhibited significant differences between the two groups (\u003cstrong\u003eSupplementary Table \u003cspan class=\"InternalRef\"\u003eS1\u003c/span\u003e\u003c/strong\u003e). Furthermore, patients belonging to the high NLR, PLR, MLR, and ICPI groups exhibited inferior OS outcomes (Fig. 2A, \u003cstrong\u003eB, C\u003c/strong\u003e).\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eVariable selection\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eLasso regression, XGBoost, and random forest were used for variable selection, and the intersection of important variables selected by the three machine learning methods was represented in a Venn diagram. Random forest provides variable importance measures through permutation. For random forest, we performed analysis through minimum depth variable selection and ultimately identified 7 variables as important (Fig.\u0026nbsp;3A). The LASSO regression model included 18 variables. The selection criterion was based on lambda. min and the model showed the best fit at lambda. min\u0026thinsp;=\u0026thinsp;0.034 (Fig.\u0026nbsp;3B). Finally, 8 candidate variables with non-zero coefficients were selected (Fig.\u0026nbsp;3B). Currently, there is no consensus on the number of important variables selected by XGBoost. We selected the top 10 variables based on their importance (Fig.\u0026nbsp;3C). The important variables selected by machine learning were: Age, differentiation type, pN stage, CEA, surgical time, and ICPI (Fig.\u0026nbsp;3D). Subsequently, we included the selected important variables in a multivariate COX regression analysis, and the results showed that pN stage, CEA, surgical time, ICPI, and age were independent prognostic factors for patients undergoing laparoscopic rectal cancer surgery (P\u0026thinsp;\u0026lt;\u0026thinsp;0.05) (\u003cstrong\u003eTable\u0026nbsp;2\u003c/strong\u003e).\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eConstruction and verification of the nomogram prediction model for OS\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eA nomogram model for predicting OS in rectal cancer was constructed based on independent prognostic factors selected from the training cohort using machine learning and multivariate Cox regression results. Each variable was assigned a score based on its HR. The total score of each variable was added, and its corresponding position on the total score scale was determined to obtain the probabilities of OS at 1, 3, and 5 years (Fig. \u003cspan class=\"InternalRef\"\u003e4\u003c/span\u003e). The ROC analysis of the nomogram showed AUCs of 0.848, 0.861, and 0.851 for 1-year, 3-year, and 5-year OS, respectively, in the training cohort (\u003cstrong\u003eSupplementary Figure S3\u003c/strong\u003e); while in the validation cohort, the AUCs were 0.829, 0.857, and 0.824 (Fig. \u003cspan class=\"InternalRef\"\u003e5\u003c/span\u003e,A,B,C). The C-index was used to validate the nomogram constructed in the training set, with values of 0.809 (95% CI: 0.768\u0026ndash;0.851) and 0.786 (95% CI: 0.722\u0026ndash;0.849) in the training and validation cohorts, respectively. The time-dependent ROC curves in the validation cohort tended to stabilize over time (\u003cstrong\u003eSupplementary Figure S4\u003c/strong\u003e). In both the training cohort (\u003cstrong\u003eSupplementary Figure S5\u003c/strong\u003e) and the validation cohort (Fig. \u003cspan class=\"InternalRef\"\u003e6\u003c/span\u003e,A,B,C), the nomogram calibration curves demonstrate a high degree of agreement between the observed and predicted probabilities. Furthermore, DCA was employed to assess the clinical utility of the nomogram, revealing significant positive net benefits in both the training cohort (\u003cstrong\u003eSupplementary Figure S6\u003c/strong\u003e) and the validation cohort (Fig.\u0026nbsp;7,\u003cstrong\u003eA,B,C\u003c/strong\u003e), indicating its important clinical applicability in predicting OS among patients undergoing laparoscopic rectal cancer surgery.\u003c/p\u003e"},{"header":"Discussion","content":"\u003cp\u003eIn this study, we have, for the first time, explored the relationship between ICPI and OS in patients undergoing laparoscopic rectal cancer surgery. We have discovered, for the first time, that patients with high ICPI have worse prognosis compared to those with low ICPI. Additionally, NLR, PLR, and MLR all exhibited a similar trend, indicating that patients with high inflammatory indices have a poorer prognosis. Conversely, patients with low inflammatory indices had a better prognosis. Furthermore, we utilized machine learning to screen variables, ultimately constructing a nomogram for predicting prognosis in rectal cancer patients. This nomogram exhibits high efficacy and clinical benefits. Our findings may contribute to a deeper understanding of the nature of the relationship between ICPI and survival in rectal cancer patients. While neoadjuvant therapy is increasingly used, upfront surgery persists in early-stage disease and resource-constrained settings. Our model addresses an unmet need in these scenarios. Consequently, they offer valuable references for prognostic assessment, treatment outcome prediction, and follow-up monitoring of rectal cancer patients.\u003c/p\u003e\u003cp\u003eIn the tumor-induced systemic environment, numerous inflammatory cytokines are involved in the development of colorectal cancer cell invasion and metastasis [\u003cspan citationid=\"CR20\" class=\"CitationRef\"\u003e20\u003c/span\u003e]. Tumors can also trigger local inflammatory responses and release proinflammatory cytokines, leading to the formation of an inflammatory microenvironment [\u003cspan citationid=\"CR21\" class=\"CitationRef\"\u003e21\u003c/span\u003e, \u003cspan citationid=\"CR22\" class=\"CitationRef\"\u003e22\u003c/span\u003e, \u003cspan citationid=\"CR23\" class=\"CitationRef\"\u003e23\u003c/span\u003e]. The role of lymphocytes in tumor immune surveillance and immune editing has been extensively studied [\u003cspan citationid=\"CR24\" class=\"CitationRef\"\u003e24\u003c/span\u003e]. Lymphocytes primarily play an antitumor defense role. They induce cytotoxic cell death and produce cytokines that inhibit cancer cell proliferation and metastatic activity [\u003cspan citationid=\"CR25\" class=\"CitationRef\"\u003e25\u003c/span\u003e]. Neutrophils may contribute to tumor progression. Neutrophils are the primary source of vascular endothelial growth factor (VEGF) [\u003cspan citationid=\"CR26\" class=\"CitationRef\"\u003e26\u003c/span\u003e] and release prostaglandin E2 to amplify inflammation and create a tumor microenvironment, thereby promoting colorectal tumorigenesis through the secretion of interleukin-1β and matrix metalloproteinases, inhibiting natural killer cell activity and increasing tumor cell infiltration [\u003cspan citationid=\"CR24\" class=\"CitationRef\"\u003e24\u003c/span\u003e]. Additionally, neutrophils can degrade the basement membrane, mediating local tumor invasion and the formation of distant metastases [\u003cspan citationid=\"CR27\" class=\"CitationRef\"\u003e27\u003c/span\u003e]. Studies have shown that platelets also play a role in tumor progression [\u003cspan citationid=\"CR28\" class=\"CitationRef\"\u003e28\u003c/span\u003e, \u003cspan citationid=\"CR29\" class=\"CitationRef\"\u003e29\u003c/span\u003e]. In the tumor microenvironment, platelets promote angiogenesis by releasing proangiogenic proteins such as VEGF and transforming growth factor-β. In the tumor microenvironment, platelets can promote angiogenesis by releasing angiogenic proteins (such as vascular endothelial growth factor and transforming growth factor-β), thereby promoting tumorigenesis. Platelet-derived growth factor produced by platelets also plays a crucial role in promoting tumor growth and invasion [\u003cspan citationid=\"CR30\" class=\"CitationRef\"\u003e30\u003c/span\u003e]. Furthermore, cytokines and chemokines produced by platelets can promote cancer-related inflammation [\u003cspan citationid=\"CR30\" class=\"CitationRef\"\u003e30\u003c/span\u003e, \u003cspan citationid=\"CR31\" class=\"CitationRef\"\u003e31\u003c/span\u003e, \u003cspan citationid=\"CR32\" class=\"CitationRef\"\u003e32\u003c/span\u003e]. This serves as one of the strong evidence for platelets' role in tumor progression. Monocytes may also act as \"boosters\" for tumor cells. Monocytes in the blood can produce reactive oxygen species, reactive nitrogen species, and other cytokines, inhibiting lymphocyte activation, which leads to DNA mutations and tumor progression [\u003cspan citationid=\"CR32\" class=\"CitationRef\"\u003e32\u003c/span\u003e]. Therefore, the calculation formulas for NLR, PLR, and MLR also indicate that a higher level of inflammatory status predicts a poorer survival outcome, which is consistent with our research findings.\u003c/p\u003e\u003cp\u003eNLR, PLR, and MLR, each focusing on distinct aspects of host inflammation and immunity, have been consistently validated as valuable indicators across multiple studies [\u003cspan citationid=\"CR15\" class=\"CitationRef\"\u003e15\u003c/span\u003e, \u003cspan citationid=\"CR16\" class=\"CitationRef\"\u003e16\u003c/span\u003e]. Currently, various inflammatory indices have been utilized to predict the prognosis of colorectal cancer. In a large cohort study involving 1,260 colorectal cancer patients, the relationship between the C-reactive protein-albumin-lymphocyte (CALLY) score and the prognosis of colorectal cancer was explored. The study found that the C-index of the nomogram constructed based on the CALLY score was 0.784, which is lower than that of our study (0.809) [\u003cspan citationid=\"CR43\" class=\"CitationRef\"\u003e43\u003c/span\u003e]. Another study combined tumor markers with the systemic immune-inflammation index to predict the prognosis of colorectal cancer, and the C-index of their constructed nomogram was 0.723, which is also lower than that of our study. These findings demonstrate the excellent predictive performance of our study [\u003cspan citationid=\"CR44\" class=\"CitationRef\"\u003e44\u003c/span\u003e].In our research, each inflammatory biomarker exhibited significant differences in univariate analysis. The innovative ICPI, which ingeniously integrates these three inflammatory indicators, provides a more comprehensive assessment of patients' inflammatory and immune status, thereby enhancing the accuracy of cancer prognosis prediction. Notably, our concurrent application of three machine learning variable selection processes consistently identified ICPI as a pivotal variable, underlining its robustness within the model. Furthermore, after multivariate Cox regression analysis, pN stage, CEA, surgical time, and age were also recognized as critical variables influencing the prognosis of patients undergoing laparoscopic rectal cancer surgery, aligning with previous findings [\u003cspan citationid=\"CR33\" class=\"CitationRef\"\u003e33\u003c/span\u003e, \u003cspan citationid=\"CR34\" class=\"CitationRef\"\u003e34\u003c/span\u003e, \u003cspan citationid=\"CR35\" class=\"CitationRef\"\u003e35\u003c/span\u003e].Hence, for patients with a high ICPI level, preoperative intervention is highly necessary, and aggressive anti-inflammatory treatment should be administered. This includes:The use of medications such as antibiotics and glucocorticoids. However, it is important to note that anti-inflammatory treatment should be individualized based on the patient's specific condition to avoid overtreatment or undertreatment.Nutritional support: High inflammation levels often indicate high catabolism, thus nutritional support should be enhanced to improve the patient's nutritional status and immune function [\u003cspan citationid=\"CR36\" class=\"CitationRef\"\u003e36\u003c/span\u003e].Regular monitoring and assessment: During the course of treatment, the patient's ICPI indicators, as well as clinical manifestations and radiological findings, should be regularly monitored. Treatment plans should be adjusted promptly based on monitoring results to ensure the effectiveness and safety of the treatment. Given our consideration that neoadjuvant therapy may affect patients' inflammatory levels, our study did not enroll patients who had undergone neoadjuvant therapy. However, studies have also shown that even among patients who received neoadjuvant therapy, those with higher NLR, PLR, and MLR exhibited poorer prognoses[\u003cspan citationid=\"CR45\" class=\"CitationRef\"\u003e45\u003c/span\u003e, \u003cspan citationid=\"CR46\" class=\"CitationRef\"\u003e46\u003c/span\u003e].\u003c/p\u003e\u003cp\u003eTumor location is also recognized as an important predictor of postoperative OS in rectal cancer patients [\u003cspan citationid=\"CR37\" class=\"CitationRef\"\u003e37\u003c/span\u003e]. Cheng et al [\u003cspan citationid=\"CR38\" class=\"CitationRef\"\u003e38\u003c/span\u003e] classified T3/T4 rectal cancer patients who underwent surgery into high and mid/low rectal cancer groups, and found that patients with stage III high rectal cancer had a better prognosis than those with mid/low rectal cancer, indicating that tumor location is an independent prognostic factor for long-term survival. However, other studies have reached different conclusions, suggesting that tumor location does not affect long-term outcomes. Bhangu et al [\u003cspan citationid=\"CR39\" class=\"CitationRef\"\u003e39\u003c/span\u003e]concluded that the tumor location in rectal cancer, whether high or low, does not result in worse survival rates after radical surgery, with low rectal cancer demonstrating comparable oncologic outcomes compared to mid/high rectal cancer. Similarly, Khan et al [\u003cspan citationid=\"CR40\" class=\"CitationRef\"\u003e40\u003c/span\u003e] found that although the level of rectal cancer affected the use of neoadjuvant therapy and R0 resection rates, it did not impact recurrence rates and long-term survival. Additionally, postoperative complications may also influence the prognosis of rectal cancer patients [\u003cspan citationid=\"CR41\" class=\"CitationRef\"\u003e41\u003c/span\u003e]. Several studies have shown an association between anastomotic leakage (AL) and disease recurrence, as well as OS, while other studies have not found adverse effects on tumor outcomes[\u003cspan citationid=\"CR42\" class=\"CitationRef\"\u003e42\u003c/span\u003e]. This may depend on the different definitions of AL used in various studies. It is noteworthy that in our study, ICPI and operative time were identified as more significant prognostic factors than adjuvant chemoradiotherapy. This may be associated with the preoperative systemic inflammatory response, which can directly facilitate metastasis by promoting angiogenesis and suppressing anti-tumour immunity [\u003cspan citationid=\"CR47\" class=\"CitationRef\"\u003e47\u003c/span\u003e]. Furthermore, recent studies suggest that an inflammatory microenvironment may reduce sensitivity to chemoradiotherapy[\u003cspan citationid=\"CR48\" class=\"CitationRef\"\u003e48\u003c/span\u003e]. Additionally, animal experiments indicate that prolonged mechanical manipulation during surgery might enhance the release of circulating tumour cells [\u003cspan citationid=\"CR49\" class=\"CitationRef\"\u003e49\u003c/span\u003e]. These mechanisms may collectively explain why operative time and ICPI emerged as independent prognostic determinants surpassing the impact of adjuvant therapy.\u003c/p\u003e\u003cp\u003eHowever, it is crucial to note that the optimal combination and cut-off values may vary according to cancer types. Moreover, various anticancer treatments can differentially impact the systemic inflammatory state. Therefore, a tailored approach focusing on specific cancer types is imperative to accurately assess the prognostic implications of inflammation-related biomarkers. While ctDNA emerges as a sensitive prognostic tool, ICPI offers an economical alternative for settings lacking advanced molecular testing. Future studies should explore combining inflammatory indices with ctDNA for precision prognostication.\u003c/p\u003e\u003cp\u003eCertainly, this study has several limitations. Firstly, this study was a retrospective study conducted at a single center, and the number of enrolled patients was relatively small, which may have increased bias in sample selection and analysis. Further validation with a larger sample size from multiple centers is needed. Secondly, this study only included patients in stages I-III, and we did not conduct subgroup analysis for patients with distant metastasis or postoperative adjuvant therapy. While generalizability to neoadjuvant-treated cohorts requires further validation, this study delivers prognostic decision support for patients undergoing upfront surgery. Moreover, the relatively high proportion of Stage I patients in our study has led to an imbalance in the staging of the included patient data. Additionally, we have only explored the relationship between ICPI and OS, and have not investigated the relationship between recurrence-free survival and ICPI. This represents a limitation of our study.Therefore, further investigation is needed to understand the prognostic significance of ICPI in rectal cancer patients with distant metastasis. Lastly, the results of peripheral blood cell analysis are susceptible to factors such as blood circulation, infection, and nutritional status, which may lead to changes in inflammatory indicators and thus affect the outcome.\u003c/p\u003e\u003cp\u003eNonetheless, our study is valuable as it is the first to discover a significant correlation between ICPI and OS in patients undergoing laparoscopic rectal cancer surgery. Furthermore, we have successfully developed a nomogram based on ICPI and three other independent prognostic parameters from multivariate analysis to predict OS in rectal cancer patients.\u003c/p\u003e"},{"header":"Conclusions","content":"\u003cp\u003eThrough our research, preoperative ICPI is an effective indicator for assessing the prognosis of patients undergoing laparoscopic rectal cancer surgery and may provide assistance for anti-inflammatory therapy. Secondly, we developed and validated a nomogram using machine learning to predict the overall survival of patients undergoing laparoscopic rectal cancer surgery, and it demonstrated excellent predictive performance.\u003c/p\u003e"},{"header":"Abbreviations","content":"\u003cp\u003eICPI, inflammatory combined prognostic index;\u003c/p\u003e\u003cp\u003eNLR, neutrophil-to-lymphocyte ratio;\u003c/p\u003e\u003cp\u003ePLR, platelet-to-lymphocyte ratio;\u003c/p\u003e\u003cp\u003eMLR, monocyte-to-lymphocyte ratiol;\u003c/p\u003e\u003cp\u003eRF random forest decision tree;\u003c/p\u003e\u003cp\u003eBMI body mass index;\u003c/p\u003e\u003cp\u003eRC rectal cancer;\u003c/p\u003e\u003cp\u003eML machine learning;\u003c/p\u003e\u003cp\u003eASA American Society of Anesthesiologists;\u003c/p\u003e\u003cp\u003eAUC Area under the receiver operating characteristic curve;\u003c/p\u003e\u003cp\u003eROC Receiver operating characteristic curve;\u003c/p\u003e\u003cp\u003eHR, hazard ratios\u003c/p\u003e"},{"header":"Declarations","content":"\u003cp\u003e\u003cstrong\u003eEthics approval and consent to participate\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eIt complies with the World Medical Association Declaration of Helsinki in 1964 and subsequently amended versions.\u0026nbsp;The Ethics Committee of the Second Affiliated Hospital of Soochow University approved our retrospective study(JD-HG-2024-051). The Ethics Committee of the Second Affiliated Hospital of Soochow University waived the need for patient approval or informed consent. As this is a retrospective study, patient information has been anonymized prior to the use of these data, and all data have undergone encryption processing, with access restricted to authorized personnel only.\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eConsent for publication\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eNot applicable.\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eAvailability of data and materials\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eThe data sets analyzed during the current study are not publicly available for patient privacy purposes but are available from the corresponding author (Wu) upon reasonable request.\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eCompeting Interests\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eThe authors declare no competing interests.\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eFunding\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eThe present study was supported by the Suzhou Science and Technology Bureau (No.SKY2022156).\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eAuthor contributions\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eXiangyong Li and Yong Wu conceptualized and designed the work. Xiangyong Li and Yan Zhou collected all the data. Xiangyong Li and Yan Zhou drafted and analyzed the manuscript. Xiaodong Yang, Yong Wu and Chungen Xing reviewed and revised the manuscript. All authors have read and approved the final work.\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eAcknowledgements\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eNot applicable\u003c/p\u003e"},{"header":"References","content":"\u003col\u003e\u003cli\u003e\u003cspan\u003eBray F, Laversanne M, Sung H, et al. Global cancer statistics 2022: GLOBOCAN estimates of incidence and mortality worldwide for 36 cancers in 185 countries. CA Cancer J Clin. 2024;74:229\u0026ndash;63.\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eSiegel RL, Wagle NS, Cercek A, Smith RA, Jemal A. Colorectal cancer statistics, 2023. CA Cancer J Clin. 2023;73:233\u0026ndash;54.\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eMorgan E, Arnold M, Gini A, et al. Global burden of colorectal cancer in 2020 and 2040: incidence and mortality estimates from GLOBOCAN. Gut. 2023;72:338\u0026ndash;44.\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eAmin MB, Greene FL, Edge SB, et al. The Eighth Edition AJCC Cancer Staging Manual: Continuing to build a bridge from a population-based to a more personalized approach to cancer staging. CA Cancer J Clin. 2017;67:93\u0026ndash;9.\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eQuirke P, Williams GT, Ectors N, Ensari A, Piard F, Nagtegaal I. The future of the TNM staging system in colorectal cancer: time for a debate? Lancet Oncol. 2007;8:651\u0026ndash;7.\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eUeno H, Mochizuki H, Akagi Y, et al. Optimal colorectal cancer staging criteria in TNM classification. J Clin Oncol. 2012;30:1519\u0026ndash;26.\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eQuail DF, Joyce JA. Microenvironmental regulation of tumor progression and metastasis. Nat Med. 2013;19:1423\u0026ndash;37.\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eDiakos CI, Charles KA, McMillan DC, Clarke SJ. Cancer-related inflammation and treatment effectiveness. Lancet Oncol. 2014;15:e493\u0026ndash;503.\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eJohnson CE, Alberg AJ, Bandera EV, et al. Association of inflammation-related exposures and ovarian cancer survival in a multi-site cohort study of Black women. Br J Cancer. 2023;129:1119\u0026ndash;25.\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eXie HL, Ruan GT, Wei L, et al. The prognostic value of the combination of body composition and systemic inflammation in patients with cancer cachexia. J Cachexia Sarcopenia Muscle. 2023;14:879\u0026ndash;90.\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eWang P, Wang S, Sun Z, et al. Systemic inflammation influences the prognosis of patients with radically resected non-small cell lung cancer and correlates with the immunosuppressive microenvironment. Int J Cancer. 2023;153:826\u0026ndash;42.\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eZhou D, Wu Y, Zhu Y, Lin Z, Yu D, Zhang T. The Prognostic Value of Neutrophil-to-lymphocyte Ratio and Monocyte-to-lymphocyte Ratio in Metastatic Gastric Cancer Treated with Systemic Chemotherapy. J Cancer. 2020;11:4205\u0026ndash;12.\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eNost TH, Alcala K, Urbarova I, et al. Systemic inflammation markers and cancer incidence in the UK Biobank. Eur J Epidemiol. 2021;36:841\u0026ndash;8.\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eSong M, Zhang Q, Song C, et al. The advanced lung cancer inflammation index is the optimal inflammatory biomarker of overall survival in patients with lung cancer. J Cachexia Sarcopenia Muscle. 2022;13:2504\u0026ndash;14.\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eDiem S, Schmid S, Krapf M, et al. Neutrophil-to-Lymphocyte ratio (NLR) and Platelet-to-Lymphocyte ratio (PLR) as prognostic markers in patients with non-small cell lung cancer (NSCLC) treated with nivolumab. Lung Cancer. 2017;111:176\u0026ndash;81.\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eYamamoto T, Kawada K, Obama K. Inflammation-Related Biomarkers for the Prediction of Prognosis in Colorectal Cancer Patients. Int J Mol Sci. 2021;22.\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eHirahara N, Matsubara T, Kaji S, et al. Novel inflammation-combined prognostic index to predict survival outcomes in patients with gastric cancer. Oncotarget. 2023;14:71\u0026ndash;82.\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003ePainuli D, Bhardwaj S, K\u0026ouml;se U. Recent advancement in cancer diagnosis using machine learning and deep learning techniques: A comprehensive review. Comput Biol Med. 2022;146:105580.\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eEl-Sherbini AH, Coroneos S, Zidan A, Othman M. Machine Learning as a Diagnostic and Prognostic Tool for Predicting Thrombosis in Cancer Patients: A Systematic Review. Semin Thromb Hemost. 2024;50:809\u0026ndash;16.\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eCrusz SM, Balkwill FR. Inflammation and cancer: advances and new agents. Nat Rev Clin Oncol. 2015;12:584\u0026ndash;96.\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eGreten FR, Grivennikov SI. Inflammation and Cancer: Triggers, Mechanisms, and Consequences. Immunity. 2019;51:27\u0026ndash;41.\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eAnderson NM, Simon MC. The tumor microenvironment. Curr Biol. 2020;30:R921\u0026ndash;5.\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eHou J, Karin M, Sun B. Targeting cancer-promoting inflammation - have anti-inflammatory therapies come of age? Nat Rev Clin Oncol. 2021;18:261\u0026ndash;79.\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eGubin MM, Vesely MD. Cancer Immunoediting in the Era of Immuno-oncology. Clin Cancer Res. 2022;28:3917\u0026ndash;28.\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eKilincalp S, \u0026Ccedil;oban Ş, Akinci H, et al. Neutrophil/lymphocyte ratio, platelet/lymphocyte ratio, and mean platelet volume as potential biomarkers for early detection and monitoring of colorectal adenocarcinoma. Eur J Cancer Prev. 2015;24:328\u0026ndash;33.\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eMcCourt M, Wang JH, Sookhai S, Redmond HP. Proinflammatory mediators stimulate neutrophil-directed angiogenesis. Arch Surg. 1999;134:1325\u0026ndash;31. discussion 1331\u0026thinsp;\u0026ndash;\u0026thinsp;1322.\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eHuh SJ, Liang S, Sharma A, Dong C, Robertson GP. Transiently entrapped circulating tumor cells interact with neutrophils to facilitate lung metastasis development. Cancer Res. 2010;70:6071\u0026ndash;82.\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eWojtukiewicz MZ, Sierko E, Hempel D, Tucker SC, Honn KV. Platelets and cancer angiogenesis nexus. Cancer Metastasis Rev. 2017;36:249\u0026ndash;62.\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eStojkovic Lalosevic M, Pavlovic Markovic A, Stankovic S, et al. Combined Diagnostic Efficacy of Neutrophil-to-Lymphocyte Ratio (NLR), Platelet-to-Lymphocyte Ratio (PLR), and Mean Platelet Volume (MPV) as Biomarkers of Systemic Inflammation in the Diagnosis of Colorectal Cancer. Dis Markers. 2019;2019:6036979.\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eZhu X, Cao Y, Lu P, et al. Evaluation of platelet indices as diagnostic biomarkers for colorectal cancer. Sci Rep. 2018;8:11814.\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eKaraman K, Bostanci EB, Aksoy E, et al. The predictive value of mean platelet volume in differential diagnosis of non-functional pancreatic neuroendocrine tumors from pancreatic adenocarcinomas. Eur J Intern Med. 2011;22:e95\u0026ndash;98.\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003ePeterson JE, Zurakowski D, Italiano JE Jr., et al. VEGF, PF4 and PDGF are elevated in platelets of colorectal cancer patients. Angiogenesis. 2012;15:265\u0026ndash;73.\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eJeon Y, Kim YJ, Jeon J, et al. Machine learning based prediction of recurrence after curative resection for rectal cancer. PLoS ONE. 2023;18:e0290141.\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eTakeda Y, Sugano H, Okamoto A, et al. Prognostic usefulness of the C-reactive protein-albumin-lymphocyte (CALLY) index as a novel biomarker in patients undergoing colorectal cancer surgery. Asian J Surg. 2024;47:3492\u0026ndash;8.\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eDuffy MJ. Carcinoembryonic antigen as a marker for colorectal cancer: is it clinically useful? Clin Chem. 2001;47:624\u0026ndash;30.\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eStumpf F, Keller B, Gressies C, Schuetz P. Inflammation and Nutrition: Friend or Foe? Nutrients. 2023; 15(5).\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eYang H, Yao Z, Cui M, et al. Influence of tumor location on short- and long-term outcomes after laparoscopic surgery for rectal cancer: a propensity score matched cohort study. BMC Cancer. 2020;20:761.\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eCheng LJ, Chen JH, Chen SY, et al. Distinct Prognosis of High Versus Mid/Low Rectal Cancer: a Propensity Score-Matched Cohort Study. J Gastrointest Surg. 2019;23:1474\u0026ndash;84.\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eBhangu A, Rasheed S, Brown G, et al. Does rectal cancer height influence the oncological outcome? Colorectal Dis. 2014;16:801\u0026ndash;8.\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eKhan MAS, Ang CW, Hakeem AR, et al. The Impact of Tumour Distance From the Anal Verge on Clinical Management and Outcomes in Patients Having a Curative Resection for Rectal Cancer. J Gastrointest Surg. 2017;21:2056\u0026ndash;65.\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eWarps AK, Tollenaar R, Tanis PJ, et al. Postoperative complications after colorectal cancer surgery and the association with long-term survival. Eur J Surg Oncol. 2022;48:873\u0026ndash;82.\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eEsp\u0026iacute;n E, Ciga MA, Pera M, et al. Oncological outcome following anastomotic leak in rectal surgery. Br J Surg. 2015;102:416\u0026ndash;22.\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eYang M, Lin SQ, Liu XY, et al. Association between C-reactive protein-albumin-lymphocyte (CALLY) index and overall survival in patients with colorectal cancer: From the investigation on nutrition status and clinical outcome of common cancers study. Front Immunol. 2023;14:1131496.\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eXie H, Yuan G, Huang S, et al. The prognostic value of combined tumor markers and systemic immune-inflammation index in colorectal cancer patients. Langenbecks Arch Surg. 2020;405:1119\u0026ndash;30.\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eHuai Q, Luo C, Song P, et al. Peripheral blood inflammatory biomarkers dynamics reflect treatment response and predict prognosis in non-small cell lung cancer patients with neoadjuvant immunotherapy. Cancer Sci. 2023;114:4484\u0026ndash;98.\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eHwang M, Canzoniero JV, Rosner S et al. Peripheral blood immune cell dynamics reflect antitumor immune responses and predict clinical response to immunotherapy. J Immunother Cancer. 2022; 10(6).\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eRoxburgh CS, D, McMillan DC. Cancer and systemic inflammation: treat the tumour and treat the host. Br J Cancer 110,6 (2014): 1409\u0026ndash;12. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003e10.1038/bjc.2014.90\u003c/span\u003e\u003cspan address=\"10.1038/bjc.2014.90\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eHuang Y, et al. Improving immune-vascular crosstalk for cancer immunotherapy. Nat reviews Immunol vol. 2018;18(3):195\u0026ndash;203. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003e10.1038/nri.2017.145\u003c/span\u003e\u003cspan address=\"10.1038/nri.2017.145\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e.\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eRetsky M, et al. Surgery triggers outgrowth of latent distant disease in breast cancer: an inconvenient truth? Cancers 2,2 305\u0026thinsp;\u0026ndash;\u0026thinsp;37. 30 Mar. 2010. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003e10.3390/cancers2020305\u003c/span\u003e\u003cspan address=\"10.3390/cancers2020305\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e.\u003c/span\u003e\u003c/li\u003e\u003c/ol\u003e"},{"header":"Tables","content":"\u003cp\u003eTables 1 and 2 are available in the Supplementary Files section.\u003c/p\u003e"}],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":true,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":false,"hideJournal":false,"highlight":"","institution":"","isAcceptedByJournal":false,"isAuthorSuppliedPdf":false,"isDeskRejected":"","isHiddenFromSearch":false,"isInQc":false,"isInWorkflow":false,"isPdf":false,"isPdfUpToDate":true,"isWithdrawnOrRetracted":false,"journal":{"display":true,"email":"[email protected]","identity":"bmc-cancer","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"bcan","sideBox":"Learn more about [BMC Cancer](http://bmccancer.biomedcentral.com/)","snPcode":"","submissionUrl":"https://www.editorialmanager.com/bcan/default.aspx","title":"BMC Cancer","twitterHandle":"BMC_series","acdcEnabled":true,"dfaEnabled":false,"editorialSystem":"em","reportingPortfolio":"BMC Series","inReviewEnabled":true,"inReviewRevisionsEnabled":true},"keywords":"ICPI, machine learning, rectal cancer, overall survival, prediction nomogram","lastPublishedDoi":"10.21203/rs.3.rs-7234131/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-7234131/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003ch2\u003eObjective\u003c/h2\u003e\u003cp\u003eThis study examines the prognostic significance of preoperative inflammatory combined prognostic index (ICPI) in patients having laparoscopic rectal cancer surgery and constructs a machine learning-derived nomogram to predict patient prognosis.\u003c/p\u003e\u003ch2\u003eMethods\u003c/h2\u003e\u003cp\u003eThis study retrospectively collected patients who underwent laparoscopic rectal cancer surgery from January 2016 to January 2021. Patients receiving neoadjuvant therapy were excluded due to its alteration of inflammatory markers and pathology. The optimal cut-off values for neutrophil-to-lymphocyte ratio (NLR), platelet-to-lymphocyte ratio (PLR), monocyte-to-lymphocyte ratio (MLR), and ICPI were 3.0, 171.82, 0.32, and 4.3, respectively. Prognostic features were identified from the training cohort using three ML methods (Lasso Regression, XGBoost, Random Forest), with consensus features selected through intersection analysis. Cox regression was performed to establish a nomogram for predicting 1-year, 3-year, and 5-year overall survival (OS) in rectal cancer patients. The enhancement in predictive capability and clinical benefit were evaluated through the Concordance Index (C-index), Receiver Operating Characteristic (ROC) curves, calibration curves, and Decision Curve Analysis (DCA).\u003c/p\u003e\u003ch2\u003eResults\u003c/h2\u003e\u003cp\u003eA total of 357 patients were enrolled and randomly divided into a training cohort (70%, n\u0026thinsp;=\u0026thinsp;249) and a validation cohort (30%, n\u0026thinsp;=\u0026thinsp;108).Additionally, patients with high NLR, PLR, MLR, and ICPI had poorer OS (P\u0026thinsp;\u0026lt;\u0026thinsp;0.001). After machine learning and multivariable Cox regression, pN stage, carcinoembryonic antigen (CEA), surgical time, ICPI, and age were identified as independent prognostic factors affecting OS. A nomogram was constructed, and the area under the curve (AUC) values in both the training and validation cohorts exceeded 0.80, with C-indices of 0.80 and 0.79, respectively. The calibration curves demonstrated good agreement between the predicted and actual outcomes, indicating high prediction accuracy. DCA revealed that the nomogram exhibited a higher net benefit.\u003c/p\u003e\u003ch2\u003eConclusion\u003c/h2\u003e\u003cp\u003eICPI integrates multiple inflammatory parameters to predict rectal cancer survival. We also developed a machine learning-based nomogram for predicting OS in laparoscopic rectal cancer surgery patients.\u003c/p\u003e","manuscriptTitle":"Prognostic Value of Preoperative ICPI in Rectal Cancer: A Nomogram Based Approach","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2025-09-09 16:04:58","doi":"10.21203/rs.3.rs-7234131/v1","editorialEvents":[{"type":"communityComments","content":0},{"type":"reviewersInvited","content":"","date":"2025-09-03T08:27:47+00:00","index":"","fulltext":""},{"type":"editorAssigned","content":"","date":"2025-08-28T06:58:58+00:00","index":"","fulltext":""},{"type":"editorInvited","content":"","date":"2025-08-04T09:04:41+00:00","index":"","fulltext":""},{"type":"checksComplete","content":"","date":"2025-07-31T13:44:58+00:00","index":"","fulltext":""},{"type":"submitted","content":"BMC Cancer","date":"2025-07-31T13:30:35+00:00","index":"","fulltext":""}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"bmc-cancer","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"bcan","sideBox":"Learn more about [BMC Cancer](http://bmccancer.biomedcentral.com/)","snPcode":"","submissionUrl":"https://www.editorialmanager.com/bcan/default.aspx","title":"BMC Cancer","twitterHandle":"BMC_series","acdcEnabled":true,"dfaEnabled":false,"editorialSystem":"em","reportingPortfolio":"BMC Series","inReviewEnabled":true,"inReviewRevisionsEnabled":true}}],"origin":"","ownerIdentity":"dfe25349-763e-488f-8fd4-4cf185d27256","owner":[],"postedDate":"September 9th, 2025","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"under-review","subjectAreas":[],"tags":[],"updatedAt":"2025-09-09T16:04:59+00:00","versionOfRecord":[],"versionCreatedAt":"2025-09-09 16:04:58","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-7234131","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-7234131","identity":"rs-7234131","version":["v1"]},"buildId":"8U1c8b4HqxoKbykW_rLl7","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}