Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
[Preprint]. 2025 May 7:rs.3.rs-6529613.
doi: 10.21203/rs.3.rs-6529613/v1.

An integrated machine learning-based prognostic model in head and neck cancer using the systemic inflammatory response index and correlations with patient reported financial toxicity

Anurag K Singh  1 , Sung Jun Ma  2 , Dukagjin Blakaj  2 , Simeng Zhu  2 , Neil D Almeida  1 , Andrew Koempel  2 , Guangwei Yuan  3 , Grace Wang  3 , Kimberly Wooten  4 , Vishal Gupta  4 , Ryan McSpadden  4 , Moni A Kuriakose  4 , Michael R Markiewicz  5   6 , Song Yao  7 , Wesley L Hicks Jr  4 , Mukund Seshadri  8 , Elizabeth A Repasky  9 , Elizabeth G Bouchard  1   10   11   4   3   5   6   8   7   9   2 , Mark K Farrugia  1 , Han Yu  3
Affiliations

An integrated machine learning-based prognostic model in head and neck cancer using the systemic inflammatory response index and correlations with patient reported financial toxicity

Anurag K Singh et al. Res Sq. .

Abstract

Objective: To investigate the prognostic utility of systemic inflammatory response index (SIRI) as a biological readout of stress associated immune modulation in head and neck cancer patients who underwent radiation therapy.

Methods: Random survival forest machine learning was used to model survival in 568 head and neck cancer patients. SIRI was calculated via pre-treatment bloodwork. Model validation was performed in an external cohort of 345 patients. Baseline financial toxicity (FT) and SIRI were studied in 638 patients.

Results: Incorporation of SIRI (with performance status and smoking history) into a machine learning model identified three risk-groups that significantly stratified overall survival (p<0.0001,) and these findings were validated in the external validation cohort (p<0.001.) Increasing levels of FT were significantly associated with increasing SIRI levels. (p=0.001.).

Conclusions and relevance: An integrated machine learning model using clinical features was successfully developed and externally validated. SIRI was significantly associated with increasing FT. Our findings highlight the potential utility of SIRI as a biological marker of FT in head and neck cancer patients.

Keywords: Inflammation; lymphocyte; monocyte; neutrophil; squamous cell carcinoma.

PubMed Disclaimer

Conflict of interest statement

Additional Declarations: There is NO Competing Interest.

Figures

Figure 1.
Figure 1.
(A) In the current, reduced model, SIRI replaced several predictors from the prior, full model. (B) Receiver operating characteristic curves (ROCs) of the full model. (C) ROCs of the 4-feature model. (D) Comparison of the area under the curve (AUCs) at months 12–60. (E) The Kaplan-Meier curves based on the risk stratification by the reduced model. (F) The decision tree of the parsimonious model partitions the cohort into four groups, where two high-risk groups were merged to Group 3. (G) The Kaplan-Meier curves of the three groups in the test set.
Figure 2.
Figure 2.
The Kaplan-Meier curves of (A) overall survival, (B) progression free survival from the External Validation Cohort.
Figure 3:
Figure 3:
Distribution of log2(SIRI) among FT groupings, p=0.001.
See this image and copyright information in PMC

Similar articles

See all similar articles

References

    1. Hajdu SI. Greco-Roman thought about cancer. Cancer. 2004;100(10):2048–2051. - PubMed
    1. Eckerling A, Ricon-Becker I, Sorski L, Sandbank E, Ben-Eliyahu S. Stress and cancer: mechanisms, significance and future directions. Nat Rev Cancer. 2021;21(12):767–785. - PubMed
    1. Sandi C, Haller J. Stress and the social brain: behavioural effects and neurobiological mechanisms. Nature Reviews Neuroscience. 2015;16(5):290–304. - PubMed
    1. Zeng Y, Hu C-H, Li Y-Z, et al. Association between pretreatment emotional distress and immune checkpoint inhibitor response in non-small-cell lung cancer. Nature Medicine. 2024;30(6):1680–1688. - PMC - PubMed
    1. Davis JM, Albert JD, Tracy KJ, et al. Increased neutrophil mobilization and decreased chemotaxis during cortisol and epinephrine infusions. J Trauma. 1991;31(6):725–731; discussion 731–722. - PubMed

Publication types

LinkOut - more resources