Machine-based learning hierarchical cluster analysis: sex-based differences in prognosis following resection of hepatocellular carcinoma

Vivian Resende; Diamantis I. Tsilimigras; Yutaka Endo; Alfredo Guglielmi; Francesca Ratti; Luca Aldrighetti; Hugo P. Marques; Olivier Soubrane; Vincent Lam; George A. Poultsides; Irinel Popescu; Sorin Alexandrescu; Ana Gleisner; Guillaume Martel; Tom Hugh; Itaru Endo; Feng Shen; Timothy M. Pawlik

doi:10.1007/s00268-023-07194-z

Machine-based learning hierarchical cluster analysis: sex-based differences in prognosis following resection of hepatocellular carcinoma

Vivian Resende, Diamantis I. Tsilimigras, Yutaka Endo, Alfredo Guglielmi, Francesca Ratti, Luca Aldrighetti, Hugo P. Marques, Olivier Soubrane, Vincent Lam, George A. Poultsides, Irinel Popescu, Sorin Alexandrescu, Ana Gleisner, Guillaume Martel, Tom Hugh, Itaru Endo, Feng Shen, Timothy M. Pawlik^*

^*Corresponding author for this work

Research output: Contribution to journal › Article › peer-review

5 Citations (Scopus)

Abstract

Background: Patients with hepatocellular carcinoma (HCC) may have a heterogeneous presentation, as well as different long-term outcomes following surgical resection. We sought to use machine learning to cluster patients into different prognostic groups based on preoperative characteristics.

Methods: Patients who underwent curative-intent liver resection for HCC between 2000 and 2020 were identified from a large international multi-institutional database. A hierarchical cluster analysis was performed based on preoperative factors to characterize patterns of presentation and define disease-free survival (DFS).

Results: Among 966 with HCC, 3 distinct clusters were identified: Cluster 1 (n = 160, 16.5%), Cluster 2 (n = 537, 55.6%) and Cluster 3 (n = 269, 27.8%). Cluster 1 (n = 160, 16.5%) consisted of female patients (n = 160, 100%), low inflammation-based scores, intermediate tumor burden score (TBS) (median: 4.71) and high alpha-fetoprotein (AFP) levels (median 41.3 ng/mL); Cluster 2 consisted of male individuals (n = 537, 100%), mainly with a history of HBV infection (n = 429, 79.9%), low inflammation-based scores, intermediate AFP levels (median 26.0 ng/mL) and lower TBS (median 4.49); Cluster 3 was comprised of older patients (median age 68 years) predominantly male (n = 248, 92.2%) who had low incidence of HBV/HCV infection (7.1% and 8.2%, respectively), intermediate AFP levels (median 16.8 ng/mL), high inflammation-based scores and high TBS (median 6.58). Median DFS worsened incrementally among the three different clusters with Cluster 3 having the lowest DFS (Cluster 1: median not reached; Cluster 2: 34 months, 95% CI 23.0–48.0, Cluster 3: 19 months, 95% CI 15.0–29.0, p < 0.05).

Conclusion: Cluster analysis classified HCC patients into three distinct prognostic groups. Cluster assignment predicted DFS following resection of HCC with the female cluster having the most favorable prognosis following HCC resection.

Original language	English
Pages (from-to)	3319-3327
Number of pages	9
Journal	World Journal of Surgery
Volume	47
Issue number	12
Early online date	30 Sept 2023
DOIs	https://doi.org/10.1007/s00268-023-07194-z
Publication status	Published - Dec 2023
Externally published	Yes

Keywords

Female-patients
Disparity
Survival

Access to Document

10.1007/s00268-023-07194-z

Cite this

Resende, V., Tsilimigras, D. I., Endo, Y., Guglielmi, A., Ratti, F., Aldrighetti, L., Marques, H. P., Soubrane, O., Lam, V., Poultsides, G. A., Popescu, I., Alexandrescu, S., Gleisner, A., Martel, G., Hugh, T., Endo, I., Shen, F., & Pawlik, T. M. (2023). Machine-based learning hierarchical cluster analysis: sex-based differences in prognosis following resection of hepatocellular carcinoma. World Journal of Surgery, 47(12), 3319-3327. https://doi.org/10.1007/s00268-023-07194-z

@article{e4e8b4c2a30341e7a229e8cfa3aaf761,

title = "Machine-based learning hierarchical cluster analysis: sex-based differences in prognosis following resection of hepatocellular carcinoma",

abstract = "Background: Patients with hepatocellular carcinoma (HCC) may have a heterogeneous presentation, as well as different long-term outcomes following surgical resection. We sought to use machine learning to cluster patients into different prognostic groups based on preoperative characteristics.Methods: Patients who underwent curative-intent liver resection for HCC between 2000 and 2020 were identified from a large international multi-institutional database. A hierarchical cluster analysis was performed based on preoperative factors to characterize patterns of presentation and define disease-free survival (DFS).Results: Among 966 with HCC, 3 distinct clusters were identified: Cluster 1 (n = 160, 16.5\%), Cluster 2 (n = 537, 55.6\%) and Cluster 3 (n = 269, 27.8\%). Cluster 1 (n = 160, 16.5\%) consisted of female patients (n = 160, 100\%), low inflammation-based scores, intermediate tumor burden score (TBS) (median: 4.71) and high alpha-fetoprotein (AFP) levels (median 41.3 ng/mL); Cluster 2 consisted of male individuals (n = 537, 100\%), mainly with a history of HBV infection (n = 429, 79.9\%), low inflammation-based scores, intermediate AFP levels (median 26.0 ng/mL) and lower TBS (median 4.49); Cluster 3 was comprised of older patients (median age 68 years) predominantly male (n = 248, 92.2\%) who had low incidence of HBV/HCV infection (7.1\% and 8.2\%, respectively), intermediate AFP levels (median 16.8 ng/mL), high inflammation-based scores and high TBS (median 6.58). Median DFS worsened incrementally among the three different clusters with Cluster 3 having the lowest DFS (Cluster 1: median not reached; Cluster 2: 34 months, 95\% CI 23.0–48.0, Cluster 3: 19 months, 95\% CI 15.0–29.0, p < 0.05).Conclusion: Cluster analysis classified HCC patients into three distinct prognostic groups. Cluster assignment predicted DFS following resection of HCC with the female cluster having the most favorable prognosis following HCC resection.",

keywords = "Female-patients, Disparity, Survival",

author = "Vivian Resende and Tsilimigras, \{Diamantis I.\} and Yutaka Endo and Alfredo Guglielmi and Francesca Ratti and Luca Aldrighetti and Marques, \{Hugo P.\} and Olivier Soubrane and Vincent Lam and Poultsides, \{George A.\} and Irinel Popescu and Sorin Alexandrescu and Ana Gleisner and Guillaume Martel and Tom Hugh and Itaru Endo and Feng Shen and Pawlik, \{Timothy M.\}",

year = "2023",

month = dec,

doi = "10.1007/s00268-023-07194-z",

language = "English",

volume = "47",

pages = "3319--3327",

journal = "World Journal of Surgery",

issn = "0364-2313",

publisher = "John Wiley \& Sons",

number = "12",

}

Resende, V, Tsilimigras, DI, Endo, Y, Guglielmi, A, Ratti, F, Aldrighetti, L, Marques, HP, Soubrane, O, Lam, V, Poultsides, GA, Popescu, I, Alexandrescu, S, Gleisner, A, Martel, G, Hugh, T, Endo, I, Shen, F & Pawlik, TM 2023, 'Machine-based learning hierarchical cluster analysis: sex-based differences in prognosis following resection of hepatocellular carcinoma', World Journal of Surgery, vol. 47, no. 12, pp. 3319-3327. https://doi.org/10.1007/s00268-023-07194-z

TY - JOUR

T1 - Machine-based learning hierarchical cluster analysis

T2 - sex-based differences in prognosis following resection of hepatocellular carcinoma

AU - Resende, Vivian

AU - Tsilimigras, Diamantis I.

AU - Endo, Yutaka

AU - Guglielmi, Alfredo

AU - Ratti, Francesca

AU - Aldrighetti, Luca

AU - Marques, Hugo P.

AU - Soubrane, Olivier

AU - Lam, Vincent

AU - Poultsides, George A.

AU - Popescu, Irinel

AU - Alexandrescu, Sorin

AU - Gleisner, Ana

AU - Martel, Guillaume

AU - Hugh, Tom

AU - Endo, Itaru

AU - Shen, Feng

AU - Pawlik, Timothy M.

PY - 2023/12

Y1 - 2023/12

N2 - Background: Patients with hepatocellular carcinoma (HCC) may have a heterogeneous presentation, as well as different long-term outcomes following surgical resection. We sought to use machine learning to cluster patients into different prognostic groups based on preoperative characteristics.Methods: Patients who underwent curative-intent liver resection for HCC between 2000 and 2020 were identified from a large international multi-institutional database. A hierarchical cluster analysis was performed based on preoperative factors to characterize patterns of presentation and define disease-free survival (DFS).Results: Among 966 with HCC, 3 distinct clusters were identified: Cluster 1 (n = 160, 16.5%), Cluster 2 (n = 537, 55.6%) and Cluster 3 (n = 269, 27.8%). Cluster 1 (n = 160, 16.5%) consisted of female patients (n = 160, 100%), low inflammation-based scores, intermediate tumor burden score (TBS) (median: 4.71) and high alpha-fetoprotein (AFP) levels (median 41.3 ng/mL); Cluster 2 consisted of male individuals (n = 537, 100%), mainly with a history of HBV infection (n = 429, 79.9%), low inflammation-based scores, intermediate AFP levels (median 26.0 ng/mL) and lower TBS (median 4.49); Cluster 3 was comprised of older patients (median age 68 years) predominantly male (n = 248, 92.2%) who had low incidence of HBV/HCV infection (7.1% and 8.2%, respectively), intermediate AFP levels (median 16.8 ng/mL), high inflammation-based scores and high TBS (median 6.58). Median DFS worsened incrementally among the three different clusters with Cluster 3 having the lowest DFS (Cluster 1: median not reached; Cluster 2: 34 months, 95% CI 23.0–48.0, Cluster 3: 19 months, 95% CI 15.0–29.0, p < 0.05).Conclusion: Cluster analysis classified HCC patients into three distinct prognostic groups. Cluster assignment predicted DFS following resection of HCC with the female cluster having the most favorable prognosis following HCC resection.

AB - Background: Patients with hepatocellular carcinoma (HCC) may have a heterogeneous presentation, as well as different long-term outcomes following surgical resection. We sought to use machine learning to cluster patients into different prognostic groups based on preoperative characteristics.Methods: Patients who underwent curative-intent liver resection for HCC between 2000 and 2020 were identified from a large international multi-institutional database. A hierarchical cluster analysis was performed based on preoperative factors to characterize patterns of presentation and define disease-free survival (DFS).Results: Among 966 with HCC, 3 distinct clusters were identified: Cluster 1 (n = 160, 16.5%), Cluster 2 (n = 537, 55.6%) and Cluster 3 (n = 269, 27.8%). Cluster 1 (n = 160, 16.5%) consisted of female patients (n = 160, 100%), low inflammation-based scores, intermediate tumor burden score (TBS) (median: 4.71) and high alpha-fetoprotein (AFP) levels (median 41.3 ng/mL); Cluster 2 consisted of male individuals (n = 537, 100%), mainly with a history of HBV infection (n = 429, 79.9%), low inflammation-based scores, intermediate AFP levels (median 26.0 ng/mL) and lower TBS (median 4.49); Cluster 3 was comprised of older patients (median age 68 years) predominantly male (n = 248, 92.2%) who had low incidence of HBV/HCV infection (7.1% and 8.2%, respectively), intermediate AFP levels (median 16.8 ng/mL), high inflammation-based scores and high TBS (median 6.58). Median DFS worsened incrementally among the three different clusters with Cluster 3 having the lowest DFS (Cluster 1: median not reached; Cluster 2: 34 months, 95% CI 23.0–48.0, Cluster 3: 19 months, 95% CI 15.0–29.0, p < 0.05).Conclusion: Cluster analysis classified HCC patients into three distinct prognostic groups. Cluster assignment predicted DFS following resection of HCC with the female cluster having the most favorable prognosis following HCC resection.

KW - Female-patients

KW - Disparity

KW - Survival

UR - https://www.scopus.com/pages/publications/85173041201

U2 - 10.1007/s00268-023-07194-z

DO - 10.1007/s00268-023-07194-z

M3 - Article

C2 - 37777670

AN - SCOPUS:85173041201

SN - 0364-2313

VL - 47

SP - 3319

EP - 3327

JO - World Journal of Surgery

JF - World Journal of Surgery

IS - 12

ER -

Machine-based learning hierarchical cluster analysis: sex-based differences in prognosis following resection of hepatocellular carcinoma

Abstract

Keywords

Access to Document

Other files and links

Fingerprint

Cite this