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
. 2024 Jan 25;39(1):21.
doi: 10.1007/s00384-024-04593-z.

Development of an image-based Random Forest classifier for prediction of surgery duration of laparoscopic sigmoid resections

Florian Lippenberger  1 , Sebastian Ziegelmayer  1 , Maximilian Berlet  2   3 , Hubertus Feussner  2   3 , Marcus Makowski  1 , Philipp-Alexander Neumann  2 , Markus Graf  1 , Georgios Kaissis  1   4 , Dirk Wilhelm  2   3 , Rickmer Braren #  1   5 , Stefan Reischl #  6
Affiliations

Development of an image-based Random Forest classifier for prediction of surgery duration of laparoscopic sigmoid resections

Florian Lippenberger et al. Int J Colorectal Dis. .

Abstract

Purpose: Sigmoid diverticulitis is a disease with a high socioeconomic burden, accounting for a high number of left-sided colonic resections worldwide. Modern surgical scheduling relies on accurate prediction of operation times to enhance patient care and optimize healthcare resources. This study aims to develop a predictive model for surgery duration in laparoscopic sigmoid resections, based on preoperative CT biometric and demographic patient data.

Methods: This retrospective single-center cohort study included 85 patients who underwent laparoscopic sigmoid resection for diverticular disease. Potentially relevant procedure-specific anatomical parameters recommended by a surgical expert were measured in preoperative CT imaging. After random split into training and test set (75% / 25%) multiclass logistic regression was performed and a Random Forest classifier was trained on CT imaging parameters, patient age, and sex in the training cohort to predict categorized surgery duration. The models were evaluated in the test cohort using established performance metrics including receiver operating characteristics area under the curve (AUROC).

Results: The Random Forest model achieved a good average AUROC of 0.78. It allowed a very good prediction of long (AUROC = 0.89; specificity 0.71; sensitivity 1.0) and short (AUROC = 0.81; specificity 0.77; sensitivity 0.56) procedures. It clearly outperformed the multiclass logistic regression model (AUROC: average = 0.33; short = 0.31; long = 0.22).

Conclusion: A Random Forest classifier trained on demographic and CT imaging biometric patient data could predict procedure duration outliers of laparoscopic sigmoid resections. Pending validation in a multicenter study, this approach could potentially improve procedure scheduling in visceral surgery and be scaled to other procedures.

Keywords: Computed tomography; Diverticulitis; Laparoscopic surgery; Machine learning; Random Forest; Surgery scheduling.

PubMed Disclaimer

Conflict of interest statement

The authors declare no competing interests.

Figures

Fig. 1
Fig. 1
Anatomical distances compared between the surgery duration classes. Bar plots depicting the distribution of the anatomic features and age. Data are presented as mean values and standard deviation. Significant differences are indicated as *p < 0.05, **p < 0.01
Fig. 2
Fig. 2
Performance metrics of the multiclass logistic regression model. A Receiver operating characteristics, B confusion matrix, and C sensitivity, specificity, positive predictive value (PPV), negative predictive values (NPV), and accuracy for a model decision threshold of 0.5 are shown
Fig. 3
Fig. 3
Performance metrics of the Random Forest model. A Receiver operating characteristics, B confusion matrix, and C sensitivity, specificity, positive predictive value (PPV), negative predictive values (NPV), and accuracy are shown
See this image and copyright information in PMC

References

    1. Peery AF, Dellon ES, Lund J, Crockett SD, McGowan CE, Bulsiewicz WJ, Gangarosa LM, Thiny MT, Stizenberg K, Morgan DR, Ringel Y, Kim HP, DiBonaventura MD, Carroll CF, Allen JK, Cook SF, Sandler RS, Kappelman MD, Shaheen NJ (2012) Burden of gastrointestinal disease in the United States: 2012 update. Gastroenterology 143(5):1179–1187.e3 - PMC - PubMed
    1. Diers J, Wagner J, Baum P, Lichthardt S, Kastner C, Matthes N, Löb S, Matthes H, Germer C-T, Wiegering A (2019) Nationwide in-hospital mortality following colonic cancer resection according to hospital volume in Germany. BJS Open 3(5):672–677 - PMC - PubMed
    1. Sartelli M, Weber DG, Kluger Y, Ansaloni L, Coccolini F, Abu-Zidan F, Augustin G, Ben-Ishay O, Biffl WL, Bouliaris K, Catena R, Ceresoli M, Chiara O, Chiarugi M, Coimbra R, Cortese F, Cui Y, Damaskos D, Angelis GL, de’ Delibegovic S, Demetrashvili Z, de Simone B, Di Marzo F, Di Saverio S, Duane TM, Faro MP, Fraga GP, Gkiokas G, Gomes CA, Hardcastle TC, Hecker A, Karamarkovic A, Kashuk J, Khokha V, Kirkpatrick AW, Kok KYY, Inaba K, Isik A, Labricciosa FM, Latifi R, Leppäniemi A, Litvin A, Mazuski JE, Maier RV, Marwah S, McFarlane M, Moore EE, Moore FA, Negoi I, Pagani L, Rasa K, Rubio-Perez I, Sakakushev B, Sato N, Sganga G, Siquini W, Tarasconi A, Tolonen M, Ulrych J, Zachariah SK, Catena F (2020) 2020 update of the WSES guidelines for the management of acute colonic diverticulitis in the emergency setting. World J Emerg Surg 15(1):32 - PMC - PubMed
    1. Pietryga S, Lock JF, Diers J, Baum P, Uttinger KL, Baumann N, Flemming S, Wagner JC, Germer C-T, Wiegering A (2023) Nationwide volume-outcome relationship concerning in-hospital mortality and failure-to-rescue in surgery of sigmoid diverticulitis. Int J Colorectal Dis 38(1):203 - PubMed
    1. Guller U, Jain N, Hervey S, Purves H, Pietrobon R (2003) Laparoscopic vs open colectomy: outcomes comparison based on large nationwide databases. Arch Surg (Chicago, Ill.: 1960) 138(11):1179–1186 - PubMed

LinkOut - more resources