Dataset Information

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

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.

SUBMITTER: Lippenberger F

PROVIDER: S-EPMC10811180 | biostudies-literature | 2024 Jan

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

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

Lippenberger Florian F Ziegelmayer Sebastian S Berlet Maximilian M Feussner Hubertus H Makowski Marcus M Neumann Philipp-Alexander PA Graf Markus M Kaissis Georgios G Wilhelm Dirk D Braren Rickmer R Reischl Stefan S

International journal of colorectal disease 20240125 1

<h4>Purpose</h4>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.<h4>Methods</h4>This retrospective sing ...[more]

PMID: 38273097

Similar Datasets

Project description:BackgroundTo test the feasibility of laparoscopic approach in performing the simultaneous pelvic autonomic nerve preservation during standard anterior resection of sigmoid colon cancer.MethodsPatients meeting appropriate eligibility criteria were recruited for the present study. The surgical procedures are shown in the video. The genitourinary function was evaluated on the basis of validated questionnaires including International Prostate Symptom Score (IPSS), International Index of Erectile Function (IIEF), and Female Sexual Function Index (FSFI).ResultsA total of 112 patients (tumor, node, metastasis system stage I, n = 8; stage II, n = 54; stage III, n = 50; male, n = 58; female, n = 54; age [mean +/- standard deviation], 55.8 +/- 6.4 years) with good baseline genitourinary function were operated on with the intent of total preservation of pelvic autonomic nerves and curative resection of sigmoid colon cancer. The patients were prospectively followed (median time of follow-up, 18 months; range, 6-30 months). In patients with a successful nerve-preserving surgery (96.4%, n = 108), 104 patients completed the evaluation of urinary function. The median duration for indwelling urine Foley catheter was 3.0 days (range, 1.0-7.0 days). The voiding function after removal of the urine Foley catheter was good (IPSS, 0-7) in 98 (94.2%) patients, fair (IPSS, 8-14) in 5 (4.8%), and poor (IPSS, 15-35) in 1 (1.0%). Before and after nerve-preserving surgery, there were no significant changes of IPSS scores (3.20 +/- 1.72 vs. 3.68 +/- 2.82, P = .075, paired t-test) in the present patient series. Forty-four male patients completed the postoperative evaluation of sexual function, and ejaculation was ranked as good in 40 (90.9%), fair (decrease in ejaculatory amounts) in 3 (6.8%), and poor (retrograde ejaculation, failure of ejaculation) in 1 (2.3%), whereas the potency was good (IIEF, 60-75) in 41 (93.2%), fair (IIEF, 44-59) in 2 (4.5%), and poor (IIEF, 5-43) in 1 (2.3%). Moreover, before and after a successful nerve-preserving operation, there were no significant changes of IIEF scores (72.4 +/- 4.6 vs. 70.3 +/- 8.4, P = .082, paired t-test). For female patients (n = 42), the postoperative sexual function was ranked as good (FSFI score, 76-95) in 36 (85.7%), fair (FSFI, 58-75) in 4 (9.5%), and poor (FSFI, 4-57) in 2 (4.8%). Furthermore, there were no significant changes of FSFI scores (89.0 +/- 9.2 vs. 85.4 +/- 16.4, P = .122, paired t-test) before and after successful nerve-preserving surgery.ConclusionsUnder laparoscopy, we can clearly identify and preserve the pelvic autonomic nerves to retain genitourinary function in most patients undergoing oncologic resection of sigmoid colon cancer.

Project description:BackgroundIdentifying lncRNA-disease associations not only helps to better comprehend the underlying mechanisms of various human diseases at the lncRNA level but also speeds up the identification of potential biomarkers for disease diagnoses, treatments, prognoses, and drug response predictions. However, as the amount of archived biological data continues to grow, it has become increasingly difficult to detect potential human lncRNA-disease associations from these enormous biological datasets using traditional biological experimental methods. Consequently, developing new and effective computational methods to predict potential human lncRNA diseases is essential.ResultsUsing a combination of incremental principal component analysis (IPCA) and random forest (RF) algorithms and by integrating multiple similarity matrices, we propose a new algorithm (IPCARF) based on integrated machine learning technology for predicting lncRNA-disease associations. First, we used two different models to compute a semantic similarity matrix of diseases from a directed acyclic graph of diseases. Second, a characteristic vector for each lncRNA-disease pair is obtained by integrating disease similarity, lncRNA similarity, and Gaussian nuclear similarity. Then, the best feature subspace is obtained by applying IPCA to decrease the dimension of the original feature set. Finally, we train an RF model to predict potential lncRNA-disease associations. The experimental results show that the IPCARF algorithm effectively improves the AUC metric when predicting potential lncRNA-disease associations. Before the parameter optimization procedure, the AUC value predicted by the IPCARF algorithm under 10-fold cross-validation reached 0.8529; after selecting the optimal parameters using the grid search algorithm, the predicted AUC of the IPCARF algorithm reached 0.8611.ConclusionsWe compared IPCARF with the existing LRLSLDA, LRLSLDA-LNCSIM, TPGLDA, NPCMF, and ncPred prediction methods, which have shown excellent performance in predicting lncRNA-disease associations. The compared results of 10-fold cross-validation procedures show that the predictions of the IPCARF method are better than those of the other compared methods.

Dataset Information

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

Purpose

Methods

Results

Conclusion

Publications

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

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets