Dataset Information

Prediction of blood pressure changes associated with abdominal pressure changes during robotic laparoscopic low abdominal surgery using deep learning.

ABSTRACT:

Background

Intraoperative hypertension and blood pressure (BP) fluctuation are known to be associated with negative patient outcomes. During robotic lower abdominal surgery, the patient's abdominal cavity is filled with CO2, and the patient's head is steeply positioned toward the floor (Trendelenburg position). Pneumoperitoneum and the Trendelenburg position together with physiological alterations during anesthesia, interfere with predicting BP changes. Recently, deep learning using recurrent neural networks (RNN) was shown to be effective in predicting intraoperative BP. A model for predicting BP rise was designed using RNN under special scenarios during robotic laparoscopic surgery and its accuracy was tested.

Methods

Databases that included adult patients (over 19 years old) undergoing low abdominal da Vinci robotic surgery (ovarian cystectomy, hysterectomy, myomectomy, prostatectomy, and salpingo-oophorectomy) at Soonchunhyang University Bucheon Hospital from October 2018 to March 2021 were used. An RNN-based model was designed using Python3 language with the PyTorch packages. The model was trained to predict whether hypertension (20% increase in the mean BP from baseline) would develop within 10 minutes after pneumoperitoneum.

Results

Eight distinct datasets were generated and the predictive power was compared. The macro-average F1 scores of the datasets ranged from 68.18% to 72.33%. It took only 3.472 milliseconds to obtain 39 prediction outputs.

Conclusions

A prediction model using the RNN may predict BP rises during robotic laparoscopic surgery.

SUBMITTER: Chung YH

PROVIDER: S-EPMC9200233 | biostudies-literature | 2022

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Prediction of blood pressure changes associated with abdominal pressure changes during robotic laparoscopic low abdominal surgery using deep learning.

Chung Yang-Hoon YH Jeong Young-Seob YS Martin Gati Lother GL Choi Min Seo MS Kang You Jin YJ Lee Misoon M Cho Ana A Koo Bon Sung BS Cho Sung Hwan SH Kim Sang Hyun SH

PloS one 20220606 6

<h4>Background</h4>Intraoperative hypertension and blood pressure (BP) fluctuation are known to be associated with negative patient outcomes. During robotic lower abdominal surgery, the patient's abdominal cavity is filled with CO2, and the patient's head is steeply positioned toward the floor (Trendelenburg position). Pneumoperitoneum and the Trendelenburg position together with physiological alterations during anesthesia, interfere with predicting BP changes. Recently, deep learning using recu ...[more]

PMID: 35666742

Similar Datasets

Project description:BackgroundThe current evidence is inconclusive on whether robotic or laparoscopic surgery is the optimal platform for minimally invasive surgery. Existing comparisons techniques focus on short-term outcomes only, while potentially being confounded by a lack of standardisation in robotic procedures. There is a pertinent need for an up-to-date comparison between minimally invasive surgical techniques. We aimed to systematically review randomised controlled trials comparing robotic and laparoscopic techniques in major surgery.MethodsEmbase, Medline and Cochrane Library were searched from their inception to 13th September 2022. Included studies were randomised controlled trials comparing robotic and laparoscopic techniques in abdominal and pelvic surgery. The study followed the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) guidelines. Short-term, health-related quality of life, and long-term, outcomes were analysed.ResultsForty-five studies, across thirteen procedures, involving 7364 patients were included. All of the studies reported non-significant differences in mortality between robotic and laparoscopic surgery. In majority of studies, there was no significant difference in complication rate (n = 31/35, 85.6%), length of postoperative stay (n = 27/32, 84.4%), and conversion rate (n = 15/18, 83.3%). Laparoscopic surgery was associated with shorter operative time (n = 16/31, 51.6%) and lower total cost (n = 11/13, 84.6%). Twenty three studies reported on quality of life outcomes; majority (n = 14/23, 60.9%) found no significant differences.ConclusionThere were no significant differences between robotic surgery and laparoscopic surgery with regards to mortality and morbidity outcomes in the majority of studies. Robotic surgery was frequently associated with longer operative times and higher overall cost. Selected studies found potential benefits in post-operative recovery time, and patient-reported outcomes; however, these were not consistent across procedures and trials, with most studies being underpowered to detect differences in secondary outcomes. Future research should focus on assessing quality of life, and long-term outcomes to further elucidate where the robotic platform could lead to patient benefits, as the technology evolves.

Project description:BackgroundManual objective assessment of skill and errors in minimally invasive surgery have been validated with correlation to surgical expertise and patient outcomes. However, assessment and error annotation can be subjective and are time-consuming processes, often precluding their use. Recent years have seen the development of artificial intelligence models to work towards automating the process to allow reduction of errors and truly objective assessment. This study aimed to validate surgical skill rating and error annotations in suturing gestures to inform the development and evaluation of AI models.MethodsSAR-RARP50 open data set was blindly, independently annotated at the gesture level in Robotic-Assisted Radical Prostatectomy (RARP) suturing. Manual objective assessment tools and error annotation methodology, Objective Clinical Human Reliability Analysis (OCHRA), were used as ground truth to train and test vision-based deep learning methods to estimate skill and errors. Analysis included descriptive statistics plus tool validity and reliability.ResultsFifty-four RARP videos (266 min) were analysed. Strong/excellent inter-rater reliability (range r = 0.70-0.89, p < 0.001) and very strong correlation (r = 0.92, p < 0.001) between objective assessment tools was demonstrated. Skill estimation of OSATS and M-GEARS had a Spearman's Correlation Coefficient 0.37 and 0.36, respectively, with normalised mean absolute error representing a prediction error of 17.92% (inverted "accuracy" 82.08%) and 20.6% (inverted "accuracy" 79.4%) respectively. The best performing models in error prediction achieved mean absolute precision of 37.14%, area under the curve 65.10% and Macro-F1 58.97%.ConclusionsThis is the first study to employ detailed error detection methodology and deep learning models within real robotic surgical video. This benchmark evaluation of AI models sets a foundation and promising approach for future advancements in automated technical skill assessment.

Project description:IntroductionEndometriosis is a common gynaecological disease affecting around 10% of fertile-aged women, causing severe pain symptoms. Deep endometriosis is defined as endometriotic implants that infiltrate the underlying organs more than 5 mm in depth. Surgery for deep endometriosis requires advanced multidisciplinary surgical technique, often in very difficult surgical conditions, with increased risks of complications. Robotic surgery offers a high-definition three-dimensional view and articulating instruments that may allow more precise dissection than conventional laparoscopy in the pelvic area. The superiority of robotic surgery has not, however, been provedin randomised controlled studies, and there is a lack of long-term outcome data. Advanced endometriosis surgery offers an excellent platform to study the feasibility and long-term outcomes of robotic surgery compared with conventional laparoscopy.Methods and analysisROBEndo is a prospective, randomised, controlled clinical trial in a single-centre setting. Patients with deep endometriosis verified by MRI needing surgery at Oulu University Hospital (Oulu, Finland) will be considered eligible. 70 patients will be allocated 1:1 to receive either robotic-assisted or conventional laparoscopic surgery in two strata: radical surgery (with the removal of the uterus and adnexae) and gynaecological organ-sparing surgery. The primary outcome will be the surgical outcome as regards to pain symptoms measured on numeric rating scale (NRS) questionnaires at 24 hours and 6, 12 and 24 months postoperatively. As secondary outcomes, intraoperative measures, enhanced recovery after surgery factors, complications, cost and long-term quality of life measured with Endometriosis Health Profile-30 (EHP-30), Female Sexual Function Index (FSFI) and 15-dimensional (15D) questionnaires will be compared.Ethics and disseminationThis study has been approved by the Northern Ostrobothnian Hospital District Ethical Committee at Oulu University Hospital (212/2021). Informed consent will be obtained during the preoperative check-up by the operating gynaecologist. The results will be published in peer-reviewed international journals.Trial registration numberNCT05179109.

Project description:Sacrocolpopexy has been dubbed the “gold standard” repair for apical pelvic organ prolapse (POP). This study sought to determine a genetic cause for sacrocolpopexy failure by comparing genotypes from 10 women who suffered from early POP reoccurance after sacrocolpopexy surgery, versus 40 randomly selected women with long term success after the same procedure. We objectively defined early overt failure after robotic-assisted laparoscopic sacrocolpopexy as having a pelvic organ prolapse quantification system examination (POP-Q) of stage III or IV occurring in more than one compartment within six months after surgery. All medical records identified during this process were then reviewed by a panel of urogynecology attendings and fellows to select patients who were truly clinical outliers. By this method we identified 10 patients (cases) who experienced early overt surgical failure. We also randomly selected 40 controls from our research database which includes greater than 500 patients who underwent robotic-assisted laparoscopic sacrocolpopexy during the same time period and had been objectively and subjectively assessed for ≥ 12 months with surgical success at ≥ 12 months that did not undergo prolapse re-operation or re-treatment. Demographics and peri-operative details were compared between cases and controls. Exclusion criteria for controls included use of other graft material besides polypropylene mesh, prior surgery for prolapse involving graft material, and conversion to laparotomy. DNA from the 10 cases and 40 controls was isolated from buccal swabs and genotyped on a single nucleotide polymorphism (SNP) array that contains 250,000 markers (NspI 250K SNP array, Affymetrix, Santa Clara, CA). All women in this study identified as Caucasian. All subjects provided written informed consent to study participation and data release. This was a case-control study approved by the Institutional Review Board at the Atlantic Health System in Morristown New Jersey (R11-10-004).

Dataset Information

Prediction of blood pressure changes associated with abdominal pressure changes during robotic laparoscopic low abdominal surgery using deep learning.

Background

Methods

Results

Conclusions

Publications

Prediction of blood pressure changes associated with abdominal pressure changes during robotic laparoscopic low abdominal surgery using deep learning.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets