Applications of natural language processing tools in the surgical journey.

Background: Natural language processing tools are becoming increasingly adopted in multiple industries worldwide. They have shown promising results however their use in the field of surgery is under-recognised. Many trials have assessed these benefits in small settings with promising results before large scale adoption can be considered in surgery. This study aims to review the current research and insights into the potential for implementation of natural language processing tools into surgery. Methods: A narrative review was conducted following a computer-assisted literature search on Medline, EMBASE and Google Scholar databases. Papers related to natural language processing tools and consideration into their use for surgery were considered. Results: Current applications of natural language processing tools within surgery are limited. From the literature, there is evidence of potential improvement in surgical capability and service delivery, such as through the use of these technologies to streamline processes including surgical triaging, data collection and auditing, surgical communication and documentation. Additionally, there is potential to extend these capabilities to surgical academia to improve processes in surgical research and allow innovation in the development of educational resources. Despite these outcomes, the evidence to support these findings are challenged by small sample sizes with limited applicability to broader settings. Conclusion: With the increasing adoption of natural language processing technology, such as in popular forms like ChatGPT, there has been increasing research in the use of these tools within surgery to improve surgical workflow and efficiency. This review highlights multifaceted applications of natural language processing within surgery, albeit with clear limitations due to the infancy of the infrastructure available to leverage these technologies. There remains room for more rigorous research into broader capability of natural language processing technology within the field of surgery and the need for cross-sectoral collaboration to understand the ways in which these algorithms can best be integrated.

A systematic review of minimally invasive cytoreductive surgery and hyperthermic intraperitoneal chemotherapy in patients with peritoneal malignancy.

BACKGROUND: Cytoreductive surgery (CRS) and hyperthermic intraperitoneal chemotherapy (HIPEC) is traditionally a maximally invasive operation with a large abdominal incision and multi-visceral resections. However, to minimize abdominal wall morbidity and improve functional recovery, some centres have adopted a minimally invasive (MI) approach in select cases. The primary aim of this systematic review and meta-analysis was to assess the evidence for safety and patient selection for minimally invasive approaches to CRS and HIPEC with curative intent. METHODS: A PRISMA-compliant systematic review was performed using three electronic databases: Ovid MEDLINE, EMBASE and Web of Science. Data regarding postoperative morbidity was meta-analysed. RESULTS: Thirteen studies met the inclusion criteria (N = 462 MI patients), all of which were retrospective in design. Six studies included an open comparison group. Pseudomyxoma peritonei, mesothelioma and ovarian carcinoma made up the majority of cases (>90%), with a PCI < 10 listed as a prerequisite to selection across all studies. On pooled analysis there was no difference in major morbidity between MI and open groups (OR 0.52 95% CI 0.18-1.46, P = 0.33). There was one perioperative death reported in the MI group. Length of stay appeared shorter in the MI group (median range MI: 4-11 v Open: 7-13 days). Short-term recurrence and overall survival between both groups also appeared no different. CONCLUSION: Minimally invasive CRS and HIPEC appears feasible and safe in appropriately selected patients. Clear histological stratification and longer term follow up is required to determine oncological safety, particularly in more aggressive tumours such as colorectal peritoneal metastases.

Emerging multi-port soft tissue robotic systems: a systematic review of clinical outcomes.

Multiple novel multi-port robotic surgical systems have been introduced into clinical practice. This systematic review aims to evaluate the clinical outcomes of these novel robotic systems to conventional laparoscopic technique and established da Vinci robotic surgical platforms. A literature search of Embase, Medline, Pubmed, Cochrane library, and Google Scholar was performed according to the PRISMA guidelines from 2012 to May 2023. Studies comparing clinical outcomes of novel multi-port robotic surgical systems with laparoscopic or the da Vinci platforms were included. Case series with no comparison groups were excluded. Descriptive statistics were used to report patient and outcome data. A systematic narrative review was provided for each outcome. Twelve studies comprised of 1142 patients were included. A total of 6 novel multi-port robotic systems: Micro Hand S, Senhance, Revo-i MSR-5000, KangDuo, Versius, and Hugo™ RAS were compared against the laparoscopic or the da Vinci robotic platforms. Clinical outcomes of these novel robotic platforms were comparable to the established da Vinci platforms. When compared against conventional laparoscopic approaches, the robotic platforms demonstrated lower volume of blood loss, shorter length of stay but longer operative time. This systematic review highlighted the safe implementation and efficacy of 6 new robotic systems. The clinical outcomes achieved by these new robotic systems are comparable to the established da Vinci robotic system in simple to moderate case complexities. There is emerging evidence that these new robotic systems provide a viable alternative to currently available robotic platforms.

Robotic versus laparoscopic gastric bypass in bariatric surgery: a systematic review and meta-analysis on perioperative outcomes.

BACKGROUND: Robotic-assisted surgery has emerged as a compelling approach to bariatric surgery. However, current literature has not consistently demonstrated superior outcomes to laparoscopic bariatric surgery to justify its higher cost. With its mechanical advantages, the potential gains from the robotic surgical platform are likely to be apparent in more complex cases such as gastric bypass, especially revisional cases. OBJECTIVE: This systematic review and meta-analysis aimed to summarize the literature and evaluate the peri-operative outcomes of patients with obesity undergoing robotic gastric bypass versus laparoscopic gastric bypass surgery. SETTING: Systematic review. METHODS: A literature search of Embase, Medline, Pubmed, Cochrane library, and Google Scholar was performed according to Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) guidelines. Studies comparing outcomes of robotic and laparoscopic gastric bypass for obesity were included. RESULTS: Twenty-eight eligible studies comprised a total of 82,155 patients; 9051 robotic bypass surgery (RBS) versus 73,104 laparoscopic bypass surgery (LBS) were included. All included studies compared Roux-en-Y gastric bypass. RBS was noted to have higher reoperation rate within 30 days (4.4% versus 3.4%; odds ratio 1.31 [95% CI, 1.04-1.66]; P = .027; I2 = 43.5%) than LBS. All other endpoints measured (complication rate, anastomotic leak, anastomotic stricture, surgical site infections, hospital readmission, length of stay, operative time, conversion rate and mortality) did not show any difference between RBS and LBS. CONCLUSION: This systematic review and meta-analysis showed that there was no significant difference in key outcome measures in robotic versus laparoscopic gastric bypass. RBS was associated with a slightly higher reoperation rate and there was no reduction in overall complication rate with the use of robotic platform.

Use of patient-derived explants as a preclinical model for precision medicine in colorectal cancer: A scoping review.

PURPOSE: Whilst the treatment paradigm for colorectal cancer has evolved significantly over time, there is still a lack of reliable biomarkers of treatment response. Treatment decisions are based on high-risk features such as advanced TNM stage and histology. The role of the tumour microenvironment, which can influence tumour progression and treatment response, has generated considerable interest. Patient-derived explant cultures allow preservation of native tissue architecture and tumour microenvironment. The aim of the scoping review is to evaluate the utility of patient-derived explant cultures as a preclinical model in colorectal cancer. METHODS: A search was conducted using Ovid MEDLINE, EMBASE, Web of Science, and Cochrane databases from start of database records to September 1, 2022. We included all peer-reviewed human studies in English language which used patient-derived explants as a preclinical model in primary colorectal cancer. Eligible studies were grouped into the following categories: assessing model feasibility; exploring tumour microenvironment; assessing ex vivo drug responses; discovering and validating biomarkers. RESULTS: A total of 60 studies were eligible. Fourteen studies demonstrated feasibility of using patient-derived explants as a preclinical model. Ten studies explored the tumour microenvironment. Thirty-eight studies assessed ex vivo drug responses of chemotherapy agents and targeted therapies. Twenty-four studies identified potential biomarkers of treatment response. CONCLUSIONS: Given the preservation of tumour microenvironment and tumour heterogeneity, patient-derived explants has the potential to identify reliable biomarkers, treatment resistance mechanisms, and novel therapeutic agents. Further validation studies are required to characterise, refine and standardise this preclinical model before it can become a part of precision medicine in colorectal cancer.

Immune mediated colitis: a surgical perspective.

BACKGROUND: This study aims to review and summarize the current up to date literature that explore the current treatment approaches to immune mediated colitis and the role of surgical specialties in the landscape of management. METHODS: A narrative review of papers was performed following a literature search through Medline, EMBASE and Cochrane Central databases pertaining to immune mediated colitis as an adverse event of cancer immunotherapy. RESULTS: Current guidelines for the diagnosis and treatment of immune mediated colitis mirror the approach to the workup of inflammatory bowel disease and guided by treating oncology and gastroenterology specialties. Immune mediated colitis however relies on surgical specific skills as a consequence of obtaining a diagnosis as well as in the management of complications that may arise. CONCLUSION: Immune mediate colitis management has largely been under the purview of medical specialties. This review explores the current landscape of managing immune mediated colitis from a surgical perspective and highlights key areas in which surgeons can engage in the multidisciplinary care of this condition. To facilitate prompt diagnosis and management of immune-mediated colitis, there is an increasing necessity for surgeons to become familiar with the latest multidisciplinary approaches and recommendations.

Operative and oncological outcomes after robotic rectal resection compared with laparoscopy: a systematic review and meta-analysis.

BACKGROUND: Most studies comparing robotic and laparoscopic surgery, show little difference in clinical outcomes to justify the expense. We systematically reviewed and pooled evidence from studies comparing robotic and laparoscopic rectal resection. METHOD: Medical Literature Analysis and Retrieval System Online (MEDLINE), Excerpta Medica (EMBASE), and Cochrane databases were searched for studies between 1996 and 2021 comparing clinical outcomes between laparoscopic and robotic rectal surgeries involving total mesorectal excision. Outcome measures included operative times, conversions to open, complications, recurrence and survival rates. RESULTS: Fifty eligible studies compared outcomes between robotic and laparoscopic rectal resections; three were randomized trials. Pooled results showed significantly longer operating times for robotic surgery but lower conversion and complications rates, shorter lengths of stay in hospital, better rates of complete mesorectal resection and better three-year overall survival. However, the low number of randomized studies makes most data subject to bias. CONCLUSION: Available evidence supports the safety and ongoing use of robotic rectal cancer surgery, while further high-quality evidence is sought to justify the expense.

Retrospective audit: Utility of PET scan in routine preoperative rectal cancer staging.

BACKGROUND: Accurate staging for rectal cancer is pertinent with recent introduction of rectum-sparing approaches for patients showing complete clinical response on restaging. Positron emission tomography(PET) is used in detection of recurrence or metastasis, but its value in routine preoperative rectal cancer staging remains unclear. Studies report that preoperative PET altered the stage in 39% and changed the management in 17-27% of patients. Our study aims to look at the utility of PET in routine preoperative staging of rectal cancer within 2 two colorectal units, and to determine if PET did result in a change in management. METHODS: Patients in Nepean Hospital (NSW) and Peter MacCallum Cancer Centre (VIC) who were diagnosed with rectal cancer between 1 January 2017 and 31 December 2021 were included in this retrospective study. All patients who did not have a PET scan were excluded. PET scan results were then compared with MRI and CT results. RESULTS: Three hundred and fifty-seven patients were included in the study. 30.3% of the patients had Stage 3 rectal cancer. 71.7% received neoadjuvant therapy. PET scan provided additional information in 55.5% of patients when compared with CT and MRI alone; 18.2% of the PET findings resulted in an altered management for the patient. CONCLUSION: PET scan can be a valuable tool in accurate staging, especially for ambiguous or equivocal lesions on CT. Our study demonstrated that additional information from PET scan resulted in an altered management plan in 18.2% of the patients. PET/MRI as a newer modality may be more accurate with reduced radiation exposure.

Effect of Surgical Humidification on Inflammation and Peritoneal Trauma in Colorectal Cancer Surgery: A Randomized Controlled Trial.

BACKGROUND: Pre-clinical studies indicate that dry-cold-carbon-dioxide (DC-CO2) insufflation leads to more peritoneal damage, inflammation and hypothermia compared with humidified-warm-CO2 (HW-CO2). Peritoneum and core temperature in patients undergoing colorectal cancer (CRC) surgery were compared. METHODS: Sixty-six patients were randomized into laparoscopic groups; those insufflated with DC-CO2 or HW-CO2. A separate group of nineteen patients undergoing laparotomy were randomised to conventional surgery or with the insertion of a device delivering HW-CO2. Temperatures were monitored and peritoneal biopsies and bloods were taken at the start of surgery, at 1 and 3 h. Further bloods were taken depending upon hospital length-of-stay (LOS). Peritoneal samples were subjected to scanning electron microscopy to evaluate mesothelial damage. RESULTS: Laparoscopic cases experienced a temperature drop despite Bair-HuggerTM use. HW-CO2 restored normothermia (≥ 36.5 °C) by 3 h, DC-CO2 did not. LOS was shorter for colon compared with rectal cancer cases and if insufflated with HW-CO2 compared with DC-CO2; 5.0 vs 7.2 days, colon and 11.6 vs 15.4 days rectum, respectively. Unexpectedly, one third of patients had pre-existing damage. Damage increased at 1 and 3 h to a greater extent in the DC-CO2 compared with the HW-CO2 laparoscopic cohort. C-reactive protein levels were higher in open than laparoscopic cases and lower in both matched HW-CO2 groups. CONCLUSIONS: This prospective RCT is in accord with animal studies while highlighting pre-existing damage in some patients. Peritoneal mesothelium protection, reduced inflammation and restoration of core-body temperature data suggest benefit with the use of HW-CO2 in patients undergoing CRC surgery.

Patient-Related Functional Outcomes After Robotic-Assisted Rectal Surgery Compared With a Laparoscopic Approach: A Systematic Review and Meta-analysis.

BACKGROUND: Robotic surgery has gained significant momentum in rectal cancer surgery. Most studies focus on short-term and oncological outcomes, showing similar outcomes to laparoscopic surgery. Increasing survivorship mandates greater emphasis on quality of life and long-term function. OBJECTIVE: This study aimed to compare quality of life and urinary, sexual, and lower GI functions between robotic and laparoscopic rectal surgeries. DATA SOURCES: A systematic search of Medline, PubMed, Embase, Clinical Trials Register, and Cochrane Library-identified articles comparing robotic with laparoscopic rectal resections was performed. MAIN OUTCOME MEASURES: The outcome measures were quality of life and urinary, sexual, and GI functions between robotic and laparoscopic rectal resection patient groups. Where comparable data were available, results were pooled for analysis. RESULTS: The initial search revealed 1777 papers; 101 were reviewed in full, and 14 studies were included for review. Eleven assessed male sexual function; 7 favored robotic surgery, and the remaining studies showed no significant difference. Pooled analysis of 5 studies reporting rates of male sexual dysfunction at 12 months showed significantly lower rates after robotic surgery (OR, 0.51; p = 0.043). Twelve studies compared urinary function. Six favored robotic surgery, but in 2 studies, a difference was seen at 6 months but not sustained at 12 months. Pooled analysis of 4 studies demonstrated significantly better urinary function scores at 12 months after robotic surgery (OR, 0.26; p = 0.016). Quality of life and GI function were equivalent, but very little data exist for these parameters. LIMITATIONS: A small number of studies compare outcomes between these groups; only 2 are randomized. Different scoring systems limit comparisons and pooling of data. CONCLUSIONS: The limited available data suggest that robotic rectal cancer resection improves male sexual and urinary functions when compared with laparoscopy, but there is no difference in quality of life or GI function. Future studies should report all facets of functional outcomes using standardized scoring systems.

The National Aeronautics and Space Administration-task load index: NASA-TLX: evaluation of its use in surgery.

BACKGROUND: The technical difficulty an operation creates for a surgeon is difficult to measure. Current measures are poor surrogates. In both research and teaching settings it would be valuable to be able to accurately measure this degree of difficulty. The National Aeronautics and Space Administration Task Load Index (NASA TLX) is a multi-dimensional scale designed to obtain workload estimates relating to a task. This study aimed to evaluate the NASA TLX as an objective measure of technical difficulty of an operation. METHODS: Seven surgeons performed 127 pre-defined operations (minimally invasive right hemicolectomy & re-do bariatric surgery) and recorded a NASA TLX score after each operation. These scores were compared to numerous clinical parameters and the score was correlated with the subjective measure of whether the surgeon categorized the operation as "easy", "moderate" or "difficult". RESULTS: The NASA TLX score was significantly correlated with operative duration, blood loss, previous abdominal surgery and the surgeons' assessment of difficulty. It did not correlate with intra-operative or post-operative complications, conversion to open surgery or length of stay. CONCLUSIONS: The NASA TLX score provides a graded numerical score that that correlated significantly with the surgeon's assessment of the technical difficulty, and with operative duration, intra-operative blood loss and previous abdominal surgery. This novel application of this tool could be employed in both research and teaching settings to score surgical difficulty and monitor a trainee's proficiency over time.

The Impact of Neoadjuvant Chemotherapy on the Surgical Management of Colorectal Peritoneal Metastases: A Systematic Review and Meta-Analysis.

BACKGROUND: Cytoreductive surgery (CRS) with or without hyperthermic intraperitoneal chemotherapy (HIPEC) is a well-recognised treatment option for the management of colorectal peritoneal metastases (CRPM). However, incorporating the routine use of neoadjuvant chemotherapy (NAC) into this management plan is controversial. METHODS: A systematic review and meta-analysis were conducted to evaluate the impact of neoadjuvant chemotherapy on perioperative morbidity and mortality, and long-term survival of patients with CRPM undergoing CRS and HIPEC. RESULTS: Twelve studies met the inclusion criteria (n = 2,463 patients). Ten were retrospective cohort, one was prospective cohort, and one was a prospective randomised by design. Patients who received NAC followed by CRS and HIPEC experienced no difference in major perioperative morbidity and mortality compared with patients who underwent surgery first (SF). There was no difference in overall survival at 3 years, but at 5 years NAC patients had superior survival (relative risk [RR] 1.31; 95% confidence interval [CI] 1.11-1.54, P < 0.001). There were no differences in 1- and 3-year, disease-free survival (DFS) between groups. Study heterogeneity was generally high across all outcome measures. CONCLUSIONS: Patients who received neoadjuvant chemotherapy did not experience any increase in perioperative morbidity or mortality. The potential improvement in 5-year overall survival in patients receiving NAC is based on limited confidence due to several limitations in the data, but not sufficiently enough to curtail its use. The practice of NAC in this setting will remain heterogeneous and guided by retrospective evidence until prospective, randomised data are reported.

The learning curve in robotic colorectal surgery compared with laparoscopic colorectal surgery: a systematic review.

AIM: The learning curve has implications for efficient surgical training. Robotic surgery is perceived to have a shorter learning curve than laparoscopy; however, detailed analysis is lacking. The aim of this work was to analyse studies comparing robotic and laparoscopic colorectal learning curves. Simulation studies comparing novices' learning curves were analysed in order to surmise applicability to colorectal surgery. METHOD: A systematic search of Medline, PubMed, Embase and the Cochrane Library identified colorectal papers (from 1 January 2000 to 3 March 2021) comparing robotic and laparoscopic learning curves where surgeons lacked laparoscopic colorectal experience. Simulation studies comparing learning curves were also included. The learning curve was defined as the period of ongoing improvement in speed and/or accuracy. RESULTS: From 576 abstracts reviewed, three operative and 16 simulation studies were included. The robotic learning curve for right colectomy was significantly faster in one study (16 vs. 25 cases) and equal for anterior resection in two studies (44 vs. 41 cases and 55 vs. 55). One study showed fewer complications for robotic patients (14.6% vs. 0%, p = 0.013). Ten simulation studies reported faster times and eight recorded error rates favouring robotic surgery. Seven studies measured the learning curve. Four favoured laparoscopic surgery, but operating times were faster using the robotic platform. CONCLUSION: Operating times for robotic surgery may be faster than laparoscopy when surgeons are inexperienced with both platforms. This may be related to a superior baseline performance rather than a shorter learning curve. Whether a shorter learning curve on the laparoscopic platform will persist for long enough to enable skills to overtake robotic ability needs further investigation.