Applicability of the surgical risk calculator by the American College of Surgeons in the setting of German patients undergoing complete pancreatectomy: multicentre study using data from the StuDoQ|Pancreas registry

Höhn, Philipp; Runde, Fabian; Luu, Andreas Minh; Fahlbusch, Tim; Fein, Daniel; Klinger, Carsten; Uhl, Waldemar; Belyaev, Orlin; Keck, Tobias; Werner, Jens; Nüssler, Natascha C.; Bartsch, Detlef K.; Germer, Christoph‐Thomas; Friess, Helmut; Mönch, Christian; Oldhafer, KJ; Kalff, Jörg C.

doi:10.1093/bjsopen/zrac164

Cited by 3 publications

(2 citation statements)

References 26 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This means that it requires more ressources to collect and enter the data into the calculator. Furthermore, it lacks prove of general transferability to Germany or a European setting [38,39]. The assessment with The Prehab App risk calculator did take less than 5 min before the surgical procedure.…”

Section: Discussionmentioning

confidence: 99%

Predictive value of a novel digital risk calculator to determine early patient outcomes after major surgery: a proof-of-concept pilot study

Sliwinski,

Faqar-Uz-Zaman,

Heil

et al. 2024

Patient Saf Surg

View full text Add to dashboard Cite

Background A structured risk assessment of patients with validated and evidence-based tools can help to identify modifiable factors before major surgeries. The Protego Maxima trial investigated the value of a new digitized risk assessment tool that combines tools which can be easily used and implemented in the clinical workflow by doctors and qualified medical staff. The hypothesis was that the structured assessment and risk-grouping is predictive of short-term surgical quality reflected by complications and overall survival. Methods The Protego Maxima Trial was a prospective cohort analysis of patients undergoing major surgery (visceral, thoracic, urology, vascular and gynecologic surgeries) as key inclusion criterion and the absence of an acute or acute on chronically decompensated pulmo-cardiovascular decompensation. Patients were risk-scored with the software (The Prehab App) that includes a battery of evidence-based risk assessment tools that allow a structured risk assessment. The data were grouped to predefined high and low risk groups and aggregate and individual scores. The primary outcome was to validate the predictive value of the RAI score and the TUG for overall survival in the high and low risk groups. Secondary outcomes were surgical outcomes at 90-days after surgery (overall survival, Clavien-Dindo (CD) 1–5 (all complications), and CD 3–5 (major complications)). The study was carried out in accordance with the DIN ISO 14,155, and the medical device regulation (MDR) at Frankfurt University Hospital between March 2022 and January 2023. Results In total 267 patients were included in the intention to treat analysis. The mean age was 62.1 ± 12.4 years. Patients with a RAI score > 25 and/or a timed up and go (TUG) > 8 s had a higher risk for mortality at 90 days after surgery. The low-risk group predicted beneficial outcome and the high-risk group predicted adverse outcome in the ROC analysis (Area Under the Curve Receiver Operator Characteristics: AUROC > 0.800; p = 0.01). Risk groups (high vs. low) showed significant differences for 90-day survival (99.4% vs. 95.5%; p = 0.04) and major complications (16.4% vs. 32.4%; p < 0.001). Conclusion The proof-of-concept trial showed that a risk assessment with ‘The Prehab App’ may be viable to estimate the preoperative risk for mortality and major complications before major surgeries. The overall performance in this initial set of data indicated a certain reliability of the scoring and risk grouping, especially of the RAI score and the TUG. A larger data set will be required to proof the generalizability of the risk scoring to every subgroup and may be fostered by artificial intelligence approaches. Trial registration Ethics number: 2021-483-MDR/MPDG-zuständig monocentric; The Federal Institute for Pharmaceuticals and Medical Devices/BfArM, reference number: 94.1.04-5660-13655; Eudamed: CIV-21-07-0307311; German Clinical Trial Registry: DRKS 00026985.

show abstract

Section: Discussionmentioning

confidence: 99%

Predictive value of a novel digital risk calculator to determine early patient outcomes after major surgery: a proof-of-concept pilot study

Sliwinski,

Faqar-Uz-Zaman,

Heil

et al. 2024

Patient Saf Surg

View full text Add to dashboard Cite

show abstract

“…7 Due to these factors as well as the fact that upwards of 80% of successfully resected patients suffer tumor recurrence 8 , the risk of an operative approach to PDAC treatment needs to be carefully weighed against the potential benefits, and tools for identifying PoC risks thus play an important role in selecting optimal treatment strategies for PDAC patients. While multiple risk prediction tools have been proposed for both general surgical and PDAC patients, these have reported varied performance in terms of identifying PoC risks 9,10 , especially for PD patients 11 . Novel approaches such as artificial intelligence (AI) deep neural networks (DNNs) have, however, recently shown superior performance over legacy approaches in PoC prediction 12 although the potential value for pancreatic surgery patients remain unknown.…”

Section: Introductionmentioning

confidence: 99%

Assessing The Value of Deep Neural Networks for Postoperartive Complication Prediction in Pancreaticoduodenectomy Patients

Bonde,

Kaafarani

et al. 2023

Preprint

View full text Add to dashboard Cite

IntroductionPancreaticoduodenectomy (PD) for patients with pancreatic ductal adenocarcinoma (PDAC) is associated with a high risk of postoperative complications (PoCs) and risk prediction of these is therefore critical for optimal treatment planning. We hypothesize that novel deep learning network approaches through transfer learning may be superior to legacy approaches for PoC risk prediction in the PDAC surgical setting.MethodsData from the US National Surgical Quality Improvement Program (NSQIP) 2002-2018 was used, with a total of 5,881,881 million patients, including 31,728 PD patients. Modelling approaches comprised of a model trained on a general surgery patient cohort and then tested on a PD specific cohort (general model), a transfer learning model trained on the general surgery patients with subsequent transfer and retraining on a PD-specific patient cohort (transfer learning model), a model trained and tested exclusively on the PD-specific patient cohort (direct model), and a benchmark random forest model trained on the PD patient cohort (RF model). The models were subsequently compared against the American College of Surgeons (ACS) surgical risk calculator (SRC) in terms of predicting mortality and morbidity risk.ResultsBoth the general model and transfer learning model outperformed the RF model in 14 and 16 out of 19 prediction tasks, respectively. Additionally, both models outperformed the direct model on 17 out of the 19 tasks. The transfer learning model also outperformed the general model on 11 out of the 19 prediction tasks. The transfer learning model outperformed the ACS-SRC regarding mortality and all the models outperformed the ACS-SRC regarding the morbidity prediction with the general model achieving the highest Receiver Operator Area Under the Curve (ROC AUC) of 0.668 compared to the 0.524 of the ACS SRC.ConclusionDNNs deployed using a transfer learning approach may be of value for PoC risk prediction in the PD setting.

show abstract

Digital risk calculator for early surgical outcomes in patients undergoing major surgeries – a prospective cohort study

Sliwinski,

Faqar-Uz-Zaman,

Heil

et al. 2024

Preprint

View full text Add to dashboard Cite

Introduction: Surgery puts patients at relevant risk for complications. Knowing a patient's risk helps to identify modifiable and unmodifiable factors to weigh the benefit of surgery against the risk of harm. A structured data analysis with validated tools will increase the reliability of risk assessment. Digitized solutions may add additional value. The Protego Maxima trial evaluated a health app for structured risk assessment before major surgeries and utilizing. The hypothesis was that the structured assessment is predictive of short-term surgical quality. Methods: Patients undergoing major surgery were risk-scored with the software (The Prehab App), and the scores were correlated with 90-day outcomes (survival, Clavien-Dindo (CD) 1-5 (all complications), and CD 3-5 (major complications)). Results: The study included 267 patients. Mean age was 62.1 ± 12.4 years, the risk analysis index (RAI)-score was 21.5 ± 9.7, the timed up and go (TUG) was 7.7 ± 2.3 seconds, 89 patients (33%) were anemic, and 238 patients had an Eastern Cooperative Oncology Group (ECOG) score of 0 (89.1%), 23 of 1 (8.6%), 6 of 2 or 3 (2.3%) which defined the risk groups (low risk: 156 (58.4%), high risk: 111 (41.6%). Receiver operator characteristics (ROC) showed a highly significant potential of the risk score in its prediction of mortality for the high-risk group (Area Under the Curve Receiver Operator Characteristics: AUROC = 0.842) and for the low-risk group (AUROC = 0,990) with difference in AUROCs of -0.149 (95% CI: -0.263; -0.034; p=0.01). The 90-day mortality was 2.2%. Complication rates were 59.9%; major complication rates were 22.5%. Risk groups (high vs. low) showed significant differences for 90-day survival (99.4% vs. 95.5%; p=0.04) and major complications (16.4% vs. 32.4%; p<0.001). Conclusion: The risk assessment with The Prehab App is a viable method to identify risk factors for mortality before major surgeries. The specific validated scoring tools deliver robust and reliable data.

show abstract

Applicability of the surgical risk calculator by the American College of Surgeons in the setting of German patients undergoing complete pancreatectomy: multicentre study using data from the StuDoQ|Pancreas registry

Cited by 3 publications

References 26 publications

Predictive value of a novel digital risk calculator to determine early patient outcomes after major surgery: a proof-of-concept pilot study

Predictive value of a novel digital risk calculator to determine early patient outcomes after major surgery: a proof-of-concept pilot study

Assessing The Value of Deep Neural Networks for Postoperartive Complication Prediction in Pancreaticoduodenectomy Patients

Digital risk calculator for early surgical outcomes in patients undergoing major surgeries – a prospective cohort study

Contact Info

Product

Resources

About