Protocol of a prospective study investigating the association of PAncreatic parenchymal RISk factors with postoperative pancreatic fistula after partial pancreaticoduodenectomy (PARIS trial)

Either High or Low Risk: The Acinar Score at the Resection Margin Dichotomizes the Risk Spectrum of Pancreas-specific Complications After Pancreatoduodenectomy

BACKGROUND

Pancreatic acinar content (Ac) has been associated with pancreas-specific complications after pancreatoduodenectomy. The aim of this study was to improve the prediction ability of intraoperative risk stratification by integrating the pancreatic acinar score.

METHODS

A training and validation cohort underwent pancreatoduodenectomy with a subsequent histologic assessment of pancreatic section margins for Ac, fibrosis (Fc), and fat. Intraoperative risk stratification (pancreatic texture, duct diameter) and pancreas-specific complications (postoperative hyperamylasemia [POH], postpancreatectomy acute pancreatitis [PPAP], pancreatic fistula [POPF]) were classified according to ISGPS definitions.

RESULTS

In the validation cohort (n= 373), the association of pancreas-specific complications with higher Ac and lower Fc was replicated (all P <0.001). In the entire cohort (n= 761), the ISGPS classification allocated 275 (36%) patients into intermediate-risk classes B (POH 32%/PPAP 3%/POPF 17%) and C (POH 36%/PPAP 9%/POPF 33%). Using the acinar score (Ac ≥60% and/or Fc ≤10%), intermediate-risk patients could be dichotomized into a low-risk (POH 5%/PPAP 1%/POPF 6%) and a high-risk (POH 51%/PPAP 9%/POPF 38%) group (all P <0.001). The acinar score AUC for POPF prediction was 0.70 in the ISGPS intermediate-risk classes. Overall, 239 (31%) patients were relocated into the high-risk group from lower ISGPS risk classes using the acinar score.

CONCLUSIONS

The risk of pancreas-specific complications appears to be dichotomous-either high or low-according to the acinar score, a tool to better target the application of mitigation strategies in cases of intermediate macroscopic features.

Surgomics: personalized prediction of morbidity, mortality and long-term outcome in surgery using machine learning on multimodal data

BACKGROUND

Personalized medicine requires the integration and analysis of vast amounts of patient data to realize individualized care. With Surgomics, we aim to facilitate personalized therapy recommendations in surgery by integration of intraoperative surgical data and their analysis with machine learning methods to leverage the potential of this data in analogy to Radiomics and Genomics.

METHODS

We defined Surgomics as the entirety of surgomic features that are process characteristics of a surgical procedure automatically derived from multimodal intraoperative data to quantify processes in the operating room. In a multidisciplinary team we discussed potential data sources like endoscopic videos, vital sign monitoring, medical devices and instruments and respective surgomic features. Subsequently, an online questionnaire was sent to experts from surgery and (computer) science at multiple centers for rating the features' clinical relevance and technical feasibility.

RESULTS

In total, 52 surgomic features were identified and assigned to eight feature categories. Based on the expert survey (n = 66 participants) the feature category with the highest clinical relevance as rated by surgeons was "surgical skill and quality of performance" for morbidity and mortality (9.0 ± 1.3 on a numerical rating scale from 1 to 10) as well as for long-term (oncological) outcome (8.2 ± 1.8). The feature category with the highest feasibility to be automatically extracted as rated by (computer) scientists was "Instrument" (8.5 ± 1.7). Among the surgomic features ranked as most relevant in their respective category were "intraoperative adverse events", "action performed with instruments", "vital sign monitoring", and "difficulty of surgery".

CONCLUSION

Surgomics is a promising concept for the analysis of intraoperative data. Surgomics may be used together with preoperative features from clinical data and Radiomics to predict postoperative morbidity, mortality and long-term outcome, as well as to provide tailored feedback for surgeons.