Explainable artificial intelligence prediction-based model in laparoscopic liver surgery for segments 7 and 8 : an international multicenter study
© 2024. The Author(s)..
BACKGROUND: Artificial intelligence (AI) is becoming more useful as a decision-making and outcomes predictor tool. We have developed AI models to predict surgical complexity and the postoperative course in laparoscopic liver surgery for segments 7 and 8.
METHODS: We included patients with lesions located in segments 7 and 8 operated by minimally invasive liver surgery from an international multi-institutional database. We have employed AI models to predict surgical complexity and postoperative outcomes. Furthermore, we have applied SHapley Additive exPlanations (SHAP) to make the AI models interpretable. Finally, we analyzed the surgeries not converted to open versus those converted to open.
RESULTS: Overall, 585 patients and 22 variables were included. Multi-layer Perceptron (MLP) showed the highest performance for predicting surgery complexity and Random Forest (RF) for predicting postoperative outcomes. SHAP detected that MLP and RF gave the highest relevance to the variables "resection type" and "largest tumor size" for predicting surgery complexity and postoperative outcomes. In addition, we explored between surgeries converted to open and non-converted, finding statistically significant differences in the variables "tumor location," "blood loss," "complications," and "operation time.".
CONCLUSION: We have observed how the application of SHAP allows us to understand the predictions of AI models in surgical complexity and the postoperative outcomes of laparoscopic liver surgery in segments 7 and 8.
Errataetall: | |
---|---|
Medienart: |
E-Artikel |
Erscheinungsjahr: |
2024 |
---|---|
Erschienen: |
2024 |
Enthalten in: |
Zur Gesamtaufnahme - year:2024 |
---|---|
Enthalten in: |
Surgical endoscopy - (2024) vom: 05. Feb. |
Sprache: |
Englisch |
---|
Links: |
---|
Themen: |
Artificial intelligence |
---|
Anmerkungen: |
Date Revised 20.03.2024 published: Print-Electronic ErratumIn: Surg Endosc. 2024 Mar 19;:. - PMID 38503907 Citation Status Publisher |
---|
doi: |
10.1007/s00464-024-10681-6 |
---|
funding: |
|
---|---|
Förderinstitution / Projekttitel: |
|
PPN (Katalog-ID): |
NLM368044742 |
---|
LEADER | 01000caa a22002652 4500 | ||
---|---|---|---|
001 | NLM368044742 | ||
003 | DE-627 | ||
005 | 20240320234113.0 | ||
007 | cr uuu---uuuuu | ||
008 | 240206s2024 xx |||||o 00| ||eng c | ||
024 | 7 | |a 10.1007/s00464-024-10681-6 |2 doi | |
028 | 5 | 2 | |a pubmed24n1337.xml |
035 | |a (DE-627)NLM368044742 | ||
035 | |a (NLM)38315197 | ||
040 | |a DE-627 |b ger |c DE-627 |e rakwb | ||
041 | |a eng | ||
100 | 1 | |a Lopez-Lopez, Victor |e verfasserin |4 aut | |
245 | 1 | 0 | |a Explainable artificial intelligence prediction-based model in laparoscopic liver surgery for segments 7 and 8 |b an international multicenter study |
264 | 1 | |c 2024 | |
336 | |a Text |b txt |2 rdacontent | ||
337 | |a ƒaComputermedien |b c |2 rdamedia | ||
338 | |a ƒa Online-Ressource |b cr |2 rdacarrier | ||
500 | |a Date Revised 20.03.2024 | ||
500 | |a published: Print-Electronic | ||
500 | |a ErratumIn: Surg Endosc. 2024 Mar 19;:. - PMID 38503907 | ||
500 | |a Citation Status Publisher | ||
520 | |a © 2024. The Author(s). | ||
520 | |a BACKGROUND: Artificial intelligence (AI) is becoming more useful as a decision-making and outcomes predictor tool. We have developed AI models to predict surgical complexity and the postoperative course in laparoscopic liver surgery for segments 7 and 8 | ||
520 | |a METHODS: We included patients with lesions located in segments 7 and 8 operated by minimally invasive liver surgery from an international multi-institutional database. We have employed AI models to predict surgical complexity and postoperative outcomes. Furthermore, we have applied SHapley Additive exPlanations (SHAP) to make the AI models interpretable. Finally, we analyzed the surgeries not converted to open versus those converted to open | ||
520 | |a RESULTS: Overall, 585 patients and 22 variables were included. Multi-layer Perceptron (MLP) showed the highest performance for predicting surgery complexity and Random Forest (RF) for predicting postoperative outcomes. SHAP detected that MLP and RF gave the highest relevance to the variables "resection type" and "largest tumor size" for predicting surgery complexity and postoperative outcomes. In addition, we explored between surgeries converted to open and non-converted, finding statistically significant differences in the variables "tumor location," "blood loss," "complications," and "operation time." | ||
520 | |a CONCLUSION: We have observed how the application of SHAP allows us to understand the predictions of AI models in surgical complexity and the postoperative outcomes of laparoscopic liver surgery in segments 7 and 8 | ||
650 | 4 | |a Journal Article | |
650 | 4 | |a Artificial intelligence | |
650 | 4 | |a Liver resection | |
650 | 4 | |a Making decision | |
650 | 4 | |a Minimally invasive surgery | |
700 | 1 | |a Morise, Zeniche |e verfasserin |4 aut | |
700 | 1 | |a Albaladejo-González, Mariano |e verfasserin |4 aut | |
700 | 1 | |a Gavara, Concepción Gomez |e verfasserin |4 aut | |
700 | 1 | |a Goh, Brian K P |e verfasserin |4 aut | |
700 | 1 | |a Koh, Ye Xin |e verfasserin |4 aut | |
700 | 1 | |a Paul, Sijberden Jasper |e verfasserin |4 aut | |
700 | 1 | |a Hilal, Mohammed Abu |e verfasserin |4 aut | |
700 | 1 | |a Mishima, Kohei |e verfasserin |4 aut | |
700 | 1 | |a Krürger, Jaime Arthur Pirola |e verfasserin |4 aut | |
700 | 1 | |a Herman, Paulo |e verfasserin |4 aut | |
700 | 1 | |a Cerezuela, Alvaro |e verfasserin |4 aut | |
700 | 1 | |a Brusadin, Roberto |e verfasserin |4 aut | |
700 | 1 | |a Kaizu, Takashi |e verfasserin |4 aut | |
700 | 1 | |a Lujan, Juan |e verfasserin |4 aut | |
700 | 1 | |a Rotellar, Fernando |e verfasserin |4 aut | |
700 | 1 | |a Monden, Kazuteru |e verfasserin |4 aut | |
700 | 1 | |a Dalmau, Mar |e verfasserin |4 aut | |
700 | 1 | |a Gotohda, Naoto |e verfasserin |4 aut | |
700 | 1 | |a Kudo, Masashi |e verfasserin |4 aut | |
700 | 1 | |a Kanazawa, Akishige |e verfasserin |4 aut | |
700 | 1 | |a Kato, Yutaro |e verfasserin |4 aut | |
700 | 1 | |a Nitta, Hiroyuki |e verfasserin |4 aut | |
700 | 1 | |a Amano, Satoshi |e verfasserin |4 aut | |
700 | 1 | |a Valle, Raffaele Dalla |e verfasserin |4 aut | |
700 | 1 | |a Giuffrida, Mario |e verfasserin |4 aut | |
700 | 1 | |a Ueno, Masaki |e verfasserin |4 aut | |
700 | 1 | |a Otsuka, Yuichiro |e verfasserin |4 aut | |
700 | 1 | |a Asano, Daisuke |e verfasserin |4 aut | |
700 | 1 | |a Tanabe, Minoru |e verfasserin |4 aut | |
700 | 1 | |a Itano, Osamu |e verfasserin |4 aut | |
700 | 1 | |a Minagawa, Takuya |e verfasserin |4 aut | |
700 | 1 | |a Eshmuminov, Dilmurodjon |e verfasserin |4 aut | |
700 | 1 | |a Herrero, Irene |e verfasserin |4 aut | |
700 | 1 | |a Ramírez, Pablo |e verfasserin |4 aut | |
700 | 1 | |a Ruipérez-Valiente, José A |e verfasserin |4 aut | |
700 | 1 | |a Robles-Campos, Ricardo |e verfasserin |4 aut | |
700 | 1 | |a Wakabayashi, Go |e verfasserin |4 aut | |
773 | 0 | 8 | |i Enthalten in |t Surgical endoscopy |d 1996 |g (2024) vom: 05. Feb. |w (DE-627)NLM012660159 |x 1432-2218 |7 nnns |
773 | 1 | 8 | |g year:2024 |g day:05 |g month:02 |
856 | 4 | 0 | |u http://dx.doi.org/10.1007/s00464-024-10681-6 |3 Volltext |
912 | |a GBV_USEFLAG_A | ||
912 | |a GBV_NLM | ||
951 | |a AR | ||
952 | |j 2024 |b 05 |c 02 |