Multimodal machine learning to predict surgical site infection with healthcare workload impact assessment

被引：0

作者：

Mclean, Kenneth A. ^{[1
,2
]}

Sgro, Alessandro ^{[3
]}

Brown, Leo R. ^{[1
]}

Buijs, Louis F. ^{[3
]}

Mountain, Katie E. ^{[1
]}

Shaw, Catherine A. ^{[1
,2
]}

Drake, Thomas M. ^{[1
,2
]}

Pius, Riinu ^{[1
,2
]}

Knight, Stephen R. ^{[1
,2
]}

Fairfield, Cameron J. ^{[1
,2
]}

Skipworth, Richard J. E. ^{[1
]}

Tsaftaris, Sotirios A. ^{[4
]}

Wigmore, Stephen J. ^{[1
]}

Potter, Mark A. ^{[3
]}

Bouamrane, Matt-Mouley ^{[2
]}

Harrison, Ewen M. ^{[1
,2
]}

Baweja, K. ^{[5
]}

Cambridge, W. A. ^{[5
]}

Chauhan, V. ^{[5
]}

Czyzykowska, K. ^{[5
]}

Edirisooriya, M. ^{[5
]}

Forsyth, A. ^{[5
]}

Fox, B. ^{[5
]}

Fretwell, J. ^{[5
]}

Gent, C. ^{[5
]}

Gherman, A. ^{[5
]}

Green, L. ^{[5
]}

Grewar, J. ^{[5
]}

Heelan, S. ^{[5
]}

Henshall, D. ^{[5
]}

Iiuoma, C. ^{[5
]}

Jayasangaran, S. ^{[5
]}

Johnston, C. ^{[1
]}

Kennedy, E. ^{[2
]}

Kremel, D. ^{[3
]}

Kung, J. ^{[1
]}

Kwong, J. ^{[5
]}

Leavy, C. ^{[5
]}

Liu, J. ^{[5
]}

Mackay, S. ^{[5
]}

Macnamara, A. ^{[1
]}

Mowitt, S. ^{[1
]}

Musenga, E. ^{[5
]}

Ng, N. ^{[5
]}

Ng, Z. H. ^{[5
]}

O'Neill, S. ^{[1
]}

Ramage, M. ^{[1
]}

Reed, J. ^{[5
]}

Riad, A. ^{[5
]}

Scott, C. ^{[5
]}

机构：

[1] Univ Edinburgh, Dept Clin Surg, 51 Little France Crescent, Edinburgh EH16 4SA, Scotland

[2] Univ Edinburgh, Usher Inst, Ctr Med Informat, 9 Little France Rd, Edinburgh EH16 4UX, Scotland

[3] Western Gen Hosp, Colorectal Unit, Edinburgh EH4 2XU, Scotland

[4] UNIV EDINBURGH, AI Hub Causal Healthcare AI Real Data, EDINBURGH EH9 3FG, Scotland

[5] Univ Edinburgh, Edinburgh Med Sch, Edinburgh, Scotland

来源：

NPJ DIGITAL MEDICINE | 2025年 / 8卷 / 01期

基金：

英国医学研究理事会;

关键词：

IMPLEMENTATION; INTERVENTIONS;

D O I：

10.1038/s41746-024-01419-8

中图分类号：

R19 [保健组织与事业（卫生事业管理）];

学科分类号：

摘要：

Remote monitoring is essential for healthcare digital transformation, however, this poses greater burdens on healthcare providers to review and respond as the data collected expands. This study developed a multimodal neural network to automate assessments of patient-generated data from remote postoperative wound monitoring. Two interventional studies including adult gastrointestinal surgery patients collected wound images and patient-reported outcome measures (PROMs) for 30-days postoperatively. Neural networks for PROMs and images were combined to predict surgical site infection (SSI) diagnosis within 48 h. The multimodal neural network model to predict confirmed SSI within 48 h remained comparable to clinician triage (0.762 [0.690-0.835] vs 0.777 [0.721-0.832]), with an excellent performance on external validation. Simulated usage indicated an 80% reduction in staff time (51.5 to 9.1 h) without compromising diagnostic accuracy. This multimodal approach can effectively support remote monitoring, alleviating provider burden while ensuring high-quality postoperative care.

引用

页数：10

共 50 条

[1] Using Machine Learning to Predict Surgical Site Infection After Lumbar Spine Surgery
Chen, Tianyou
Liu, Chong
Zhang, Zide
Liang, Tuo
Zhu, Jichong
Zhou, Chenxing
Wu, Shaofeng
Yao, Yuanlin
Huang, Chengqian
Zhang, Bin
Feng, Sitan
Wang, Zequn
Huang, Shengsheng
Sun, Xuhua
Chen, Liyi
Zhan, Xinli
INFECTION AND DRUG RESISTANCE, 2023, 16 : 5197 - 5207
[2] A machine learning model to predict surgical site infection after surgery of lower extremity fractures
Gutierrez-Naranjo, Jose M.
Moreira, Alvaro
Valero-Moreno, Eduardo
Bullock, Travis S.
Ogden, Liliana A.
Zelle, Boris A.
INTERNATIONAL ORTHOPAEDICS, 2024, 48 (07) : 1887 - 1896
[3] Application of Machine Learning to Prediction of Surgical Site Infection
Fletcher, Richard Ribon
Olubeko, Olasubomi
Sonthalia, Harsh
Kateera, Fredrick
Nkurunziza, Theoneste
Ashby, Joanna L.
Riviello, Robert
Hedt-Gauthier, Bethany
2019 41ST ANNUAL INTERNATIONAL CONFERENCE OF THE IEEE ENGINEERING IN MEDICINE AND BIOLOGY SOCIETY (EMBC), 2019, : 2234 - 2237
[4] Impact of a Multimodal Approach in Prevention of Surgical Site Infection in Hepatic Transplant Recipients
Prieto, J.
Medina, J. C.
Lopez, M.
Rando, K.
Iglesias, C.
Harguindeguy, M.
Leites, A.
Etlin, A.
Menendez, J.
Valverde, M.
Scalone, P.
Castelli, J.
Grecco, G.
Abelleira, M.
Gonzalez, L. S.
Gerona, S.
TRANSPLANTATION PROCEEDINGS, 2016, 48 (02) : 658 - 664
[5] Is it possible to predict Surgical Site Infection?
Erciyestepe, Sezgi Gullu
Boran, Ahmet Birtan
Yildirim, Merve Sezer
Erciyestepe, Mert
MALAWI MEDICAL JOURNAL, 2023, 35 (03) : 190 - 195
[6] Review of multimodal machine learning approaches in healthcare
Krones, Felix
Marikkar, Umar
Parsons, Guy
Szmul, Adam
Mahdi, Adam
INFORMATION FUSION, 2025, 114
[7] Machine learning applications for the prediction of surgical site infection in neurological operations
Tunthanathip, Thara
Sae-heng, Sakchai
Oearsakul, Thakul
Sakarunchai, Ittichai
Kaewborisutsakul, Anukoon
Taweesomboonyat, Chin
NEUROSURGICAL FOCUS, 2019, 47 (02)
[8] Blood Biomarkers Predict Cardiac Workload Using Machine Learning
Shou, Lan
Huang, Wendy Wenyu
Barszczyk, Andrew
Wu, Si Jia
Han, Helen
Waese-Perlman, Alex
Chen, Lulu
Wei, Jing
Luo, Hong
Lee, Kang
BIOMED RESEARCH INTERNATIONAL, 2021, 2021
[9] Using multiple indicators to predict the risk of surgical site infection after ORIF of tibia fractures: a machine learning based study
Ying, Hui
Guo, Bo-Wen
Wu, Hai-Jian
Zhu, Rong-Ping
Liu, Wen-Cai
Zhong, Hong-Fa
FRONTIERS IN CELLULAR AND INFECTION MICROBIOLOGY, 2023, 13
[10] Systematic evaluation of machine learning models for postoperative surgical site infection prediction
van Boekel, Anna M.
van der Meijden, Siri L.
Arbous, Sesmu M.
Nelissen, Rob G. H. H.
Veldkamp, Karin E.
Nieswaag, Emma B.
Jochems, Kim F. T.
Holtz, Jeroen
Veenstra, Annekee van IJlzinga
Reijman, Jeroen
de Jong, Ype
van Goor, Harry
Wiewel, Maryse A.
Schoones, Jan W.
Geerts, Bart F.
de Boer, Mark G. J.
PLOS ONE, 2024, 19 (12):

← 1 2 3 4 5 →