Forecasting adverse surgical events using self-supervised transfer learning for physiological signals

Chen, Hugh; Lundberg, Scott; Erion, Gabriel; Kim, Jerry H.; Lee, Su-In

doi:10.1038/s41746-021-00536-y

Cited by 37 publications

(47 citation statements)

References 60 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This represents an example where the complementary relationship between humans and machines can outperform either one alone. More recently Chen et al ( 37 ) tested a transferable embedding method (i.e., a method to transform time series signals into input features for predictive ML models) named PHASE (PHysiologicAl Signal Embeddings) with a large amount of dataset from ORs and ICU. Results indicated that PHASE outperforms other state-of-the-art approaches in predicting six distinct outcomes: hypoxemia, hypocapnia, hypotension, hypertension, phenylephrine, and epinephrine ( 37 ).…”

Section: Discussionmentioning

confidence: 99%

Artificial intelligence and anesthesia: a narrative review

Carnà¹,

Russo²,

Vincenzo³

et al. 2022

Ann Transl Med

View full text Add to dashboard Cite

Background and Objective The aim of this narrative review is to analyze whether or not artificial intelligence (AI) and its subsets are implemented in current clinical anesthetic practice, and to describe the current state of the research in the field. AI is a general term which refers to all the techniques that enable computers to mimic human intelligence. AI is based on algorithms that gives machines the ability to reason and perform functions such as problem-solving, object and word recognition, inference of world states, and decision-making. It includes machine learning (ML) and deep learning (DL). Methods We performed a narrative review of the literature on Scopus, PubMed and Cochrane databases. The research string comprised various combinations of “artificial intelligence”, “machine learning”, “anesthesia”, “anesthesiology”. The databases were searched independently by two authors. A third reviewer would mediate any disagreement the results of the two screeners. Key Content and Findings The application of AI has shown excellent results in both anesthesia and in operating room (OR) management. In each phase of the perioperative process, pre-, intra- and postoperative ones, it is able to perform different and specific tasks, using various techniques. Conclusions Thanks to the use of these new technologies, even anesthesia, as it is happening for other disciplines, is going through a real revolution, called Anesthesia 4.0. However, AI is not free from limitations and open issues. Unfortunately, the models created, provided they have excellent performance, have not yet entered daily practice. Clinical impact analyzes and external validations are needed before this happens. Therefore, qualitative research will be needed to better understand the ethical, cultural, and societal implications of integrating AI into clinical workflows.

show abstract

Section: Discussionmentioning

confidence: 99%

Artificial intelligence and anesthesia: a narrative review

Carnà¹,

Russo²,

Vincenzo³

et al. 2022

Ann Transl Med

View full text Add to dashboard Cite

show abstract

“…Hence, we argue that transfer learning might be a promising and feasible strategy to maintain the effectiveness of the trans-center deployment of machine learning models. Furthermore, transfer learning has been applied to similar domains or similar tasks in several medical fields, reducing the size requirements of the target dataset, and improving the training speed and the prediction performance [ 35 – 38 ]. In our context, transfer learning can be used to predict different types of diseases, such as disseminated intravascular coagulation (DIC) or acute kidney injury (AKI).…”

Section: Discussionmentioning

confidence: 99%

Transferability and interpretability of the sepsis prediction models in the intensive care unit

Chen

Lin

et al. 2022

BMC Med Inform Decis Mak

View full text Add to dashboard Cite

Background We aimed to develop an early warning system for real-time sepsis prediction in the ICU by machine learning methods, with tools for interpretative analysis of the predictions. In particular, we focus on the deployment of the system in a target medical center with small historical samples. Methods Light Gradient Boosting Machine (LightGBM) and multilayer perceptron (MLP) were trained on Medical Information Mart for Intensive Care (MIMIC-III) dataset and then finetuned on the private Historical Database of local Ruijin Hospital (HDRJH) using transfer learning technique. The Shapley Additive Explanations (SHAP) analysis was employed to characterize the feature importance in the prediction inference. Ultimately, the performance of the sepsis prediction system was further evaluated in the real-world study in the ICU of the target Ruijin Hospital. Results The datasets comprised 6891 patients from MIMIC-III, 453 from HDRJH, and 67 from Ruijin real-world data. The area under the receiver operating characteristic curves (AUCs) for LightGBM and MLP models derived from MIMIC-III were 0.98 − 0.98 and 0.95 − 0.96 respectively on MIMIC-III dataset, and, in comparison, 0.82 − 0.86 and 0.84 − 0.87 respectively on HDRJH, from 1 to 5 h preceding. After transfer learning and ensemble learning, the AUCs of the final ensemble model were enhanced to 0.94 − 0.94 on HDRJH and to 0.86 − 0.9 in the real-world study in the ICU of the target Ruijin Hospital. In addition, the SHAP analysis illustrated the importance of age, antibiotics, net balance, and ventilation for sepsis prediction, making the model interpretable. Conclusions Our machine learning model allows accurate real-time prediction of sepsis within 5-h preceding. Transfer learning can effectively improve the feasibility to deploy the prediction model in the target cohort, and ameliorate the model performance for external validation. SHAP analysis indicates that the role of antibiotic usage and fluid management needs further investigation. We argue that our system and methodology have the potential to improve ICU management by helping medical practitioners identify at-sepsis-risk patients and prepare for timely diagnosis and intervention. Trial registration: NCT05088850 (retrospectively registered).

show abstract

“…Having the possibility of a direct recording, with the minimum human interference, could allow instead to increase the quality of the dataset and therefore obtain more precise results. [19][20][21] Furthermore, having a system equipped with the ability to independently record the patient's movements, could be able, in addition to reducing the error rate, to lighten the workload of the operators themselves and indirectly reduce the changeover times between the different patients. [17,21−25] Nevertheless, building a tracking system inside a hospital is not a simple task.…”

Section: Discussionmentioning

confidence: 99%

Internet of Things and Artificial Intelligence for Perioperative Tracking Patients: Towards a New Model for an Operating Rooms

Bottani

Mordonini

Pellegrino

et al. 2022

Preprint

View full text Add to dashboard Cite

Operating rooms management is a critical point in healthcare organizations; inefficient scheduling and allocation of human and physical resources are often present. This study aims to automatically collect data from a real surgical scenario to develop an integrated technological-organizational model that optimizes the operating block resources.Each patient is real-time tracked and located by wearing a bracelet sensor with a unique identifier. Exploiting indoor localization, the software architecture is able to collect the time spent in every steps inside the surgical block. The preliminary results are promising, making the study feasible and functional. Times automatically recorded are much more precise than those collected by humans and reported in the organization's information system. In addition, Machine Learning can exploit the historical data collection to predict the surgery time required for each patient according to the patient’s specific profile. This approach will make it possible to plan short and long-term strategies optimizing the available resources.

show abstract

Forecasting adverse surgical events using self-supervised transfer learning for physiological signals

Cited by 37 publications

References 60 publications

Artificial intelligence and anesthesia: a narrative review

Artificial intelligence and anesthesia: a narrative review

Transferability and interpretability of the sepsis prediction models in the intensive care unit

Internet of Things and Artificial Intelligence for Perioperative Tracking Patients: Towards a New Model for an Operating Rooms

Contact Info

Product

Resources

About