Artificial Intelligence–Based Multimodal Risk Assessment Model for Surgical Site Infection (AMRAMS): Development and Validation Study

Chen, Weijia; Lu, Zhijun; Li-jue, You; Zhou, Lingling; Xu, Jianpeng; Chen, Ken

doi:10.2196/18186

Cited by 24 publications

(25 citation statements)

References 32 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The application of text mining and NLP in the predictive setting is not new; unlocking the full potential of EHR data is contingent on the development of text mining pipelines to automatically transform free-text into structured clinical data that can guide clinical decisions [ 1 , 2 , 4 , 49 ]. Yet, text as auxiliary variables to classical clinical variables has only been considered in a few studies [ 32 – 34 , 50 , 51 ]. One study [ 51 ] predicted several clinical interventions combining structured data and clinical notes.…”

Section: Discussionmentioning

confidence: 99%

Automatic Prediction of Recurrence of Major Cardiovascular Events: A Text Mining Study Using Chest X-Ray Reports

Bagheri

Groenhof

Asselbergs

et al. 2021

Journal of Healthcare Engineering

View full text Add to dashboard Cite

Background and Objective. Electronic health records (EHRs) contain free-text information on symptoms, diagnosis, treatment, and prognosis of diseases. However, this potential goldmine of health information cannot be easily accessed and used unless proper text mining techniques are applied. The aim of this project was to develop and evaluate a text mining pipeline in a multimodal learning architecture to demonstrate the value of medical text classification in chest radiograph reports for cardiovascular risk prediction. We sought to assess the integration of various text representation approaches and clinical structured data with state-of-the-art deep learning methods in the process of medical text mining. Methods. We used EHR data of patients included in the Second Manifestations of ARTerial disease (SMART) study. We propose a deep learning-based multimodal architecture for our text mining pipeline that integrates neural text representation with preprocessed clinical predictors for the prediction of recurrence of major cardiovascular events in cardiovascular patients. Text preprocessing, including cleaning and stemming, was first applied to filter out the unwanted texts from X-ray radiology reports. Thereafter, text representation methods were used to numerically represent unstructured radiology reports with vectors. Subsequently, these text representation methods were added to prediction models to assess their clinical relevance. In this step, we applied logistic regression, support vector machine (SVM), multilayer perceptron neural network, convolutional neural network, long short-term memory (LSTM), and bidirectional LSTM deep neural network (BiLSTM). Results. We performed various experiments to evaluate the added value of the text in the prediction of major cardiovascular events. The two main scenarios were the integration of radiology reports (1) with classical clinical predictors and (2) with only age and sex in the case of unavailable clinical predictors. In total, data of 5603 patients were used with 5-fold cross-validation to train the models. In the first scenario, the multimodal BiLSTM (MI-BiLSTM) model achieved an area under the curve (AUC) of 84.7%, misclassification rate of 14.3%, and F1 score of 83.8%. In this scenario, the SVM model, trained on clinical variables and bag-of-words representation, achieved the lowest misclassification rate of 12.2%. In the case of unavailable clinical predictors, the MI-BiLSTM model trained on radiology reports and demographic (age and sex) variables reached an AUC, F1 score, and misclassification rate of 74.5%, 70.8%, and 20.4%, respectively. Conclusions. Using the case study of routine care chest X-ray radiology reports, we demonstrated the clinical relevance of integrating text features and classical predictors in our text mining pipeline for cardiovascular risk prediction. The MI-BiLSTM model with word embedding representation appeared to have a desirable performance when trained on text data integrated with the clinical variables from the SMART study. Our results mined from chest X-ray reports showed that models using text data in addition to laboratory values outperform those using only known clinical predictors.

show abstract

Section: Discussionmentioning

confidence: 99%

Automatic Prediction of Recurrence of Major Cardiovascular Events: A Text Mining Study Using Chest X-Ray Reports

Bagheri

Groenhof

Asselbergs

et al. 2021

Journal of Healthcare Engineering

View full text Add to dashboard Cite

show abstract

“…Followed by postoperative data, which integrated with the patient's condition to estimate vital signs, evaluate postoperative needs, recurrency rate, and potential adverse events [ 97 , 102 ]. Chen et al [ 103 ] developed an AI-based multimodal risk assessment model for surgical site infection (AMRAMS) for inpatients undergoing an operation. They compared them with the national nosocomial infections surveillance (NNIS) risk index.…”

Section: Trans-anal Endoscopic Microsurgery and Trans-anal Minimally Invasive Surgerymentioning

confidence: 99%

Minimally invasive gastrointestinal surgery: From past to the future

Rudiman¹

2021

Annals of Medicine and Surgery

View full text Add to dashboard Cite

The improvement of the science and art of surgery began over 150 years ago. Surgical core tasks, “cutting and sewing” with hand and direct contact with the organs, have remained the same. However, in the 21st century, there has been a shifting paradigm in the methodology of surgery. The joint union between innovators, engineers, industry, and patient demands resulted in minimally invasive surgery (MIS). This method has influenced the techniques in every aspect of abdominal surgery, such as surgeons are not required to direct contact or see the structures on which they operate. Advances in the endoscope, imaging, and improved instrumentations convert the essential open surgery into the endoscopic method. Furthermore, computers and robotics show a promising future to facilitate complex procedures, enhance accuracy in microscale operations, and develop a simulation to improve the ability to face sophisticated approaches. MIS has been replacing open surgery due to improved survival, fewer complications, and rapid recoveries in recent years. Minimally invasive surgery's further research in diagnostic and therapeutic modalities is under investigation to achieve genuinely “noninvasive” surgery. Thus, MIS has gained interest in recent days and has been improving with promising outcomes.

show abstract

“…Being human-made, artificial intelligence (AI) can simulate intellectual work such as humans’ thoughts and judgments and has thus revolutionized the medical field ( 5 ). Hence, there is an increasing attention on the application of AI for the diagnosis and treatment of cancer ( 6 , 7 ). In terms of settling the problems of classification and regression, the gradient boosting decision tree (GBDT) is regarded as a powerful ensemble learning technique ( 8 ).…”

Section: Introductionmentioning

confidence: 99%

Employment of Artificial Intelligence Based on Routine Laboratory Results for the Early Diagnosis of Multiple Myeloma

Yan

Shi

et al. 2021

Front. Oncol.

View full text Add to dashboard Cite

ObjectiveIn order to enhance the detection rate of multiple myeloma and execute an early and more precise disease management, an artificial intelligence assistant diagnosis system is developed.Methods4,187 routine blood and biochemical examination records were collected from Shengjing Hospital affiliated to China Medical University from January 2010 to January 2020, which include 1,741 records of multiple myeloma (MM) and 2,446 records of non-myeloma (infectious diseases, rheumatic immune system diseases, hepatic diseases and renal diseases). The data set was split into training and test subsets with the ratio of 4:1 while connecting hemoglobin, serum creatinine, serum calcium, immunoglobulin (A, G and M), albumin, total protein, and the ratio of albumin to globulin data. An early assistant diagnostic model of MM was established by Gradient Boosting Decision Tree (GBDT), Support Vector Machine (SVM), Deep Neural Networks (DNN), and Random Forest (RF). Out team calculated the precision and recall of the system. The performance of the diagnostic model was evaluated by using the receiver operating characteristic (ROC) curve.ResultsBy designing the features properly, the typical machine learning algorithms SVM, DNN, RF and GBDT all performed well. GBDT had the highest precision (92.9%), recall (90.0%) and F1 score (0.915) for the myeloma group. The maximized area under the ROC (AUROC) was calculated, and the results of GBDT (AUC: 0.975; 95% confidence interval (CI): 0.963–0.986) outperformed that of SVM, DNN and RF.ConclusionThe model established by artificial intelligence derived from routine laboratory results can accurately diagnose MM, which can boost the rate of early diagnosis.

show abstract

Artificial Intelligence–Based Multimodal Risk Assessment Model for Surgical Site Infection (AMRAMS): Development and Validation Study

Cited by 24 publications

References 32 publications

Automatic Prediction of Recurrence of Major Cardiovascular Events: A Text Mining Study Using Chest X-Ray Reports

Automatic Prediction of Recurrence of Major Cardiovascular Events: A Text Mining Study Using Chest X-Ray Reports

Minimally invasive gastrointestinal surgery: From past to the future

Employment of Artificial Intelligence Based on Routine Laboratory Results for the Early Diagnosis of Multiple Myeloma

Contact Info

Product

Resources

About