Risk of mortality and cardiopulmonary arrest in critical patients presenting to the emergency department using machine learning and natural language processing

Fernandes, Marta; Mendes, R. Vilela; Vieira, Susana M.; Leite, Francisca Pais; Palos, Carlos; Johnson, Alistair E. W.; Finkelstein, Stan N.; Horng, Steven; Celi, Leo Anthony

doi:10.1371/journal.pone.0230876

Cited by 31 publications

(57 citation statements)

References 64 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…More recently, Fernandes et al . applied machine learning and NLP techniques to triage data and classified patients with high mortality and cardiopulmonary arrest 16 . Bacchi et al .…”

Section: Introductionmentioning

confidence: 99%

Advanced natural language processing technique to predict patient disposition based on emergency triage notes

Tahayori

Chini-Foroush

Akhlaghi

2020

Emerg Medicine Australasia

View full text Add to dashboard Cite

Objective To demonstrate the potential of machine learning and capability of natural language processing (NLP) to predict disposition of patients based on triage notes in the ED. Methods A retrospective cohort of ED triage notes from St Vincent's Hospital (Melbourne) was used to develop a deep‐learning algorithm that predicts patient disposition. Bidirectional Encoder Representations from Transformers, a recent language representation model developed by Google, was utilised for NLP. Eighty percent of the dataset was used for training the model and 20% was used to test the algorithm performance. Ktrain library, a wrapper for TensorFlow Keras, was employed to develop the model. Results The accuracy of the algorithm was 83% and the area under the curve was 0.88. Sensitivity, specificity, precision and F1‐score of the algorithm were 72%, 86%, 56% and 63%, respectively. Conclusion Machine learning and NLP can be together applied to the ED triage note to predict patient disposition with a high level of accuracy. The algorithm can potentially assist ED clinicians in early identification of patients requiring admission by mitigating the cognitive load, thus optimises resource allocation in EDs.

show abstract

“…More recently, Fernandes et al . applied machine learning and NLP techniques to triage data and classified patients with high mortality and cardiopulmonary arrest 16 . Bacchi et al .…”

Section: Introductionmentioning

confidence: 99%

Advanced natural language processing technique to predict patient disposition based on emergency triage notes

Tahayori

Chini-Foroush

Akhlaghi

2020

Emerg Medicine Australasia

View full text Add to dashboard Cite

show abstract

“…Therefore, most EDs have a triage to manage growing patient volumes [2,4,5]. ED triage is the first risk assessment for prioritizing patients at high risk and determining the course of ED care for patients [5][6][7][8]. It is vital to accurately identify patients who need immediate care at triage and provide rapid care to patients in ED since delay in care may result in increased morbidity and mortality for many clinical conditions [2,4,5,7,9,10].…”

Section: Introductionmentioning

confidence: 99%

“…Five-level triage systems, including the Canadian Triage and Acuity Scale (CTAS), Manchester Triage System (MTS), and emergency severity index (ESI), are widely used [2,8,9]. The Korean Triage and Acuity Scale (KTAS) was developed in 2012 based on CTAS and has been used nationally as the ED triage tool in Korea since 2016 [11][12][13].…”

Section: Introductionmentioning

confidence: 99%

Prediction of Critical Care Outcome for Adult Patients Presenting to Emergency Department Using Initial Triage Information: An XGBoost Algorithm Analysis

Yun¹,

Choi²,

Park³

2021

JMIR Med Inform

View full text Add to dashboard Cite

Background The emergency department (ED) triage system to classify and prioritize patients from high risk to less urgent continues to be a challenge. Objective This study, comprising 80,433 patients, aims to develop a machine learning algorithm prediction model of critical care outcomes for adult patients using information collected during ED triage and compare the performance with that of the baseline model using the Korean Triage and Acuity Scale (KTAS). Methods To predict the need for critical care, we used 13 predictors from triage information: age, gender, mode of ED arrival, the time interval between onset and ED arrival, reason of ED visit, chief complaints, systolic blood pressure, diastolic blood pressure, pulse rate, respiratory rate, body temperature, oxygen saturation, and level of consciousness. The baseline model with KTAS was developed using logistic regression, and the machine learning model with 13 variables was generated using extreme gradient boosting (XGB) and deep neural network (DNN) algorithms. The discrimination was measured by the area under the receiver operating characteristic (AUROC) curve. The ability of calibration with Hosmer–Lemeshow test and reclassification with net reclassification index were evaluated. The calibration plot and partial dependence plot were used in the analysis. Results The AUROC of the model with the full set of variables (0.833-0.861) was better than that of the baseline model (0.796). The XGB model of AUROC 0.861 (95% CI 0.848-0.874) showed a higher discriminative performance than the DNN model of 0.833 (95% CI 0.819-0.848). The XGB and DNN models proved better reclassification than the baseline model with a positive net reclassification index. The XGB models were well-calibrated (Hosmer-Lemeshow test; P>.05); however, the DNN showed poor calibration power (Hosmer-Lemeshow test; P<.001). We further interpreted the nonlinear association between variables and critical care prediction. Conclusions Our study demonstrated that the performance of the XGB model using initial information at ED triage for predicting patients in need of critical care outperformed the conventional model with KTAS.

show abstract

“…Due to its excellent performance in classification and regression, the ELM has attracted the attention of scholars from multiple directions. [14][15][16][17][18] Compared with BP neural network, the ELM does not need to adjust the weights between layers of neurons in the training process to obtain the unique optimal solution, thus greatly saving the operation time of the algorithm. This helps find out the potential customers quickly and take relevant measures to retain them in case of customer churn.…”

Section: Introductionmentioning

confidence: 99%

“…In contrast, the extreme learning machine (ELM) has the advantage of economy and speed in forecasting classification. Due to its excellent performance in classification and regression, the ELM has attracted the attention of scholars from multiple directions 14–18 . Compared with BP neural network, the ELM does not need to adjust the weights between layers of neurons in the training process to obtain the unique optimal solution, thus greatly saving the operation time of the algorithm.…”

Section: Introductionmentioning

confidence: 99%

An early warning model for customer churn prediction in telecommunication sector based on improved bat algorithm to optimize ELM

Chun

Liu

et al. 2021

Int J Intell Syst

View full text Add to dashboard Cite

The competition in the telecommunications industry is mainly reflected in the competition for the number of key customers. Therefore, how to effectively prevent the loss of large customers is a problem that many telecommunications companies are very concerned about. This paper establishes a customer churn prediction model based on the improved bat algorithm (IBA) optimized extreme learning machine (ELM), with the purpose of discovering potential churn customers in time and taking measures to retain them in advance. This paper uses the IBA to optimize the initial random weights of the ELM, so as to improve the prediction accuracy of the ELM. To overcome the shortcomings of the bat algorithm (BA) that the convergence speed is too slow in the early stage and difficult to converge in the later stage, this paper introduces the inertia weight into the speed update formula. To improve the population diversity and local search ability of the BA, this paper adds a chaotic local search method to balance the global search ability of the BA in the early stage. To control the search range of the BAs in the later stage, the lane flight formula is introduced into the position update formula to speed up the convergence speed of the algorithm. Then according to the result of function optimization, it can be seen that IBA has a significant improvement in convergence speed and accuracy. Finally, IBA was used to optimize ELM, and a customer churn prediction model was established. The empirical results show that the predictive model proposed in this paper can effectively identify lost customers and lay a foundation for improving the competitiveness of the telecommunications industry in the future.

show abstract

Risk of mortality and cardiopulmonary arrest in critical patients presenting to the emergency department using machine learning and natural language processing

Cited by 31 publications

References 64 publications

Advanced natural language processing technique to predict patient disposition based on emergency triage notes

Advanced natural language processing technique to predict patient disposition based on emergency triage notes

Prediction of Critical Care Outcome for Adult Patients Presenting to Emergency Department Using Initial Triage Information: An XGBoost Algorithm Analysis

An early warning model for customer churn prediction in telecommunication sector based on improved bat algorithm to optimize ELM

Contact Info

Product

Resources

About