Classification of acute poisoning exposures with machine learning models derived from the National Poison Data System

The primary aim of this pilot study was to develop a machine learning algorithm to predict and distinguish eight poisoning agents based on clinical symptoms. Data were used from the National Poison Data System from 2014 to 2018, for patients 0–89 years old with single‐agent exposure to eight drugs or drug classes (acetaminophen, aspirin, benzodiazepines, bupropion, calcium channel blockers, diphenhydramine, lithium and sulfonylureas). Four classifier prediction models were applied to the data: logistic regression, LightGBM, XGBoost, and CatBoost. There were 201 031 cases used to develop and test the algorithms. Among the four models, accuracy ranged 77%–80%, with precision and F1 scores of 76%–80% and recall of 77%–78%. Overall specificity was 92% for all models. Accuracy was highest for identifying sulfonylureas, acetaminophen, benzodiazepines and diphenhydramine poisoning. F1 scores were highest for correctly classifying sulfonylureas, acetaminophen and benzodiazepine poisonings. Recall was highest for sulfonylureas, acetaminophen, and benzodiazepines, and lowest for bupropion. Specificity was >99% for models of sulfonylureas, calcium channel blockers, lithium and aspirin. For single‐agent poisoning cases among the eight possible exposures, machine learning models based on clinical signs and symptoms moderately predicted the causal agent. CatBoost and LightGBM classifier models had the highest performance of those tested.

[1]  Vivekanadam B,et al.  Artificial Intelligence Algorithm with SVM Classification using Dermascopic Images for Melanoma Diagnosis , 2021 .

[2]  Wei-Hsin Huang,et al.  Development of Machine Learning Models for Prediction of Smoking Cessation Outcome , 2021, International journal of environmental research and public health.

[3]  B. Behnoush,et al.  Machine learning algorithms to predict seizure due to acute tramadol poisoning , 2021, Human & experimental toxicology.

[4]  Michael A. Chary,et al.  Diagnosis of Acute Poisoning Using Explainable Artificial Intelligence , 2021, Comput. Biol. Medicine.

[5]  North American Congress of Clinical Toxicology (NACCT) Abstracts 2020 , 2020 .

[6]  Min-Yuan Cheng,et al.  Text mining-based construction site accident classification using hybrid supervised machine learning , 2020 .

[7]  R. Ghani,et al.  Validation of a Machine Learning Model to Predict Childhood Lead Poisoning , 2020, JAMA network open.

[8]  Arnon Nagler,et al.  Machine learning and artificial intelligence in haematology , 2020, British journal of haematology.

[9]  Pooja Anbuselvan,et al.  Heart Disease Prediction using Machine Learning Techniques , 2020, SN Computer Science.

[10]  R. Thanacoody.  Principles of assessment and diagnosis of the poisoned patient , 2020 .

[11]  Viktor E. Krebs,et al.  Machine Learning and Artificial Intelligence: Definitions, Applications, and Future Directions , 2020, Current Reviews in Musculoskeletal Medicine.

[12]  S. Pappu,et al.  Extreme Gradient Boosting for Parkinson’s Disease Diagnosis from Voice Recordings , 2020 .

[13]  Giuseppe Argenziano,et al.  Assessment of Accuracy of an Artificial Intelligence Algorithm to Detect Melanoma in Images of Skin Lesions , 2019, JAMA network open.

[14]  Fredrik Svensson,et al.  LightGBM: An Effective and Scalable Algorithm for Prediction of Chemical Toxicity-Application to the Tox21 and Mutagenicity Data Sets , 2019, J. Chem. Inf. Model..

[15]  Eneida A. Mendonça,et al.  Training and Interpreting Machine Learning Algorithms to Evaluate Fall Risk After Emergency Department Visits , 2019, Medical care.

[16]  I. Moon,et al.  Predicting cochlear dead regions in patients with hearing loss through a machine learning-based approach: A preliminary study , 2019, PloS one.

[17]  Xianqin Wang,et al.  Metabolomics Analysis in Acute Paraquat Poisoning Patients Based on UPLC-Q-TOF-MS and Machine Learning Approach. , 2019, Chemical research in toxicology.

[18]  C. Vogelmeier,et al.  Artificial intelligence outperforms pulmonologists in the interpretation of pulmonary function tests , 2019, European Respiratory Journal.

[19]  Jamile Silveira Tomiazzi,et al.  Performance of machine-learning algorithms to pattern recognition and classification of hearing impairment in Brazilian farmers exposed to pesticide and/or cigarette smoke , 2019, Environmental Science and Pollution Research.

[20]  Shih-Hwa Chiou,et al.  Artificial intelligence-based decision-making for age-related macular degeneration , 2019, Theranostics.

[21]  Barret Rush,et al.  Applying machine learning to continuously monitored physiological data , 2018, Journal of Clinical Monitoring and Computing.

[22]  S. Walsh,et al.  Deep learning for classifying fibrotic lung disease on high-resolution computed tomography: a case-cohort study. , 2018, The Lancet. Respiratory medicine.

[23]  Tadahiro Goto,et al.  Machine learning approaches for predicting disposition of asthma and COPD exacerbations in the ED , 2018, The American journal of emergency medicine.

[24]  Guanyu Wang,et al.  Machine Learning Based Toxicity Prediction: From Chemical Structural Description to Transcriptome Analysis , 2018, International journal of molecular sciences.

[25]  Woo Suk Hong,et al.  Predicting hospital admission at emergency department triage using machine learning , 2018, PloS one.

[26]  C. Lindvall,et al.  Machine Learning to Predict, Detect, and Intervene Older Adults Vulnerable for Adverse Drug Events in the Emergency Department , 2018, Journal of Medical Toxicology.

[27]  Kei-Hoi Cheung,et al.  Predicting urinary tract infections in the emergency department with machine learning , 2018, PloS one.

[28]  Luca Barletta,et al.  QoT estimation for unestablished lighpaths using machine learning , 2017, 2017 Optical Fiber Communications Conference and Exhibition (OFC).

[29]  Yuji Ikegaya,et al.  Machine learning-based prediction of adverse drug effects: An example of seizure-inducing compounds. , 2017, Journal of pharmacological sciences.

[30]  Huiling Chen,et al.  An Effective Machine Learning Approach for Prognosis of Paraquat Poisoning Patients Using Blood Routine Indexes , 2017, Basic & clinical pharmacology & toxicology.

[31]  Z. Obermeyer,et al.  Predicting the Future - Big Data, Machine Learning, and Clinical Medicine. , 2016, The New England journal of medicine.

[32]  K. Borgwardt,et al.  Machine Learning in Medicine , 2015, Mach. Learn. under Resour. Constraints Vol. 3.

[33]  Dimitrios I. Fotiadis,et al.  Machine learning applications in cancer prognosis and prediction , 2014, Computational and structural biotechnology journal.

[34]  Max Kuhn,et al.  Applied Predictive Modeling , 2013 .

[35]  Trevonne M. Thompson,et al.  The approach to the patient with an unknown overdose. , 2007, Emergency medicine clinics of North America.

[36]  Robert S Hoffman,et al.  Understanding the limitations of retrospective analyses of poison center data , 2007, Clinical toxicology.

[37]  Lucila Ohno-Machado,et al.  Logistic regression and artificial neural network classification models: a methodology review , 2002, J. Biomed. Informatics.

[38]  Yu Wang,et al.  Machine Learning Based Opioid Overdose Prediction Using Electronic Health Records , 2019, AMIA.

[39]  Lionel C. Briand,et al.  A systematic and comprehensive investigation of methods to build and evaluate fault prediction models , 2010, J. Syst. Softw..