Skip to main content

Advertisement

SpringerLink
Log in

Utility of artificial intelligence to identify antihyperglycemic agents poisoning in the USA: introducing a practical web application using National Poison Data System (NPDS)

  • Research Article
  • Published:
Environmental Science and Pollution Research Aims and scope Submit manuscript

Abstract

Clinical effects of antihyperglycemic agents poisoning may overlap each other. So, distinguishing exposure to these pharmaceutical drugs may take work. This study examined the application of machine learning techniques in identifying antihyperglycemic agent exposure using the national poisoning database in the USA. In this study, the data of single exposure due to Biguanides and Sulfonylureas (n=6183) was requested from the National Poison Data System (NPDS) for 2014–2018. We have tried five machine learning models (random forest classifier, k-nearest neighbors, Xgboost classifier, logistic regression, neural network Keras). For the multiclass classification modeling, we have divided the dataset into two parts: train (75%) and test (25%). The performance metrics used were accuracy, specificity, precision, recall, and F1-score. The algorithms used to get the classification results of different models to diagnose antihyperglycemic agents were very accurate. The accuracy of our model in determining these two antihyperglycemic agents was 91–93%. The precision-recall curve showed average precision of 0.91, 0.97, 0.97, and 0.98 for k-nearest neighbors, logistic regression, random forest, and XGB, respectively. The logistic regression, random forest, and XGB had the highest AUC (AUC=0.97) among both biguanides and sulfonylureas groups. The negative predictive values (NPV) for all the models were between 89 and 93%. We introduced a practical web application to help physicians distinguish between these agents. Despite variations in accuracy among the different types of algorithms used, all of them could accurately determine the specific exposure to biguanides and sulfonylureas retrospectively. Machine learning can distinguish antihyperglycemic agents, which may be useful for physicians without any background in medical toxicology. Besides, Our suggested ML-based Web application might help physicians in their diagnosis.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2

Similar content being viewed by others

Data availability

The datasets analyzed during this study are available from the corresponding author upon any reasonable request with permission of the National Poison Data System (NPDS) administrator.

Abbreviations

NPDS:

National Poison Data System

NPV:

Negative predictive value

ML:

Machine learning

AI:

Artificial intelligence

KNN:

k-nearest neighbors

COMIRB:

Colorado Multiple Institutional Review Board

AUC:

Area under ROC curve

PCA:

Principal component analysis

BNB:

Bayesian Naïve Bayes

DT:

Decision trees

SVM:

Support vector machines

RF:

Random forests of trees

XGB:

Gradient-boosted decision trees

SSRIs:

Selective serotonin reuptake inhibitors

SPIs:

Specialists in poisoning information

AAPC:

American Association of Poison Control Center

PCCs:

Poison control centers

References

  • Ambade B, Sankar TK, Kumar A, Sethi SS (2020) Characterization of PAHs and n-alkanes in atmospheric aerosol of Jamshedpur City, India. J Hazard Toxic Radioact Waste 24:04020003

  • Ambade B, Sethi SS (2021) Health risk assessment and characterization of polycyclic aromatic hydrocarbon from the hydrosphere. J Hazard Toxic Radioact Waste 25:05020008

  • Bailey CJ, Turner RC (1996) Metformin. N Engl J Med 334:574–579

  • Balasubramaniam V (2021) Artificial intelligence algorithm with SVM classification using dermascopic images for melanoma diagnosis. J Artif Intelligence Capsule Networks 3:34–42

  • Behnoush B, Bazmi E, Nazari S, Khodakarim S, Looha M, Soori H (2021) Machine learning algorithms to predict seizure due to acute tramadol poisoning. Hum Exp Toxicol 40:1225–1233

  • Chang Y-S, Park H, Hong SH, Chung W-H, Cho Y-S, Moon IJ (2019) Predicting cochlear dead regions in patients with hearing loss through a machine learning-based approach: A preliminary study. PloS One 14:e0217790

  • Chary M, Burnsa M, Boyerb E (2019) Tak: the computational toxicological machine. 39th International Congress of the European Association of Poisons Centres and Clinical Toxicologists (EAPCCT) 21-24 May 2019, Naples, Italy. Clin Toxicol 57:482

  • Chary M, Boyer EW, Burns MM (2021) Diagnosis of acute poisoning using explainable artificial intelligence. Comput Biol Med 134:104469

  • Chary MA, Manini AF, Boyer EW, Burns M (2020) The role and promise of artificial intelligence in medical toxicology. J Med Toxicol 16(4):458–464

  • Chen H, Hu L, Li H, Hong G, Zhang T, Ma J, Lu Z (2017) An effective machine learning approach for prognosis of paraquat poisoning patients using blood routine indexes. Basic Clin Pharmacol Toxicol 120:86–96

  • Deo RC (2015) Machine learning in medicine. Circulation 132:1920–1930

  • Dong X, Rashidian S, Wang Y, Hajagos J, Zhao X, Rosenthal RN, Kong J, Saltz M, Saltz J, Wang F (2019) Machine learning based opioid overdose prediction using electronic health records. AMIA Annu Symp Proc 2019:389–398

  • Glatstein M, Scolnik D, Bentur Y (2012) Octreotide for the treatment of sulfonylurea poisoning. Clin Toxicol 50:795–804

  • Goto T, Camargo CA Jr, Faridi MK, Yun BJ, Hasegawa K (2018) Machine learning approaches for predicting disposition of asthma and COPD exacerbations in the ED. Am J Emerg Med 36:1650–1654

  • Gute B, Basak S (1997) Predicting acute toxicity (LC50) of benzene derivatives using theoretical molecular descriptors: a hierarchical QSAR approach. SAR QSAR Environ Res 7:117–131

  • Hancock JT, Khoshgoftaar TM (2020) CatBoost for big data: an interdisciplinary review. J Big Data 7:1–45

  • Harrigan RA, Nathan MS, Beattie P (2001) Oral agents for the treatment of type 2 diabetes mellitus: pharmacology, toxicity, and treatment. Ann Emerg Med 38:68–78

  • Helm JM, Swiergosz AM, Haeberle HS, Karnuta JM, Schaffer JL, Krebs VE, Spitzer AI, Ramkumar PN (2020) Machine learning and artificial intelligence: definitions, applications, and future directions. Curr Rev Musculoskelet Med 13:69–76

  • Hong WS, Haimovich AD, Taylor RA (2018) Predicting hospital admission at emergency department triage using machine learning. PloS One 13:e0201016

  • Hwang D-K, Hsu C-C, Chang K-J, Chao D, Sun C-H, Jheng Y-C, Yarmishyn AA, Wu J-C, Tsai C-Y, Wang M-L (2019) Artificial intelligence-based decision-making for age-related macular degeneration. Theranostics 9:232

  • Kourou K, Exarchos TP, Exarchos KP, Karamouzis MV, Fotiadis DI (2015) Machine learning applications in cancer prognosis and prediction. Comput Struct Biotechnol J 13:8–17

  • Krittanawong C, Virk HUH, Kumar A, Aydar M, Wang Z, Stewart MP, Halperin JL (2021) Machine learning and deep learning to predict mortality in patients with spontaneous coronary artery dissection. Sci Rep 11:1–10

  • Kurwadkar S, Sethi SS, Mishra P, Ambade B (2022) Unregulated discharge of wastewater in the Mahanadi River Basin: risk evaluation due to occurrence of polycyclic aromatic hydrocarbon in surface water and sediments. Mar Pollut Bull 179:113686

  • Lai C-C, Huang W-H, Chang BC-C, Hwang L-C (2021) Development of machine learning models for prediction of smoking cessation outcome. Int J Environ Res Public Health 18:2584

  • Martin TM, Lilavois CR, Barron MG (2017) Prediction of pesticide acute toxicity using two-dimensional chemical descriptors and target species classification. SAR QSAR Environ Res 28:525–539

  • Mayr A, Klambauer G, Unterthiner T, Hochreiter S (2016) DeepTox: toxicity prediction using deep learning. Front Environ Sci 3:80

  • Mehrpour O, Hoyte C, Delva-Clark H, Al Masud A, Biswas A, Schimmel J, Nakhaee S, Goss F (2022a) Classification of acute poisoning exposures with machine learning models derived from the National Poison Data System. Basic Clin Pharmacol Toxicol 131:566–574

  • Mehrpour O, Saeedi F, Hoyte C, Hadianfar A, Nakhaee S, Brent J (2022b) Distinguishing characteristics of exposure to biguanide and sulfonylurea antidiabetic medications in the United States. Am J Emerg Med 56:171–177

  • Metsker OG, Yakovlev AN, Ilin A, Kovalchuk SV (2019) Echocardiography population study in Russian Federation for 4P medicine using machine learning. Stud Health Technol Inform 261:137–142

  • Nogee D, Tomassoni A (2018) Development of a prototype software tool to assist with toxidrome recognition. North American Congress of Clinical Toxicology (NACCT) Abstracts 2018. Clin Toxicol 56:1049–1049

  • Nogee D, Haimovich A, Hart K, Tomassoni A (2020) Multiclass classification machine learning identification of common poisonings. North American Congress of Clinical Toxicology (NACCT) Abstracts 2020. Clin Toxicol 58:1083–1084

  • Ouchi K, Lindvall C, Chai PR, Boyer EW (2018) Machine learning to predict, detect, and intervene older adults vulnerable for adverse drug events in the emergency department. J Med Toxicol 14:248–252

  • Patterson BW, Engstrom CJ, Sah V, Smith MA, Mendonça EA, Pulia MS, Repplinger MD, Hamedani A, Page D, Shah MN (2019) Training and interpreting machine learning algorithms to evaluate fall risk after emergency department visits. Med Care 57:560

  • Phillips M, Marsden H, Jaffe W, Matin RN, Wali GN, Greenhalgh J, McGrath E, James R, Ladoyanni E, Bewley A (2019) Assessment of accuracy of an artificial intelligence algorithm to detect melanoma in images of skin lesions. JAMA Netw Open 2:e1913436

  • Potash E, Ghani R, Walsh J, Jorgensen E, Lohff C, Prachand N, Mansour R (2020) Validation of a machine learning model to predict childhood lead poisoning. JAMA Netw Open 3:e2012734

  • Qiao Z, Sun N, Li X, Xia E, Zhao S, Qin Y (2018) Using machine learning approaches for emergency room visit prediction based on electronic health record data. Stud Health Technol Inform 247:111–115

  • Rajkomar A, Dean J, Kohane I (2019) Machine learning in medicine. N Engl J Med 380:1347–1358

  • Rehman M, Shah RA, Khan MB, Shah SA, AbuAli NA, Yang X, Alomainy A, Imran MA, Abbasi QH (2021) Improving machine learning classification accuracy for breathing abnormalities by enhancing dataset. Sensors 21:6750

  • Rush B, Celi LA, Stone DJ (2019) Applying machine learning to continuously monitored physiological data. J Clin Monit Comput 33:887–893

  • Sidey-Gibbons JA, Sidey-Gibbons CJ (2019) Machine learning in medicine: a practical introduction. BMC Med Res Methodol 19:1–18

  • Spiller HA, Sawyer TS (2006) Toxicology of oral antidiabetic medications. Am J Health Syst Pharm 63:929–938

  • Taylor RA, Moore CL, Cheung K-H, Brandt C (2018) Predicting urinary tract infections in the emergency department with machine learning. PloS One 13:e0194085

  • Thieme A, Belgrave D, Doherty G (2020) Machine learning in mental health: a systematic review of the HCI literature to support the development of effective and implementable ML systems. ACM Transactions on Computer-Human Interaction (TOCHI) 27:1–53

  • Tomiazzi JS, Pereira DR, Judai MA, Antunes PA, Favareto APA (2019) Performance of machine-learning algorithms to pattern recognition and classification of hearing impairment in Brazilian farmers exposed to pesticide and/or cigarette smoke. Environ Sci Pollut Res 26:6481–6491

  • Topalovic M, Das N, Burgel P-R, Daenen M, Derom E, Haenebalcke C, Janssen R, Kerstjens HA, Liistro G, Louis R (2019) Artificial intelligence outperforms pulmonologists in the interpretation of pulmonary function tests. Eur Respir J 53(4)

  • Uspenskaya-Cadoz O, Alamuri C, Wang L, Yang M, Khinda S, Nigmatullina Y, Cao T, Kayal N, O’Keefe M, Rubel C (2019) Machine learning algorithm helps identify non-diagnosed prodromal Alzheimer’s disease patients in the general population. J Prev Alzheimers Dis 6:185–191

  • Walia H, Jeevaraj S (2021) Early mortality risk prediction in Covid-19 patients using an ensemble of machine learning models. In: 2021 International Conference on Computational Performance Evaluation (ComPE). IEEE, pp 965–970. https://doi.org/10.1109/ComPE53109.2021.9751945

  • Walsh SL, Calandriello L, Silva M, Sverzellati N (2018) Deep learning for classifying fibrotic lung disease on high-resolution computed tomography: a case-cohort study. Lancet Respir Med 6:837–845

  • Watson WA, Litovitz TL, Rodgers GC, Klein-Schwartz W, Reid N, Youniss J, Flanagan A, Wruk KM (2005) 2004 Annual report of the American Association of Poison Control Centers Toxic Exposure Surveillance System. Am J Emerg Med 23:589–666

  • Wen C, Lin F, Huang B, Zhang Z, Wang X, Ma J, Lin G, Chen H, Hu L (2019) Metabolomics analysis in acute paraquat poisoning patients based on UPLC-Q-TOF-MS and machine learning approach. Chem Res Toxicol 32:629–637

  • Wu Y, Wang G (2018) Machine learning based toxicity prediction: from chemical structural description to transcriptome analysis. Int J Mol Sci 19:2358

  • Xu T, Yu Y, Yan J, Xu H (2020) Long-term rainfall forecast model based on the TabNet and LightGbm algorithm. Research Square. https://doi.org/10.21203/rs.3.rs-107107/v1

  • Xu Y, Pei J, Lai L (2017) Deep learning based regression and multiclass models for acute oral toxicity prediction with automatic chemical feature extraction. J Chem Inf Model 57:2672–2685

  • Yilmaz A, Demircali AA, Kocaman S, Uvet H (2020): Comparison of deep learning and traditional machine learning techniques for classification of pap smear images arXiv preprint arXiv:2009.06366. https://doi.org/10.48550/arXiv.2009.06366

Download references

Author information

Authors and Affiliations

  1. AI and Health LLC, Tucson, AZ, USA

    Omid Mehrpour

  2. Rocky Mountain Poison & Drug Safety, Denver Health, and Hospital Authority, Denver, CO, USA

    Omid Mehrpour

  3. Medical Toxicology and Drug Abuse Research Center (MTDRC), Birjand University of Medical Sciences (BUMS), Birjand, Iran

    Samaneh Nakhaee, Farhad Saeedi, Bahare Valizade & Erfan Lotfi

  4. Student Research Committee, Birjand University of Medical Sciences, Birjand, Iran

    Farhad Saeedi

  5. University of Engineering and Technology, Mardan, Pakistan

    Malik Hamza Nawaz

Authors
  1. Omid Mehrpour
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Samaneh Nakhaee
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Farhad Saeedi
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Bahare Valizade
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. Erfan Lotfi
    View author publications

    You can also search for this author in PubMed Google Scholar

  6. Malik Hamza Nawaz
    View author publications

    You can also search for this author in PubMed Google Scholar

Contributions

OM designed the study. OM, SN, FS, BV, EL, and MHN contributed to writing the draft and revising the manuscript. All authors approved the final version of the manuscript.

Corresponding author

Correspondence to Omid Mehrpour.

Ethics declarations

Ethics approval

This study was formally exempted by the Colorado Multiple Institutional Review Board (COMIRB#: 22-1088).

Consent to participate

Not applicable.

Consent for publication

Not applicable.

Conflict of interest

The authors declare no competing interests.

Disclaimer

The American Association of Poison Control Center (AAPC) manages the National Poison Data system (NPDS), which contains de-identified case records of all self-reported information collected from callers during calls for exposure management and poison information managed by the nation’s poison control centers (PCCs).

As additional exposures may be underreported to PCCs, NPDS data do not represent the whole universe of exposures to a substance; hence, NPDS data do not necessarily indicate poisoning or overdose, and AAPCC cannot validate the accuracy of each report. Consequently, the results drawn from NPDS data do not necessarily represent the AAPCC’s position.

Additional information

Responsible Editor: Lotfi Aleya

Publisher’s note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Rights and permissions

Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Mehrpour, O., Nakhaee, S., Saeedi, F. et al. Utility of artificial intelligence to identify antihyperglycemic agents poisoning in the USA: introducing a practical web application using National Poison Data System (NPDS). Environ Sci Pollut Res 30, 57801–57810 (2023). https://doi.org/10.1007/s11356-023-26605-1

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s11356-023-26605-1

Keywords

Search

Navigation