Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
. 2025 Apr 25;15(1):14468.
doi: 10.1038/s41598-025-94395-2.

Machine learning for predicting medical outcomes associated with acute lithium poisoning

Omid Mehrpour  1 , Varun Vohra  2 , Samaneh Nakhaee  3 , Seyed Ali Mohtarami  4 , Farshad M Shirazi  5
Affiliations

Machine learning for predicting medical outcomes associated with acute lithium poisoning

Omid Mehrpour et al. Sci Rep. .

Abstract

The use of machine learning algorithms and artificial intelligence in medicine has attracted significant interest due to its ability to aid in predicting medical outcomes. This study aimed to evaluate the effectiveness of the random forest algorithm in predicting medical outcomes related to acute lithium toxicity. We analyzed cases recorded in the National Poison Data System (NPDS) between January 1, 2014, and December 31, 2018. We highlighted instances of acute lithium toxicity in patients with ages ranging from 0 to 89 years. A random forest model was employed to predict serious medical outcomes, including those with a major effect, moderate effect, or death. Predictions were made using the pre-defined NPDS coding criteria. The model's predictive performance was assessed by computing accuracy, recall (sensitivity), and F1-score. Of the 11,525 reported cases of lithium poisoning documented during the study, 2,760 cases were categorized as acute lithium overdose. One hundred thirty-nine individuals experienced severe outcomes, whereas 2,621 patients endured minor outcomes. The random forest model exhibited exceptional accuracy and F1-scores, achieving values of 99%, 98%, and 98% for the training, validation, and test datasets, respectively. The model achieved an accuracy rate of 100% and a sensitivity rate of 96% for important results. In addition, it achieved a 96% accuracy rate and a sensitivity rate of 100% for minor outcomes. The SHapley Additive exPlanations (SHAP) study found factors, including drowsiness/lethargy, age, ataxia, abdominal pain, and electrolyte abnormalities, significantly influenced individual predictions. The random forest algorithm achieved a 98% accuracy rate in predicting medical outcomes for patients with acute lithium intoxication. The model demonstrated high sensitivity and precision in accurately predicting significant and minor outcomes. Further investigation is necessary to authenticate these findings.

Keywords: Artificial intelligence; Lithium; Machine learning; Poisoning.

PubMed Disclaimer

Conflict of interest statement

Declarations. Competing interests: The authors declare no competing interests. Ethical approval and consent to participate: Our research methods adhered to all applicable guidelines and regulations. The data used in this study was obtained from the NPDS in a de-identified format. The Colorado Multiple Institutional Review Board on Human Subjects Protection has established guidelines for determining whether a study qualifies as human subjects research. According to these guidelines, our analysis of NPDS data does not meet the criteria outlined in 45 Code of Federal Regulations (CFR) 46.101(b) for human subjects research. Consequently, formal IRB approval was optional for this study. It is important to note that certain research categories, classified as exempt research, are not subject to federal regulations and can proceed without formal IRB review and approval. To qualify for this exemption, research activities must involve minimal risk and meet specific criteria defined in federal regulations 45 CFR 46.101(b). In our case, the Colorado Multiple Institutional Review Board on Human Subjects Protection reviewed our study protocol and determined that it met the criteria for exemption. This decision is documented under COMIRB#22-1088. This exemption status indicates that while our research involves human data, it poses minimal risk and falls within the parameters that allow for streamlined ethical review processes.

Figures

Fig. 1
Fig. 1
Significance of features for each target outcome class as determined by the SHAP algorithm “Serious outcome”: class 0, “Minor effect”: class1.
Fig. 2
Fig. 2
Roc curve (A) and Precision-recall curve (B) for the random forest model.
Fig. 3
Fig. 3
Roc curve and Precision-recall curve for the Extra Tree and Decision Tree Classifier.
See this image and copyright information in PMC

Similar articles

See all similar articles

References

    1. Malhi, G. S. & Outhred, T. Therapeutic mechanisms of lithium in bipolar disorder: recent advances and current Understanding. CNS Drugs30, 931–949 (2016). - PubMed
    1. Timmer, R. T. & Sands, J. M. Lithium intoxication. J. Am. Soc. Nephrol.10, 666–674 (1999). - PubMed
    1. Netto, I. & Phutane, V. H. Reversible lithium neurotoxicity: review of the literature. Prim. Care Companion CNS Disorders14, 27249 (2012). - PMC - PubMed
    1. Schneider, M. A. & Smith, S. S. Lithium-Induced neurotoxicity: a case study. J. Neurosci. Nurs.51, 283–286 (2019). - PubMed
    1. Yatham, L. N. et al. Canadian network for mood and anxiety treatments (CANMAT) and international society for bipolar disorders (ISBD) 2018 guidelines for the management of patients with bipolar disorder. Bipolar Disord.20, 97–170 (2018). - PMC - PubMed

LinkOut - more resources