Predictive Machine learning Models for necessity Supplemental Anesthesia in Endodontic treatment

Main Article Content

Dr. Md. Abu Saeed Ibn Harun Mohammad Arif Mazumder Dr. Abu Hena Mohammod Zakir Hossain Shikder Dr. Nazneen Karim Dr. Md. Shahedur Rahman Hera


Purpose: In cases of irreversible pulpitis, controlling intraoperative endodontic discomfort is extremely difficult, and patient satisfaction plays a big part in this. In order to forecast a diagnostic's and a treatment's outcome, machine learning (ML) has recently been implemented in the fields of medicine and dentistry. The goal of this work was to create machine learning (ML) models that could predict the need for further anesthesia.

Methods: According to inclusion and exclusion criteria, this study included 128 individuals with endodontic discomfort. All patients underwent a clinical evaluation and endodontic diagnostic procedures. All interpretation results were entered into a prepared data sheet. All info were statistically evaluated using Github software version ydata-profilling vv4.1.2, configuration config.json, was employed to review the explanatory data for machine learning models for all examination and investigation aspects. By using Pearson correlation, chi 2, Random Forest, and LightGBM, the final feature importance was determined. 20% of the test set and 80% of the train set are observation sets used to build models. Logistic regression F1 and k-nearest neighbors (KNN) F1 were used to assess the performance of the ML model on the train and test sets.

Results: For Machine learning models, 11 of the 20 features—such as pulp stone or calcification of the pulp space, pain duration, age, percussion, palpation, response persistent after EPT, dental history, curved root canal, pain persistent after a cold test, and pain severity during a cold test—were important. In logistic regression, F1 for the train set was 0.793, while for the test sets, it was 0.878. Regression using a logistic model had an accuracy of 0.81. KNN F1 for train was 0.781, while for test it was 0.829. The Machine learning model's k-nearest neighbors (KNN) F1 accuracy was 72.86.

Conclusion: The trained machine learning models can predict if further anesthetic will be required during endodontic treatment based on the specific feature.

Keywords: Machine learning, Supplementary Anesthesia, Logistic regression, KNN algorithm, Clinical examination, feature importance.

Article Details

How to Cite
HARUN, Dr. Md. Abu Saeed Ibn et al. Predictive Machine learning Models for necessity Supplemental Anesthesia in Endodontic treatment. Medical Research Archives, [S.l.], v. 12, n. 4, apr. 2024. ISSN 2375-1924. Available at: <>. Date accessed: 27 may 2024. doi:
Research Articles


1. Riyadh A, Dana K, Robert H, Joshua C, Paul A. Rosenberg and Mathew M. Factors Influencing Pain and Anxiety Before Endodontic Treatment: A Cross-Sectioned Study Amongst American Individuals. Eur Endod J. 2020;5(3):199-204.

2. Noelia Santos-Puerta and Cecilia Peñacoba-Puente. Pain and Avoidance during and after Endodontic Therapy: The Role of Pain Anticipation and Self-efficacy. Int J Environ Res Public Health. 2022; 19:1399.

3. Nessrin AT, Alaa M. Abuzaid , Yousef SK. A randomized Controlled Clinical Trial of Pulpotomy versus Root canal Therapy in Mature teeth with Irreversible pulpitis: Outcome, Quality of Life and Patients Satisfaction. J Endod. 2023; 49(6): 624-631.

4. Sara F, Melissa D, Al Reader, Mike B. Anesthetic Success of an inferior alveolar Nerve and Supplemental articaine Buccal Infiltration for molars and Premolars in patients with Symptomatic Irreversible Pulpitis. J Endod. 2016;42(3): 390-392. DOI:

5. Modaresi J, Dianat O, Soluti A. Effect of pulpal inflammation on nerve impulse quality with or without anesthesia. J Endod. 2008; 34: 438-41.

6. Jaclyn GP, Shane N. White. Pain prevalence and severity before, during and after root canal treatment: Systemic review. J Endod. 2011; 37(4): 429-438.

7. Masoud P, Sina K, Nouzar N, Hamed M, Paul VA. The effect of the anatomical variables on the success rate of anesthesia in maxillary molars with irreversible pulpitis. J Endod. 2022; 48(6): 707-713.

8. Eugene Chen and Paul VA. Dental Pulp Testing: A review. International Journal of Dentistry. 2009;12: 1-12.
DOI: 10.1155/2009/365785

9. Kayaoglu G, Ekici M, Altunkaynak B. Mechanical allodynia in healthy teeth adjacent and contralateral to endodontically diseased teeth: a clinical study. J Endod. 2020; 46:611-618.

10. Nargis Sonde, Malcolm E. Perio-endo lesions: a guide to diagnosis and clinical management. Prim Dent J. 2020; 9(4): 45-51.

11. Domenico Ricucci, José FS, Isabela NR. Pulp Response to Periodontal Disease: Novel observations help clarify the process of tissue breakdown and infection. J Endod. 2021; 47(5): 740-754.

12. Hassam WA, Mohammed A, Moamen MA, Mohamed IG, Mohamed Abd Elfatah Abd Allah, Nabeel A. The association of dental pulp stones to cardiovascular and renal diseases: a systemic review and meta-analysis. J Endod. 2022; 48(7): 845-854.

13. Yandy GM, Yoshifumi K, Mohammad SI et al. Altered Prevalence of pulp diagnosis in diabetes mellitus patients: A retrospective study. J Endod. 2022; 48(2): 208-212.

14. Covino BG, Vassallo HG. Local Anesthetic: Mechanisms of action and clinical use. New York: Grune & Stratton;1976.

15. Kaufman E, Weinstein P, Milgrom P. Difficulties in achieving anesthesia. J Am Dent Assoc. 1984; 108: 205-207.

16. Malamed S F. Local anesthetics: dentistry’s most important drugs. J Am Dent Assoc. 1994; 125: 1571.

17. Mohamed ES, Kamis G. Postanesthetic Cold Sensibility test as an indicator for the Efficacy of Inferior Alveolar Nerve Block in Patients with symptomatic Irreversible Pulpitis of mandibular molars. International Journal of Dentistry. 2021: 1-11.

18. Muhammad L J, Ebrahem A Algehyne, Sani Sharif Usman, Abdulkadir Ahmed et al. Supervised Machine Learning Models for prediction of COVID-19 infection using epidemiology dataset. SN Computer Science. 2021; 2:11.

19. Muhammad L J, Ebrahem A Algehyne and Sani Sharif Usman. Predictive Supervised Machine Learning models for Diabetes Mellitus. SN Computer Science. 2020; 1:240.

20. Ongsulee P. Artificial intelligence, machine learning and deep learning. 15th international conference on ICT and Knowledge engineering (ICT & KE) 2017. Paper presentation.

21. Khalid S, Sreelekshmi VB, Hashem FAM et al. Artificial Intelligence and learning algorithms: Artificial Intelligence in Dentistry. Springer Nature Switzerland AG 2023.

22. Amiya RR. Advantages and Disadvantage of logistic regression. Accessed December 2023. https://www.geeksforgee

23. Joose K. The k-Nearest Neighbors (KNN) algorithm in Python. Accessed December 2023.

24. Mousavi E, and Heshmati M. Relationship between dental pulp stone with the success of local anesthesia for maxillary molars with irreversible pulpitis. International Journal of advanced Biotechnology and research. 2018; 9(1): 127-132.

25. Ahmed A. Alelyani, Pardis S. Azar, Vanessa C, Anibal D. Quantitative Assessment of Mechanical allodynia and Central Sensitization in Endodontic Patients. J Endod. 2020; 46(12): 1841-1848.

26. Shabin S, Aditya S, Ganesh B, Mithra NH. Management of Local Anesthesia failures in endodontics with different anesthetic techniques and agents. Annual resrarch and review in Biology. 2014; 4(7): 1080-1091.

27. Newton CW, Hoen MM, Goodis HE et al. Identify and determine the metrics, hierarchy and predictive value of all the parameters and/or methods used during endodontic diagnosis. J Endod. 2009;35: 1635-1644.

28. Srivastava KC, Shrivastava D, S Nagarajappa AK, et al. Assessing the prevalence and association of pulp stones with cardiaovascular diseases and diabetes mellitus in Saudi Arabian population -a CBCT based study. Int J Environ Res Public health. 2020; 17:9293.