EUVIMEDEUVIMED entdecken
Crossref

Prediction of Medical Students’ Performance in Summative Assessment Using Machine Learning Algorithms

Vorhersage der Leistung von Medizinstudierenden in der summativen Prüfung mit Machine-Learning-Algorithmen

Mallika Sengupta, Kaushik Mukhopadhyay, Sujaya Mazumder, Kalyan Goswami, Biswabina Ray, Rashmi Avinash Patil

Annals of African Medicine · 03.11.2026

DOI: 10.4103/aam.aam_1059_26 ↗

Auf einen Blick

Machine-Learning-Modelle sagten die Leistung von Studierenden im zweiten MBBS-Jahr in summativen Prüfungen über die Fächer Mikrobiologie, Pathologie und Pharmakologie gut voraus.

Fragestellung

Wie gut lassen sich Machine-Learning-Modelle nutzen, um die Leistung von MBBS-Studierenden in summativen Prüfungen vorherzusagen?

Methode

Beobachtende analytische Studie an der All India Institute of Medical Sciences, Kalyani; Daten aus fünf aufeinanderfolgenden MBBS-Kohorten (2019–2023); Training mit Daten aus vier Kohorten, Validierung mit der fünften.

Ergebnisse

Die Modelle zeigten in allen drei Fächern eine starke Vorhersageleistung. Das SVM-Modell hatte die höchste Sensitivität (89 %) für Studierende mit Risiko des Nichtbestehens; die Spezifität lag über die Modelle hinweg bei 100 %.

Schlussfolgerung der Autor:innen

Machine-Learning-basierte Vorhersagemodelle können Studierende mit Risiko für schlechte akademische Leistung effektiv identifizieren.

Kernaussagen

  • SVM zeigte die höchste Sensitivität (89 %)
  • Spezifität über die Modelle hinweg 100 %
  • Random Forest, XGBoost und LightGBM erzielten ebenfalls hohe Genauigkeit und AUC

Deutsche Zusammenfassung: KI-gestützt aus dem Original-Abstract erstellt; alle Zahlen wurden automatisch mit dem Original abgeglichen. Maßgeblich ist der Original-Abstract.

Kurz gefasst

Fachartikel in der Zeitschrift Annals of African Medicine, online erschienen am 03.11.2026. Verfasst von Mallika Sengupta und 5 weiteren Autor:innen. Beteiligte Einrichtung: Department of Microbiology, All India Institute of Medical Sciences, Kalyani, West Bengal, India.

Auf einen BlickAbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Background

Early identification of medical students at risk of poor academic performance is essential for timely academic intervention and student support. This study aimed to develop and evaluate machine learning models to predict the performance of second-year MBBS students in summative assessments.

Methods

This observational analytical study was conducted at All India Institute of Medical Sciences, Kalyani, using academic data from five consecutive MBBS batches (2019–2023). Variables included demographic information, attendance records, internal assessment scores, previous academic performance, and final summative examination results in microbiology, pathology, and pharmacology. Multiple machine learning algorithms including logistic regression, decision tree, random forest, support vector machine (SVM), k-nearest neighbors, Naïve Bayes, XGBoost, and LightGBM were implemented using R statistical software. The models were trained using data from four batches and validated using the fifth batch. Performance was evaluated using accuracy, sensitivity, specificity, positive predictive value, negative predictive value, and area under the receiver operating characteristic curve (AUC).

Results

Machine learning models demonstrated strong predictive performance across all three subjects. Among the algorithms evaluated, the SVM model showed the highest sensitivity (89%) in identifying students at risk of failing in final examinations. Specificity across models reached 100%, indicating that students predicted to pass were accurately classified. Random forest, XGBoost, and LightGBM also demonstrated high predictive accuracy and AUC values.

Conclusion

Machine learning-based predictive models can effectively identify medical students at risk of poor academic performance. Integrating predictive analytics into medical education systems may enable early academic support, reduce student stress, and improve educational outcomes.

Schlagwörter

Stichwörter der Autor:innen

Enseignement médicalMedical educationapprentissage automatiqueeducational data miningfouille de données éducativesmachine learningprédiction des performances des étudiantsstudent performance prediction

Autor:innen und Institutionen

  • Department of Microbiology, All India Institute of Medical Sciences, Kalyani, West Bengal, India.
  • Department of Pharmacology, All India Institute of Medical Sciences, Kalyani, West Bengal, India.
  • Department of Pathology, All India Institute of Medical Sciences, Kalyani, West Bengal, India.
  • Department of Biochemistry, All India Institute of Medical Sciences, Kalyani, West Bengal, India.
  • Department of Anatomy, All India Institute of Medical Sciences, Kalyani, West Bengal, India.
  • Department of Anatomy, Seth GSMC and KEM Hospital, Mumbai, Maharashtra, India.

Zitieren

APA

Sengupta, M., Mukhopadhyay, K., Mazumder, S., Goswami, K., Ray, B., & Patil, R. A. (2026). Prediction of Medical Students’ Performance in Summative Assessment Using Machine Learning Algorithms. Annals of African Medicine. https://doi.org/10.4103/aam.aam_1059_26

Vancouver

Sengupta M, Mukhopadhyay K, Mazumder S, Goswami K, Ray B, Patil RA. Prediction of Medical Students’ Performance in Summative Assessment Using Machine Learning Algorithms. Annals of African Medicine. 2026. doi:10.4103/aam.aam_1059_26

BibTeX
@article{Sengupta2026,
  author = {Sengupta, Mallika and Mukhopadhyay, Kaushik and Mazumder, Sujaya and Goswami, Kalyan and Ray, Biswabina and Patil, Rashmi Avinash},
  title = {Prediction of Medical Students’ Performance in Summative Assessment Using Machine Learning Algorithms},
  journal = {Annals of African Medicine},
  year = {2026},
  doi = {10.4103/aam.aam_1059_26}
}
Kostenlos starten →