JoVE - Journal of Visualized Experiments
JoVE Visualize
Contact Us

Artificial neural network to predict post-operative hypocalcemia following total thyroidectomy

  • 0Principal Consultant, Head and Neck Oncology, Sri Shankara Cancer Hospital and Research Center, Bangalore, India.
Indian Journal of Otolaryngology and Head and Neck Surgery : Official Publication of the Association of Otolaryngologists of India +

|

August 12, 2024

|

August 12, 2024

View abstract on PubMed

Summary

This summary is machine-generated.

Artificial neural networks accurately predict post-operative hypocalcemia and its severity after total thyroidectomy. The model highlights intact parathormone levels as the key predictor, emphasizing its clinical utility.

Area Of Science

  • Endocrinology and Surgical Oncology
  • Medical Artificial Intelligence
  • Clinical Decision Support Systems

Background

  • Post-operative hypocalcemia is a common complication following total thyroidectomy.
  • Accurate prediction of hypocalcemia and its severity is crucial for patient management.
  • Current predictive methods may lack precision and comprehensive factor analysis.

Purpose Of The Study

  • To develop and validate an artificial neural network (ANN) model for predicting post-operative hypocalcemia and its severity after total thyroidectomy.
  • To determine the relative importance of various factors in predicting hypocalcemia using ANN.

Main Methods

  • A retrospective case series of 196 patients undergoing total thyroidectomy.
  • Multilayer Perceptron (MLP) artificial neural network (ANN) for prediction and validation.
  • Multivariate analysis to assess predictor weightage and construct validity.

Main Results

  • The ANN model achieved high accuracy, predicting hypocalcemia in 96.3% of test samples and severity in 92.8%.
  • Mean incorrect predictions were low (3.18% training, 3.66% testing).
  • Intact parathormone (iPTH) levels were identified as the most significant predictor (100% weightage), followed by the need for sternotomy (28.55%).

Conclusions

  • ANN models, particularly MLP, demonstrate significant potential for accurately predicting post-operative hypocalcemia and severity after total thyroidectomy.
  • iPTH levels are a critical factor in predicting hypocalcemia post-thyroidectomy.
  • While promising, the ANN model should complement, not replace, clinical expertise.

Keywords:

Related Concept Videos

Skeleton and Calcium Homeostasis 01:21

4.4K

Calcium is not only the most abundant mineral in bone but also the most abundant mineral in the human body. Calcium ions are needed for bone mineralization, tooth health, heart rate regulation and strength of contraction, blood coagulation, the contraction of smooth and skeletal muscle cells, and the regulation of nerve impulse conduction. The average calcium level in the blood is about 10 mg/dL. When the body cannot maintain this level, a person will experience hypo or hypercalcemia.

Hormones and Bone Tissue 01:17

2.6K

The endocrine system produces and secretes hormones, which interact with the skeletal system. These hormones control bone growth, maintain bone once it is formed, and remodel it.
Hormones That Influence Osteoblasts and/or Maintain the Matrix
Several hormones are necessary for controlling bone growth and maintaining the bone matrix. The pituitary gland secretes growth hormone (GH), which, as its name implies, controls bone growth. This happens in several ways: first, it triggers chondrocyte...

Synthesis and Functions of Calcitonin 00:51

1.7K

Calcitonin, a vital polypeptide hormone, regulates calcium levels within body fluids. It is released by the parafollicular cells, also known as C cells, situated in the follicular epithelium of the thyroid gland. Calcitonin responds to fluctuations in blood calcium levels and the influence of gastrointestinal hormones like gastrin and cholecystokinin.
The exact mechanisms by which calcitonin operates in calcium homeostasis remain elusive, but its significance is evident in several vital...