Evaluation of multiple machine learning models predicting the results of hybrid imaging in primary hyperparathyroidism

BACKGROUND: Primary hyperparathyroidism (PHP) diagnosis is based on abnormalities in biochemical blood tests. Preoperative localization of the affected gland with imaging may increase the effectiveness of the surgical treatment. The aim of this study is to evaluate predictive strategies for the asse...

Full description

Saved in:
Bibliographic Details
Main Authors: Anna Drynda, Jacek Podlewski, Karolina Kucharczyk, Grzegorz Sokołowski, Anna Sowa-Staszczak, Alicja Hubalewska-Dydejczyk, Małgorzata Trofimiuk- Müldner
Format: Article
Language:English
Published: Via Medica 2025-08-01
Series:Nuclear Medicine Review
Subjects:
Online Access:https://journals.viamedica.pl/nuclear_medicine_review/article/view/105377
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849230269565894656
author Anna Drynda
Jacek Podlewski
Karolina Kucharczyk
Grzegorz Sokołowski
Anna Sowa-Staszczak
Alicja Hubalewska-Dydejczyk
Małgorzata Trofimiuk- Müldner
author_facet Anna Drynda
Jacek Podlewski
Karolina Kucharczyk
Grzegorz Sokołowski
Anna Sowa-Staszczak
Alicja Hubalewska-Dydejczyk
Małgorzata Trofimiuk- Müldner
author_sort Anna Drynda
collection DOAJ
description BACKGROUND: Primary hyperparathyroidism (PHP) diagnosis is based on abnormalities in biochemical blood tests. Preoperative localization of the affected gland with imaging may increase the effectiveness of the surgical treatment. The aim of this study is to evaluate predictive strategies for the assessment of radiotracer uptake in pre-operative [99mTc]Tc-sestamibi scintigraphy ([99mTc] Tc-MIBI SPECT-CT) among PHP patients to identify individuals with a high probability of negative results, and to develop clinical decision-making tools. MATERIAL AND METHODS: Development and evaluation of logistic regression (LR), classification trees utilizing the classification and regression trees (CART) algorithm, random forest (RF), and boosted trees employing XGBoost (XGB) predictive models. All models were constructed using data obtained from 499 patients diagnosed with PHP who underwent [99mTc]Tc-MIBI SPECT-CT imaging between 2010 and 2022 at the University Hospital in Cracow, Poland. RESULTS: The LR model demonstrated the best out-of-sample performance, achieving a specificity of 81.3% and an accuracy of 69.3%, with a sensitivity of 55.7%. Along with CART and XGB, LR performed well when using only 5 predictors: concentrations of parathormone (PTH), serum calcium, serum phosphates, total serum vitamin D, and maximal lesion diameter measured in ultrasound. Random forest (RF) exhibited higher sensitivity (62.7%), but lower specificity (74.2%) and accuracy (68.6%). Other models demonstrated subpar performance. CONCLUSIONS: Logistic regression and RF models were the most effective in predicting radiotracer uptake in pre-operative hybrid imaging of the parathyroids, suggesting their suitability as the foundation for software to be used in clinical settings. However, opting for the CART model, despite its easier interpretation, would come at the expense of performance.
format Article
id doaj-art-f359d18e20814d75a46bf6421fcd0cec
institution Kabale University
issn 1506-9680
1644-4345
language English
publishDate 2025-08-01
publisher Via Medica
record_format Article
series Nuclear Medicine Review
spelling doaj-art-f359d18e20814d75a46bf6421fcd0cec2025-08-21T07:22:28ZengVia MedicaNuclear Medicine Review1506-96801644-43452025-08-0128Continuous Publishing10.5603/nmr.105377Evaluation of multiple machine learning models predicting the results of hybrid imaging in primary hyperparathyroidismAnna Drynda0https://orcid.org/0009-0009-5556-2637Jacek Podlewski1Karolina Kucharczyk2Grzegorz Sokołowski3Anna Sowa-Staszczak4Alicja Hubalewska-Dydejczyk5Małgorzata Trofimiuk- Müldner6https://orcid.org/0000-0001-5247-9760Doctoral School of Medical Sciences and Health Sciences, Jagiellonian University Medical College, Kraków, PolandDover Fueling Solutions, Kraków, PolandStudents’ Scientific Group at the Department of Endocrinology, Jagiellonian University Medical College, Kraków, PolandChair and Department of Endocrinology, Jagiellonian University Medical College, Kraków, PolandChair and Department of Endocrinology, Jagiellonian University Medical College, Kraków, PolandChair and Department of Endocrinology, Jagiellonian University Medical College, Kraków, PolandChair and Department of Endocrinology, Jagiellonian University Medical College, Kraków, PolandBACKGROUND: Primary hyperparathyroidism (PHP) diagnosis is based on abnormalities in biochemical blood tests. Preoperative localization of the affected gland with imaging may increase the effectiveness of the surgical treatment. The aim of this study is to evaluate predictive strategies for the assessment of radiotracer uptake in pre-operative [99mTc]Tc-sestamibi scintigraphy ([99mTc] Tc-MIBI SPECT-CT) among PHP patients to identify individuals with a high probability of negative results, and to develop clinical decision-making tools. MATERIAL AND METHODS: Development and evaluation of logistic regression (LR), classification trees utilizing the classification and regression trees (CART) algorithm, random forest (RF), and boosted trees employing XGBoost (XGB) predictive models. All models were constructed using data obtained from 499 patients diagnosed with PHP who underwent [99mTc]Tc-MIBI SPECT-CT imaging between 2010 and 2022 at the University Hospital in Cracow, Poland. RESULTS: The LR model demonstrated the best out-of-sample performance, achieving a specificity of 81.3% and an accuracy of 69.3%, with a sensitivity of 55.7%. Along with CART and XGB, LR performed well when using only 5 predictors: concentrations of parathormone (PTH), serum calcium, serum phosphates, total serum vitamin D, and maximal lesion diameter measured in ultrasound. Random forest (RF) exhibited higher sensitivity (62.7%), but lower specificity (74.2%) and accuracy (68.6%). Other models demonstrated subpar performance. CONCLUSIONS: Logistic regression and RF models were the most effective in predicting radiotracer uptake in pre-operative hybrid imaging of the parathyroids, suggesting their suitability as the foundation for software to be used in clinical settings. However, opting for the CART model, despite its easier interpretation, would come at the expense of performance.https://journals.viamedica.pl/nuclear_medicine_review/article/view/105377primary hyperparathyroidismSPECT-CThybrid imagingparathyroidectomymachine learning
spellingShingle Anna Drynda
Jacek Podlewski
Karolina Kucharczyk
Grzegorz Sokołowski
Anna Sowa-Staszczak
Alicja Hubalewska-Dydejczyk
Małgorzata Trofimiuk- Müldner
Evaluation of multiple machine learning models predicting the results of hybrid imaging in primary hyperparathyroidism
Nuclear Medicine Review
primary hyperparathyroidism
SPECT-CT
hybrid imaging
parathyroidectomy
machine learning
title Evaluation of multiple machine learning models predicting the results of hybrid imaging in primary hyperparathyroidism
title_full Evaluation of multiple machine learning models predicting the results of hybrid imaging in primary hyperparathyroidism
title_fullStr Evaluation of multiple machine learning models predicting the results of hybrid imaging in primary hyperparathyroidism
title_full_unstemmed Evaluation of multiple machine learning models predicting the results of hybrid imaging in primary hyperparathyroidism
title_short Evaluation of multiple machine learning models predicting the results of hybrid imaging in primary hyperparathyroidism
title_sort evaluation of multiple machine learning models predicting the results of hybrid imaging in primary hyperparathyroidism
topic primary hyperparathyroidism
SPECT-CT
hybrid imaging
parathyroidectomy
machine learning
url https://journals.viamedica.pl/nuclear_medicine_review/article/view/105377
work_keys_str_mv AT annadrynda evaluationofmultiplemachinelearningmodelspredictingtheresultsofhybridimaginginprimaryhyperparathyroidism
AT jacekpodlewski evaluationofmultiplemachinelearningmodelspredictingtheresultsofhybridimaginginprimaryhyperparathyroidism
AT karolinakucharczyk evaluationofmultiplemachinelearningmodelspredictingtheresultsofhybridimaginginprimaryhyperparathyroidism
AT grzegorzsokołowski evaluationofmultiplemachinelearningmodelspredictingtheresultsofhybridimaginginprimaryhyperparathyroidism
AT annasowastaszczak evaluationofmultiplemachinelearningmodelspredictingtheresultsofhybridimaginginprimaryhyperparathyroidism
AT alicjahubalewskadydejczyk evaluationofmultiplemachinelearningmodelspredictingtheresultsofhybridimaginginprimaryhyperparathyroidism
AT małgorzatatrofimiukmuldner evaluationofmultiplemachinelearningmodelspredictingtheresultsofhybridimaginginprimaryhyperparathyroidism