A machine learning prediction model for Cardiac Amyloidosis using routine blood tests in patients with left ventricular hypertrophy
Abstract Current approaches for cardiac amyloidosis (CA) identification are time-consuming, labor-intensive, and present challenges in sensitivity and accuracy, leading to limited treatment efficacy and poor prognosis for patients. In this retrospective study, we aimed to leverage machine learning (...
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Nature Portfolio
2024-11-01
|
| Series: | Scientific Reports |
| Subjects: | |
| Online Access: | https://doi.org/10.1038/s41598-024-77466-8 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1850129760099762176 |
|---|---|
| author | Yuling Pan Qingkun Fan Yu Liang Yunfan Liu Haihang You Chunzi Liang |
| author_facet | Yuling Pan Qingkun Fan Yu Liang Yunfan Liu Haihang You Chunzi Liang |
| author_sort | Yuling Pan |
| collection | DOAJ |
| description | Abstract Current approaches for cardiac amyloidosis (CA) identification are time-consuming, labor-intensive, and present challenges in sensitivity and accuracy, leading to limited treatment efficacy and poor prognosis for patients. In this retrospective study, we aimed to leverage machine learning (ML) to create a diagnostic model for CA using data from routine blood tests. Our dataset included 6,563 patients with left ventricular hypertrophy, 261 of whom had been diagnosed with CA. We divided the dataset into training and testing cohorts, applying ML algorithms such as logistic regression, random forest, and XGBoost for automated learning and prediction. Our model’s diagnostic accuracy was then evaluated against CA biomarkers, specifically serum-free light chains (FLCs). The model’s interpretability was elucidated by visualizing the feature importance through the gain map. XGBoost outperformed both random forest and logistic regression in internal validation on the testing cohort, achieving an area under the curve (AUC) of 0.95 (95%CI: 0.92–0.97), sensitivity of 0.92 (95%CI: 0.86–0.98), specificity of 0.95 (95%CI: 0.94–0.97), and an F1 score of 0.89 (95%CI: 0.85–0.92). Its performance was also superior to the serum FLC-kappa and FLC-lambda combination (AUC of 0.88). Furthermore, XGBoost identified unique biomarker signatures indicative of multisystem dysfunction in CA patients, with significant changes in eGFR, FT3, cTnI, ANC, and NT-proBNP. This study develops a highly sensitive and accurate ML model for CA detection using routine clinical laboratory data, effectively streamlining diagnostic procedures, and providing valuable clinical insights and guiding future research into disease mechanisms. |
| format | Article |
| id | doaj-art-63bbe87d07984ac1bd45de8fe24f58bb |
| institution | OA Journals |
| issn | 2045-2322 |
| language | English |
| publishDate | 2024-11-01 |
| publisher | Nature Portfolio |
| record_format | Article |
| series | Scientific Reports |
| spelling | doaj-art-63bbe87d07984ac1bd45de8fe24f58bb2025-08-20T02:32:52ZengNature PortfolioScientific Reports2045-23222024-11-0114111110.1038/s41598-024-77466-8A machine learning prediction model for Cardiac Amyloidosis using routine blood tests in patients with left ventricular hypertrophyYuling Pan0Qingkun Fan1Yu Liang2Yunfan Liu3Haihang You4Chunzi Liang5School of Laboratory Medicine, Hubei University of Chinese MedicineDepartment of Medical Laboratory, Wuhan Asia Heart HospitalSchool of Laboratory Medicine, Hubei University of Chinese MedicineUniversity of TorontoInstitute of Computing Technology, Chinese Academy of SciencesSchool of Laboratory Medicine, Hubei University of Chinese MedicineAbstract Current approaches for cardiac amyloidosis (CA) identification are time-consuming, labor-intensive, and present challenges in sensitivity and accuracy, leading to limited treatment efficacy and poor prognosis for patients. In this retrospective study, we aimed to leverage machine learning (ML) to create a diagnostic model for CA using data from routine blood tests. Our dataset included 6,563 patients with left ventricular hypertrophy, 261 of whom had been diagnosed with CA. We divided the dataset into training and testing cohorts, applying ML algorithms such as logistic regression, random forest, and XGBoost for automated learning and prediction. Our model’s diagnostic accuracy was then evaluated against CA biomarkers, specifically serum-free light chains (FLCs). The model’s interpretability was elucidated by visualizing the feature importance through the gain map. XGBoost outperformed both random forest and logistic regression in internal validation on the testing cohort, achieving an area under the curve (AUC) of 0.95 (95%CI: 0.92–0.97), sensitivity of 0.92 (95%CI: 0.86–0.98), specificity of 0.95 (95%CI: 0.94–0.97), and an F1 score of 0.89 (95%CI: 0.85–0.92). Its performance was also superior to the serum FLC-kappa and FLC-lambda combination (AUC of 0.88). Furthermore, XGBoost identified unique biomarker signatures indicative of multisystem dysfunction in CA patients, with significant changes in eGFR, FT3, cTnI, ANC, and NT-proBNP. This study develops a highly sensitive and accurate ML model for CA detection using routine clinical laboratory data, effectively streamlining diagnostic procedures, and providing valuable clinical insights and guiding future research into disease mechanisms.https://doi.org/10.1038/s41598-024-77466-8Cardiac amyloidosisMachine learningRoutine blood testsMulti-system dysfunction profilePrediction model |
| spellingShingle | Yuling Pan Qingkun Fan Yu Liang Yunfan Liu Haihang You Chunzi Liang A machine learning prediction model for Cardiac Amyloidosis using routine blood tests in patients with left ventricular hypertrophy Scientific Reports Cardiac amyloidosis Machine learning Routine blood tests Multi-system dysfunction profile Prediction model |
| title | A machine learning prediction model for Cardiac Amyloidosis using routine blood tests in patients with left ventricular hypertrophy |
| title_full | A machine learning prediction model for Cardiac Amyloidosis using routine blood tests in patients with left ventricular hypertrophy |
| title_fullStr | A machine learning prediction model for Cardiac Amyloidosis using routine blood tests in patients with left ventricular hypertrophy |
| title_full_unstemmed | A machine learning prediction model for Cardiac Amyloidosis using routine blood tests in patients with left ventricular hypertrophy |
| title_short | A machine learning prediction model for Cardiac Amyloidosis using routine blood tests in patients with left ventricular hypertrophy |
| title_sort | machine learning prediction model for cardiac amyloidosis using routine blood tests in patients with left ventricular hypertrophy |
| topic | Cardiac amyloidosis Machine learning Routine blood tests Multi-system dysfunction profile Prediction model |
| url | https://doi.org/10.1038/s41598-024-77466-8 |
| work_keys_str_mv | AT yulingpan amachinelearningpredictionmodelforcardiacamyloidosisusingroutinebloodtestsinpatientswithleftventricularhypertrophy AT qingkunfan amachinelearningpredictionmodelforcardiacamyloidosisusingroutinebloodtestsinpatientswithleftventricularhypertrophy AT yuliang amachinelearningpredictionmodelforcardiacamyloidosisusingroutinebloodtestsinpatientswithleftventricularhypertrophy AT yunfanliu amachinelearningpredictionmodelforcardiacamyloidosisusingroutinebloodtestsinpatientswithleftventricularhypertrophy AT haihangyou amachinelearningpredictionmodelforcardiacamyloidosisusingroutinebloodtestsinpatientswithleftventricularhypertrophy AT chunziliang amachinelearningpredictionmodelforcardiacamyloidosisusingroutinebloodtestsinpatientswithleftventricularhypertrophy AT yulingpan machinelearningpredictionmodelforcardiacamyloidosisusingroutinebloodtestsinpatientswithleftventricularhypertrophy AT qingkunfan machinelearningpredictionmodelforcardiacamyloidosisusingroutinebloodtestsinpatientswithleftventricularhypertrophy AT yuliang machinelearningpredictionmodelforcardiacamyloidosisusingroutinebloodtestsinpatientswithleftventricularhypertrophy AT yunfanliu machinelearningpredictionmodelforcardiacamyloidosisusingroutinebloodtestsinpatientswithleftventricularhypertrophy AT haihangyou machinelearningpredictionmodelforcardiacamyloidosisusingroutinebloodtestsinpatientswithleftventricularhypertrophy AT chunziliang machinelearningpredictionmodelforcardiacamyloidosisusingroutinebloodtestsinpatientswithleftventricularhypertrophy |