The interpretable machine learning model associated with metal mixtures to identify hypertension via EMR mining method
© 2024 The Authors. The Journal of Clinical Hypertension published by Wiley Periodicals LLC..
There are limited data available regarding the connection between hypertension and heavy metal exposure. The authors intend to establish an interpretable machine learning (ML) model with high efficiency and robustness that identifies hypertension based on heavy metal exposure. Our datasets were obtained from the US National Health and Nutrition Examination Survey (NHANES, 2013-2020.3). The authors developed 5 ML models for hypertension identification by heavy metal exposure, and tested them by 10 discrimination characteristics. Further, the authors chose the optimally performing model after parameter adjustment by Genetic Algorithm (GA) for identification. Finally, in order to visualize the model's ability to make decisions, the authors used SHapley Additive exPlanation (SHAP) and Local Interpretable Model-Agnostic Explanations (LIME) algorithm to illustrate the features. The study included 19 368 participants in total. A best-performing eXtreme Gradient Boosting (XGB) with GA for hypertension identification by 16 heavy metals was selected (AUC: 0.774; 95% CI: 0.772-0.776; accuracy: 87.7%). According to SHAP values, Barium (0.02), Cadmium (0.017), Lead (0.017), Antimony (0.008), Tin (0.007), Manganese (0.006), Thallium (0.004), Tungsten (0.004) in urine, and Lead (0.048), Mercury (0.035), Selenium (0.05), Manganese (0.007) in blood positively influenced the model, while Cadmium (-0.001) in urine negatively influenced the model. Study participants' hypertension associated with heavy metal exposure was identified by an efficient, robust, and interpretable GA-XGB model with SHAP and LIME. Barium, Cadmium, Lead, Antimony, Tin, Manganese, Thallium, Tungsten in urine, and Lead, Mercury, Selenium, Manganese in blood are positively correlated with hypertension, while Cadmium in blood is negatively correlated with hypertension.
Medienart: |
E-Artikel |
---|
Erscheinungsjahr: |
2024 |
---|---|
Erschienen: |
2024 |
Enthalten in: |
Zur Gesamtaufnahme - volume:26 |
---|---|
Enthalten in: |
Journal of clinical hypertension (Greenwich, Conn.) - 26(2024), 2 vom: 15. Feb., Seite 187-196 |
Sprache: |
Englisch |
---|
Beteiligte Personen: |
---|
Links: |
---|
Anmerkungen: |
Date Completed 14.02.2024 Date Revised 22.03.2024 published: Print-Electronic Citation Status MEDLINE |
---|
doi: |
10.1111/jch.14768 |
---|
funding: |
|
---|---|
Förderinstitution / Projekttitel: |
|
PPN (Katalog-ID): |
NLM367047438 |
---|
LEADER | 01000caa a22002652 4500 | ||
---|---|---|---|
001 | NLM367047438 | ||
003 | DE-627 | ||
005 | 20240323000543.0 | ||
007 | cr uuu---uuuuu | ||
008 | 240114s2024 xx |||||o 00| ||eng c | ||
024 | 7 | |a 10.1111/jch.14768 |2 doi | |
028 | 5 | 2 | |a pubmed24n1341.xml |
035 | |a (DE-627)NLM367047438 | ||
035 | |a (NLM)38214193 | ||
040 | |a DE-627 |b ger |c DE-627 |e rakwb | ||
041 | |a eng | ||
100 | 1 | |a Xu, Site |e verfasserin |4 aut | |
245 | 1 | 4 | |a The interpretable machine learning model associated with metal mixtures to identify hypertension via EMR mining method |
264 | 1 | |c 2024 | |
336 | |a Text |b txt |2 rdacontent | ||
337 | |a ƒaComputermedien |b c |2 rdamedia | ||
338 | |a ƒa Online-Ressource |b cr |2 rdacarrier | ||
500 | |a Date Completed 14.02.2024 | ||
500 | |a Date Revised 22.03.2024 | ||
500 | |a published: Print-Electronic | ||
500 | |a Citation Status MEDLINE | ||
520 | |a © 2024 The Authors. The Journal of Clinical Hypertension published by Wiley Periodicals LLC. | ||
520 | |a There are limited data available regarding the connection between hypertension and heavy metal exposure. The authors intend to establish an interpretable machine learning (ML) model with high efficiency and robustness that identifies hypertension based on heavy metal exposure. Our datasets were obtained from the US National Health and Nutrition Examination Survey (NHANES, 2013-2020.3). The authors developed 5 ML models for hypertension identification by heavy metal exposure, and tested them by 10 discrimination characteristics. Further, the authors chose the optimally performing model after parameter adjustment by Genetic Algorithm (GA) for identification. Finally, in order to visualize the model's ability to make decisions, the authors used SHapley Additive exPlanation (SHAP) and Local Interpretable Model-Agnostic Explanations (LIME) algorithm to illustrate the features. The study included 19 368 participants in total. A best-performing eXtreme Gradient Boosting (XGB) with GA for hypertension identification by 16 heavy metals was selected (AUC: 0.774; 95% CI: 0.772-0.776; accuracy: 87.7%). According to SHAP values, Barium (0.02), Cadmium (0.017), Lead (0.017), Antimony (0.008), Tin (0.007), Manganese (0.006), Thallium (0.004), Tungsten (0.004) in urine, and Lead (0.048), Mercury (0.035), Selenium (0.05), Manganese (0.007) in blood positively influenced the model, while Cadmium (-0.001) in urine negatively influenced the model. Study participants' hypertension associated with heavy metal exposure was identified by an efficient, robust, and interpretable GA-XGB model with SHAP and LIME. Barium, Cadmium, Lead, Antimony, Tin, Manganese, Thallium, Tungsten in urine, and Lead, Mercury, Selenium, Manganese in blood are positively correlated with hypertension, while Cadmium in blood is negatively correlated with hypertension | ||
650 | 4 | |a Journal Article | |
650 | 4 | |a EMR | |
650 | 4 | |a NHANES | |
650 | 4 | |a hypertension | |
650 | 4 | |a machine learning | |
650 | 4 | |a metal mixture | |
650 | 7 | |a Cadmium |2 NLM | |
650 | 7 | |a 00BH33GNGH |2 NLM | |
650 | 7 | |a Antimony |2 NLM | |
650 | 7 | |a 9IT35J3UV3 |2 NLM | |
650 | 7 | |a Manganese |2 NLM | |
650 | 7 | |a 42Z2K6ZL8P |2 NLM | |
650 | 7 | |a Thallium |2 NLM | |
650 | 7 | |a AD84R52XLF |2 NLM | |
650 | 7 | |a Tungsten |2 NLM | |
650 | 7 | |a V9306CXO6G |2 NLM | |
650 | 7 | |a Barium |2 NLM | |
650 | 7 | |a 24GP945V5T |2 NLM | |
650 | 7 | |a Tin |2 NLM | |
650 | 7 | |a 7440-31-5 |2 NLM | |
650 | 7 | |a Selenium |2 NLM | |
650 | 7 | |a H6241UJ22B |2 NLM | |
650 | 7 | |a lime |2 NLM | |
650 | 7 | |a C7X2M0VVNH |2 NLM | |
650 | 7 | |a Metals, Heavy |2 NLM | |
650 | 7 | |a Mercury |2 NLM | |
650 | 7 | |a FXS1BY2PGL |2 NLM | |
650 | 7 | |a Oxides |2 NLM | |
650 | 7 | |a Calcium Compounds |2 NLM | |
700 | 1 | |a Sun, Mu |e verfasserin |4 aut | |
773 | 0 | 8 | |i Enthalten in |t Journal of clinical hypertension (Greenwich, Conn.) |d 1999 |g 26(2024), 2 vom: 15. Feb., Seite 187-196 |w (DE-627)NLM113204264 |x 1751-7176 |7 nnns |
773 | 1 | 8 | |g volume:26 |g year:2024 |g number:2 |g day:15 |g month:02 |g pages:187-196 |
856 | 4 | 0 | |u http://dx.doi.org/10.1111/jch.14768 |3 Volltext |
912 | |a GBV_USEFLAG_A | ||
912 | |a GBV_NLM | ||
951 | |a AR | ||
952 | |d 26 |j 2024 |e 2 |b 15 |c 02 |h 187-196 |