Artificial intelligence-enabled electrocardiography identifies severe dyscalcemias and has prognostic value
•Artificial intelligence-enabled electrocardiography can accurately identify severe dyscalcemia.•The artificial intelligence-identified dyscalcemia was associated with multiple abnormal rhythms and physical conditions.•The false positive artificial intelligence-enabled electrocardiography was associ...
Gespeichert in:
| Veröffentlicht in: | Clinica chimica acta 2022-11, Vol.536, p.126-134 |
|---|---|
| Hauptverfasser: | , , , , , , , , |
| Format: | Artikel |
| Sprache: | eng |
| Schlagworte: | |
| Online-Zugang: | Volltext |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| container_end_page | 134 |
|---|---|
| container_issue | |
| container_start_page | 126 |
| container_title | Clinica chimica acta |
| container_volume | 536 |
| creator | Lin, Chin Chen, Chien-Chou Chau, Tom Lin, Chin-Sheng Tsai, Shi-Hung Lee, Ding-Jie Lee, Chia-Cheng Shang, Hung-Sheng Lin, Shih-Hua |
| description | •Artificial intelligence-enabled electrocardiography can accurately identify severe dyscalcemia.•The artificial intelligence-identified dyscalcemia was associated with multiple abnormal rhythms and physical conditions.•The false positive artificial intelligence-enabled electrocardiography was associated with increased risk of complications.•Future application of artificial intelligence-enabled electrocardiography may actively detect unexpected severe dyscalcemia.
Abnormal serum calcium concentrations affect the heart and may alter the electrocardiogram (ECG), but the detection of hypocalcemia and hypercalcemia (collectively dyscalcemia) relies on blood laboratory tests requiring turnaround time.
The study aimed to develop a bloodless artificial intelligence (AI)-enabled (ECG) method to rapidly detect dyscalcemia and analyze its possible utility for outcome prediction.
This study collected 86,731 development, 15,611 tuning, 11,105 internal validation, and 8401 external validation ECGs from electronic medical records with at least 1 ECG associated with an albumin-adjusted calcium (aCa) value within 4 h. The main outcomes were to assess the accuracy of AI-ECG to predict aCa and follow up these patients for all-cause mortality, new-onset acute myocardial infraction (AMI), and new-onset heart failure (HF) to validate the ability of AI-ECG-aCa for previvor identification.
ECG-aCa had mean absolute errors (MAE) of 0.78/0.98 mg/dL and achieved an area under receiver operating characteristic curves (AUCs) 0.9219/0.8447 and 0.8948/0.7723 to detect severe hypercalcemia and hypocalcemia in the internal/external validation sets, respectively. Although |
| doi_str_mv | 10.1016/j.cca.2022.09.021 |
| format | Article |
| fullrecord | <record><control><sourceid>proquest_cross</sourceid><recordid>TN_cdi_proquest_miscellaneous_2718960857</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><els_id>S0009898122013195</els_id><sourcerecordid>2718960857</sourcerecordid><originalsourceid>FETCH-LOGICAL-c373t-f16de43eaba18e4957fd5dd4c9a030dfc56bb75a57104363dcd971df8d344f053</originalsourceid><addsrcrecordid>eNp9kD1PwzAQhi0EEqXwA9g8siTYsRPHYqoqvqRKLDBbjn1uXdyk2Gml_nsclZnp1Unvc7p7ELqnpKSENo_b0hhdVqSqSiJLUtELNKOtYAXjsrpEM0KILFrZ0mt0k9I2j5w0dIa-F3H0zhuvA_b9CCH4NfQGCuh1F8BiCGDGOBgdrR_WUe83J-wt9BMFCSc4QgRsT8noYGDndcK6t3iTcx-HdT-k0Rt81OEAt-jK6ZDg7i_n6Ovl-XP5Vqw-Xt-Xi1VhmGBj4WhjgTPQnaYtcFkLZ2truZGaMGKdqZuuE7WuBSWcNcwaKwW1rrWMc0dqNkcP5735gJ8DpFHtfDL5Nd3DcEiqErSVDWlrkav0XDVxSCmCU_vodzqeFCVqEqu2KotVk1hFpMpiM_N0ZiD_cPQQVTJ-cmZ9zK6UHfw_9C8tfoO5</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>2718960857</pqid></control><display><type>article</type><title>Artificial intelligence-enabled electrocardiography identifies severe dyscalcemias and has prognostic value</title><source>Elsevier ScienceDirect Journals Complete</source><creator>Lin, Chin ; Chen, Chien-Chou ; Chau, Tom ; Lin, Chin-Sheng ; Tsai, Shi-Hung ; Lee, Ding-Jie ; Lee, Chia-Cheng ; Shang, Hung-Sheng ; Lin, Shih-Hua</creator><creatorcontrib>Lin, Chin ; Chen, Chien-Chou ; Chau, Tom ; Lin, Chin-Sheng ; Tsai, Shi-Hung ; Lee, Ding-Jie ; Lee, Chia-Cheng ; Shang, Hung-Sheng ; Lin, Shih-Hua</creatorcontrib><description>•Artificial intelligence-enabled electrocardiography can accurately identify severe dyscalcemia.•The artificial intelligence-identified dyscalcemia was associated with multiple abnormal rhythms and physical conditions.•The false positive artificial intelligence-enabled electrocardiography was associated with increased risk of complications.•Future application of artificial intelligence-enabled electrocardiography may actively detect unexpected severe dyscalcemia.
Abnormal serum calcium concentrations affect the heart and may alter the electrocardiogram (ECG), but the detection of hypocalcemia and hypercalcemia (collectively dyscalcemia) relies on blood laboratory tests requiring turnaround time.
The study aimed to develop a bloodless artificial intelligence (AI)-enabled (ECG) method to rapidly detect dyscalcemia and analyze its possible utility for outcome prediction.
This study collected 86,731 development, 15,611 tuning, 11,105 internal validation, and 8401 external validation ECGs from electronic medical records with at least 1 ECG associated with an albumin-adjusted calcium (aCa) value within 4 h. The main outcomes were to assess the accuracy of AI-ECG to predict aCa and follow up these patients for all-cause mortality, new-onset acute myocardial infraction (AMI), and new-onset heart failure (HF) to validate the ability of AI-ECG-aCa for previvor identification.
ECG-aCa had mean absolute errors (MAE) of 0.78/0.98 mg/dL and achieved an area under receiver operating characteristic curves (AUCs) 0.9219/0.8447 and 0.8948/0.7723 to detect severe hypercalcemia and hypocalcemia in the internal/external validation sets, respectively. Although < 20 % variance of ECG-aCa could be explained by traditional ECG features, the ECG-aCa was found to be associated with more complications. Patients with ECG-hypercalcemia but initially normal aCa were found to have a higher risk of subsequent all-cause mortality [hazard ratio (HR): 2.05, 95 % conference interval (CI): 1.55–2.70], new-onset AMI (HR: 2.88, 95 % CI: 1.72–4.83), and new-onset HF (HR: 2.02, 95 % CI: 1.38–2.97) in the internal validation set, which were also seen in external validation.
The AI-ECG-aCa may help detecting severe dyscalcemia for early diagnosis and ECG-hypercalcemia also has prognostic value for clinical outcomes (all-cause mortality and new-onset AMI and HF).</description><identifier>ISSN: 0009-8981</identifier><identifier>EISSN: 1873-3492</identifier><identifier>DOI: 10.1016/j.cca.2022.09.021</identifier><language>eng</language><publisher>Elsevier B.V</publisher><subject>Albumin ; Artificial intelligence ; Calcium ; Deep learning ; Electrocardiogram</subject><ispartof>Clinica chimica acta, 2022-11, Vol.536, p.126-134</ispartof><rights>2022 The Authors</rights><lds50>peer_reviewed</lds50><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed><citedby>FETCH-LOGICAL-c373t-f16de43eaba18e4957fd5dd4c9a030dfc56bb75a57104363dcd971df8d344f053</citedby><cites>FETCH-LOGICAL-c373t-f16de43eaba18e4957fd5dd4c9a030dfc56bb75a57104363dcd971df8d344f053</cites></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktohtml>$$Uhttps://dx.doi.org/10.1016/j.cca.2022.09.021$$EHTML$$P50$$Gelsevier$$Hfree_for_read</linktohtml><link.rule.ids>314,780,784,3550,27924,27925,45995</link.rule.ids></links><search><creatorcontrib>Lin, Chin</creatorcontrib><creatorcontrib>Chen, Chien-Chou</creatorcontrib><creatorcontrib>Chau, Tom</creatorcontrib><creatorcontrib>Lin, Chin-Sheng</creatorcontrib><creatorcontrib>Tsai, Shi-Hung</creatorcontrib><creatorcontrib>Lee, Ding-Jie</creatorcontrib><creatorcontrib>Lee, Chia-Cheng</creatorcontrib><creatorcontrib>Shang, Hung-Sheng</creatorcontrib><creatorcontrib>Lin, Shih-Hua</creatorcontrib><title>Artificial intelligence-enabled electrocardiography identifies severe dyscalcemias and has prognostic value</title><title>Clinica chimica acta</title><description>•Artificial intelligence-enabled electrocardiography can accurately identify severe dyscalcemia.•The artificial intelligence-identified dyscalcemia was associated with multiple abnormal rhythms and physical conditions.•The false positive artificial intelligence-enabled electrocardiography was associated with increased risk of complications.•Future application of artificial intelligence-enabled electrocardiography may actively detect unexpected severe dyscalcemia.
Abnormal serum calcium concentrations affect the heart and may alter the electrocardiogram (ECG), but the detection of hypocalcemia and hypercalcemia (collectively dyscalcemia) relies on blood laboratory tests requiring turnaround time.
The study aimed to develop a bloodless artificial intelligence (AI)-enabled (ECG) method to rapidly detect dyscalcemia and analyze its possible utility for outcome prediction.
This study collected 86,731 development, 15,611 tuning, 11,105 internal validation, and 8401 external validation ECGs from electronic medical records with at least 1 ECG associated with an albumin-adjusted calcium (aCa) value within 4 h. The main outcomes were to assess the accuracy of AI-ECG to predict aCa and follow up these patients for all-cause mortality, new-onset acute myocardial infraction (AMI), and new-onset heart failure (HF) to validate the ability of AI-ECG-aCa for previvor identification.
ECG-aCa had mean absolute errors (MAE) of 0.78/0.98 mg/dL and achieved an area under receiver operating characteristic curves (AUCs) 0.9219/0.8447 and 0.8948/0.7723 to detect severe hypercalcemia and hypocalcemia in the internal/external validation sets, respectively. Although < 20 % variance of ECG-aCa could be explained by traditional ECG features, the ECG-aCa was found to be associated with more complications. Patients with ECG-hypercalcemia but initially normal aCa were found to have a higher risk of subsequent all-cause mortality [hazard ratio (HR): 2.05, 95 % conference interval (CI): 1.55–2.70], new-onset AMI (HR: 2.88, 95 % CI: 1.72–4.83), and new-onset HF (HR: 2.02, 95 % CI: 1.38–2.97) in the internal validation set, which were also seen in external validation.
The AI-ECG-aCa may help detecting severe dyscalcemia for early diagnosis and ECG-hypercalcemia also has prognostic value for clinical outcomes (all-cause mortality and new-onset AMI and HF).</description><subject>Albumin</subject><subject>Artificial intelligence</subject><subject>Calcium</subject><subject>Deep learning</subject><subject>Electrocardiogram</subject><issn>0009-8981</issn><issn>1873-3492</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2022</creationdate><recordtype>article</recordtype><recordid>eNp9kD1PwzAQhi0EEqXwA9g8siTYsRPHYqoqvqRKLDBbjn1uXdyk2Gml_nsclZnp1Unvc7p7ELqnpKSENo_b0hhdVqSqSiJLUtELNKOtYAXjsrpEM0KILFrZ0mt0k9I2j5w0dIa-F3H0zhuvA_b9CCH4NfQGCuh1F8BiCGDGOBgdrR_WUe83J-wt9BMFCSc4QgRsT8noYGDndcK6t3iTcx-HdT-k0Rt81OEAt-jK6ZDg7i_n6Ovl-XP5Vqw-Xt-Xi1VhmGBj4WhjgTPQnaYtcFkLZ2truZGaMGKdqZuuE7WuBSWcNcwaKwW1rrWMc0dqNkcP5735gJ8DpFHtfDL5Nd3DcEiqErSVDWlrkav0XDVxSCmCU_vodzqeFCVqEqu2KotVk1hFpMpiM_N0ZiD_cPQQVTJ-cmZ9zK6UHfw_9C8tfoO5</recordid><startdate>20221101</startdate><enddate>20221101</enddate><creator>Lin, Chin</creator><creator>Chen, Chien-Chou</creator><creator>Chau, Tom</creator><creator>Lin, Chin-Sheng</creator><creator>Tsai, Shi-Hung</creator><creator>Lee, Ding-Jie</creator><creator>Lee, Chia-Cheng</creator><creator>Shang, Hung-Sheng</creator><creator>Lin, Shih-Hua</creator><general>Elsevier B.V</general><scope>6I.</scope><scope>AAFTH</scope><scope>AAYXX</scope><scope>CITATION</scope><scope>7X8</scope></search><sort><creationdate>20221101</creationdate><title>Artificial intelligence-enabled electrocardiography identifies severe dyscalcemias and has prognostic value</title><author>Lin, Chin ; Chen, Chien-Chou ; Chau, Tom ; Lin, Chin-Sheng ; Tsai, Shi-Hung ; Lee, Ding-Jie ; Lee, Chia-Cheng ; Shang, Hung-Sheng ; Lin, Shih-Hua</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c373t-f16de43eaba18e4957fd5dd4c9a030dfc56bb75a57104363dcd971df8d344f053</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2022</creationdate><topic>Albumin</topic><topic>Artificial intelligence</topic><topic>Calcium</topic><topic>Deep learning</topic><topic>Electrocardiogram</topic><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Lin, Chin</creatorcontrib><creatorcontrib>Chen, Chien-Chou</creatorcontrib><creatorcontrib>Chau, Tom</creatorcontrib><creatorcontrib>Lin, Chin-Sheng</creatorcontrib><creatorcontrib>Tsai, Shi-Hung</creatorcontrib><creatorcontrib>Lee, Ding-Jie</creatorcontrib><creatorcontrib>Lee, Chia-Cheng</creatorcontrib><creatorcontrib>Shang, Hung-Sheng</creatorcontrib><creatorcontrib>Lin, Shih-Hua</creatorcontrib><collection>ScienceDirect Open Access Titles</collection><collection>Elsevier:ScienceDirect:Open Access</collection><collection>CrossRef</collection><collection>MEDLINE - Academic</collection><jtitle>Clinica chimica acta</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Lin, Chin</au><au>Chen, Chien-Chou</au><au>Chau, Tom</au><au>Lin, Chin-Sheng</au><au>Tsai, Shi-Hung</au><au>Lee, Ding-Jie</au><au>Lee, Chia-Cheng</au><au>Shang, Hung-Sheng</au><au>Lin, Shih-Hua</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Artificial intelligence-enabled electrocardiography identifies severe dyscalcemias and has prognostic value</atitle><jtitle>Clinica chimica acta</jtitle><date>2022-11-01</date><risdate>2022</risdate><volume>536</volume><spage>126</spage><epage>134</epage><pages>126-134</pages><issn>0009-8981</issn><eissn>1873-3492</eissn><abstract>•Artificial intelligence-enabled electrocardiography can accurately identify severe dyscalcemia.•The artificial intelligence-identified dyscalcemia was associated with multiple abnormal rhythms and physical conditions.•The false positive artificial intelligence-enabled electrocardiography was associated with increased risk of complications.•Future application of artificial intelligence-enabled electrocardiography may actively detect unexpected severe dyscalcemia.
Abnormal serum calcium concentrations affect the heart and may alter the electrocardiogram (ECG), but the detection of hypocalcemia and hypercalcemia (collectively dyscalcemia) relies on blood laboratory tests requiring turnaround time.
The study aimed to develop a bloodless artificial intelligence (AI)-enabled (ECG) method to rapidly detect dyscalcemia and analyze its possible utility for outcome prediction.
This study collected 86,731 development, 15,611 tuning, 11,105 internal validation, and 8401 external validation ECGs from electronic medical records with at least 1 ECG associated with an albumin-adjusted calcium (aCa) value within 4 h. The main outcomes were to assess the accuracy of AI-ECG to predict aCa and follow up these patients for all-cause mortality, new-onset acute myocardial infraction (AMI), and new-onset heart failure (HF) to validate the ability of AI-ECG-aCa for previvor identification.
ECG-aCa had mean absolute errors (MAE) of 0.78/0.98 mg/dL and achieved an area under receiver operating characteristic curves (AUCs) 0.9219/0.8447 and 0.8948/0.7723 to detect severe hypercalcemia and hypocalcemia in the internal/external validation sets, respectively. Although < 20 % variance of ECG-aCa could be explained by traditional ECG features, the ECG-aCa was found to be associated with more complications. Patients with ECG-hypercalcemia but initially normal aCa were found to have a higher risk of subsequent all-cause mortality [hazard ratio (HR): 2.05, 95 % conference interval (CI): 1.55–2.70], new-onset AMI (HR: 2.88, 95 % CI: 1.72–4.83), and new-onset HF (HR: 2.02, 95 % CI: 1.38–2.97) in the internal validation set, which were also seen in external validation.
The AI-ECG-aCa may help detecting severe dyscalcemia for early diagnosis and ECG-hypercalcemia also has prognostic value for clinical outcomes (all-cause mortality and new-onset AMI and HF).</abstract><pub>Elsevier B.V</pub><doi>10.1016/j.cca.2022.09.021</doi><tpages>9</tpages><oa>free_for_read</oa></addata></record> |
| fulltext | fulltext |
| identifier | ISSN: 0009-8981 |
| ispartof | Clinica chimica acta, 2022-11, Vol.536, p.126-134 |
| issn | 0009-8981 1873-3492 |
| language | eng |
| recordid | cdi_proquest_miscellaneous_2718960857 |
| source | Elsevier ScienceDirect Journals Complete |
| subjects | Albumin Artificial intelligence Calcium Deep learning Electrocardiogram |
| title | Artificial intelligence-enabled electrocardiography identifies severe dyscalcemias and has prognostic value |
| url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2024-12-28T04%3A59%3A36IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest_cross&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=Artificial%20intelligence-enabled%20electrocardiography%20identifies%20severe%20dyscalcemias%20and%20has%20prognostic%20value&rft.jtitle=Clinica%20chimica%20acta&rft.au=Lin,%20Chin&rft.date=2022-11-01&rft.volume=536&rft.spage=126&rft.epage=134&rft.pages=126-134&rft.issn=0009-8981&rft.eissn=1873-3492&rft_id=info:doi/10.1016/j.cca.2022.09.021&rft_dat=%3Cproquest_cross%3E2718960857%3C/proquest_cross%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_pqid=2718960857&rft_id=info:pmid/&rft_els_id=S0009898122013195&rfr_iscdi=true |