Impact of the AI-based CariHeart risk score, using cardiac CT angiography, on the stratification of patients with suspected coronary artery disease: insight from the NHS England Pilot project
Introduction: The AI-based CariHeart Risk calculator has been developed using cardiac computed tomography angiography (CCTA) assessment of peri-coronary artery inflammation (FAI) and conventional cardiovascular risk factors to predict 8 years fatal and non-fatal cardiovascular events.As one of the 5...
Saved in:
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2025-07-01
|
| Series: | Clinical Medicine |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S1470211825001320 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1850071840343457792 |
|---|---|
| author | Nerea Sanfeliu Garces Tracy Barnfather Lynne Cooley Barbara Kardos Ahmed Alsinbili Mike Pashler Sudipta Chattopadhyay Attila Kardos |
| author_facet | Nerea Sanfeliu Garces Tracy Barnfather Lynne Cooley Barbara Kardos Ahmed Alsinbili Mike Pashler Sudipta Chattopadhyay Attila Kardos |
| author_sort | Nerea Sanfeliu Garces |
| collection | DOAJ |
| description | Introduction: The AI-based CariHeart Risk calculator has been developed using cardiac computed tomography angiography (CCTA) assessment of peri-coronary artery inflammation (FAI) and conventional cardiovascular risk factors to predict 8 years fatal and non-fatal cardiovascular events.As one of the 5 hospitals chosen in the UK, we performed an interim analysis to assess the impact of the proposed new chest pain pathway on the risk stratification of patients referred for suspected angina to the Rapid Access Chest Pain Clinic (RACPC). Objective: We investigated the interaction (risk stratification predictive power) between the degree of coronary artery disease (CAD), the FAI risk score and the AI-based CariHeart Risk score. Methods: 135 consecutive patients referred to the RACPC were part of this analysis. 2 patients had no contrast CCTA images at patient request and were excluded. Risk stratification was defined as no or mild CAD (<50% stenosis), moderate, (50–69% stenosis) or severe (>70% stenosis) based on the degree or coronary artery luminal stenosis, a low FAI score defined as less than the 50 percentile for any coronary artery, intermediate FAI score defined as the 50–75 percentile for LAD/RCA or 50–90 percentile for LCX, and high FAI score defined as the >75 percentile for LAD/RCA and >90 percentile for LCX.Low AI-CariHeart risk score was defined as <1% 8 year’ CV mortality, intermediate risk as 1-5% CV mortality, and high risk as >5% CV mortality. Results: We found that patients with no or mild atherosclerotic CAD had a low FAI score in 4/114 (3.5%) cases; intermediate score in 16/114 (14%) cases; and high score in 94/114 (82%) cases (p<0.00001).Low CariHeart risk score was found in 4 (3.6%), intermediate risk score in 47 (41%), and high-risk score in 63 (55%) patients (p<0.0001).In no-or mild CAD patients, the FAI score identified more patients than did the CariHeart risk score as high risk (82% vs 55%, p<0.0001). However, merging the intermediate and high-FAI score patients and comparing them with the merged intermediate and high CariHeart risk score patients identified the same proportion of patients (97%).A low FAI score was found in none, intermediate score in 38%, and high score in 62% of the 13 patients with moderate CAD on CCTA (p=0.025).A low CariHeart risk score was found in none, intermediate risk score in 8%, and high-risk score in 92% of patients (p<0.007). A high FAI score was found in all 3 cases, whereas a high CariHeart score was found in 2 cases and intermediate in 1 with severe CAD on CCTA. Conclusion: The AI-based new chest pain pathway utilising CCTA images identified a higher proportion of at-risk patients, particularly those with non-obstructive CAD. FAI score and CariHeart risk score appear to perform similarly in the combined intermediate and high-risk groups.Further research into understanding the value of initiation of cardiovascular preventive therapy on outcome and intervention strategies to reduce perivascular inflammation and, hence, cardiovascular death is essential. |
| format | Article |
| id | doaj-art-593446b2cd8242bd82cea5994daabc3b |
| institution | DOAJ |
| issn | 1470-2118 |
| language | English |
| publishDate | 2025-07-01 |
| publisher | Elsevier |
| record_format | Article |
| series | Clinical Medicine |
| spelling | doaj-art-593446b2cd8242bd82cea5994daabc3b2025-08-20T02:47:13ZengElsevierClinical Medicine1470-21182025-07-0125410041410.1016/j.clinme.2025.100414Impact of the AI-based CariHeart risk score, using cardiac CT angiography, on the stratification of patients with suspected coronary artery disease: insight from the NHS England Pilot projectNerea Sanfeliu Garces0Tracy Barnfather1Lynne Cooley2Barbara Kardos3Ahmed Alsinbili4 Mike Pashler5Sudipta Chattopadhyay6Attila Kardos7Milton Keynes University Hospital NHS TrustMilton Keynes University Hospital NHS TrustMilton Keynes University Hospital NHS TrustOxford University HospitalsMilton Keynes University Hospital NHS TrustMilton Keynes University Hospital NHS TrustBedford Hospital NHS TrustMilton Keynes University Hospital NHS TrustIntroduction: The AI-based CariHeart Risk calculator has been developed using cardiac computed tomography angiography (CCTA) assessment of peri-coronary artery inflammation (FAI) and conventional cardiovascular risk factors to predict 8 years fatal and non-fatal cardiovascular events.As one of the 5 hospitals chosen in the UK, we performed an interim analysis to assess the impact of the proposed new chest pain pathway on the risk stratification of patients referred for suspected angina to the Rapid Access Chest Pain Clinic (RACPC). Objective: We investigated the interaction (risk stratification predictive power) between the degree of coronary artery disease (CAD), the FAI risk score and the AI-based CariHeart Risk score. Methods: 135 consecutive patients referred to the RACPC were part of this analysis. 2 patients had no contrast CCTA images at patient request and were excluded. Risk stratification was defined as no or mild CAD (<50% stenosis), moderate, (50–69% stenosis) or severe (>70% stenosis) based on the degree or coronary artery luminal stenosis, a low FAI score defined as less than the 50 percentile for any coronary artery, intermediate FAI score defined as the 50–75 percentile for LAD/RCA or 50–90 percentile for LCX, and high FAI score defined as the >75 percentile for LAD/RCA and >90 percentile for LCX.Low AI-CariHeart risk score was defined as <1% 8 year’ CV mortality, intermediate risk as 1-5% CV mortality, and high risk as >5% CV mortality. Results: We found that patients with no or mild atherosclerotic CAD had a low FAI score in 4/114 (3.5%) cases; intermediate score in 16/114 (14%) cases; and high score in 94/114 (82%) cases (p<0.00001).Low CariHeart risk score was found in 4 (3.6%), intermediate risk score in 47 (41%), and high-risk score in 63 (55%) patients (p<0.0001).In no-or mild CAD patients, the FAI score identified more patients than did the CariHeart risk score as high risk (82% vs 55%, p<0.0001). However, merging the intermediate and high-FAI score patients and comparing them with the merged intermediate and high CariHeart risk score patients identified the same proportion of patients (97%).A low FAI score was found in none, intermediate score in 38%, and high score in 62% of the 13 patients with moderate CAD on CCTA (p=0.025).A low CariHeart risk score was found in none, intermediate risk score in 8%, and high-risk score in 92% of patients (p<0.007). A high FAI score was found in all 3 cases, whereas a high CariHeart score was found in 2 cases and intermediate in 1 with severe CAD on CCTA. Conclusion: The AI-based new chest pain pathway utilising CCTA images identified a higher proportion of at-risk patients, particularly those with non-obstructive CAD. FAI score and CariHeart risk score appear to perform similarly in the combined intermediate and high-risk groups.Further research into understanding the value of initiation of cardiovascular preventive therapy on outcome and intervention strategies to reduce perivascular inflammation and, hence, cardiovascular death is essential.http://www.sciencedirect.com/science/article/pii/S1470211825001320 |
| spellingShingle | Nerea Sanfeliu Garces Tracy Barnfather Lynne Cooley Barbara Kardos Ahmed Alsinbili Mike Pashler Sudipta Chattopadhyay Attila Kardos Impact of the AI-based CariHeart risk score, using cardiac CT angiography, on the stratification of patients with suspected coronary artery disease: insight from the NHS England Pilot project Clinical Medicine |
| title | Impact of the AI-based CariHeart risk score, using cardiac CT angiography, on the stratification of patients with suspected coronary artery disease: insight from the NHS England Pilot project |
| title_full | Impact of the AI-based CariHeart risk score, using cardiac CT angiography, on the stratification of patients with suspected coronary artery disease: insight from the NHS England Pilot project |
| title_fullStr | Impact of the AI-based CariHeart risk score, using cardiac CT angiography, on the stratification of patients with suspected coronary artery disease: insight from the NHS England Pilot project |
| title_full_unstemmed | Impact of the AI-based CariHeart risk score, using cardiac CT angiography, on the stratification of patients with suspected coronary artery disease: insight from the NHS England Pilot project |
| title_short | Impact of the AI-based CariHeart risk score, using cardiac CT angiography, on the stratification of patients with suspected coronary artery disease: insight from the NHS England Pilot project |
| title_sort | impact of the ai based cariheart risk score using cardiac ct angiography on the stratification of patients with suspected coronary artery disease insight from the nhs england pilot project |
| url | http://www.sciencedirect.com/science/article/pii/S1470211825001320 |
| work_keys_str_mv | AT nereasanfeliugarces impactoftheaibasedcariheartriskscoreusingcardiacctangiographyonthestratificationofpatientswithsuspectedcoronaryarterydiseaseinsightfromthenhsenglandpilotproject AT tracybarnfather impactoftheaibasedcariheartriskscoreusingcardiacctangiographyonthestratificationofpatientswithsuspectedcoronaryarterydiseaseinsightfromthenhsenglandpilotproject AT lynnecooley impactoftheaibasedcariheartriskscoreusingcardiacctangiographyonthestratificationofpatientswithsuspectedcoronaryarterydiseaseinsightfromthenhsenglandpilotproject AT barbarakardos impactoftheaibasedcariheartriskscoreusingcardiacctangiographyonthestratificationofpatientswithsuspectedcoronaryarterydiseaseinsightfromthenhsenglandpilotproject AT ahmedalsinbili impactoftheaibasedcariheartriskscoreusingcardiacctangiographyonthestratificationofpatientswithsuspectedcoronaryarterydiseaseinsightfromthenhsenglandpilotproject AT mikepashler impactoftheaibasedcariheartriskscoreusingcardiacctangiographyonthestratificationofpatientswithsuspectedcoronaryarterydiseaseinsightfromthenhsenglandpilotproject AT sudiptachattopadhyay impactoftheaibasedcariheartriskscoreusingcardiacctangiographyonthestratificationofpatientswithsuspectedcoronaryarterydiseaseinsightfromthenhsenglandpilotproject AT attilakardos impactoftheaibasedcariheartriskscoreusingcardiacctangiographyonthestratificationofpatientswithsuspectedcoronaryarterydiseaseinsightfromthenhsenglandpilotproject |