Deep learning predicts microsatellite instability status in colorectal carcinoma in an ethnically heterogeneous population in South Africa
Background Deep learning (DL) models are effective pre-screening tools for detecting mismatch repair deficiency (dMMR) in colorectal carcinoma (CRC). These models have been trained and validated on large cohorts from the Northern Hemisphere, without representation of African samples. We sought to de...
Gespeichert in:
| Hauptverfasser: | , , , , , , , , , |
|---|---|
| Dokumenttyp: | Article (Journal) |
| Sprache: | Englisch |
| Veröffentlicht: |
20 May 2025
|
| In: |
Journal of clinical pathology
Year: 2025, Jahrgang: 79, Heft: 1, Pages: 50-56 |
| ISSN: | 1472-4146 |
| DOI: | 10.1136/jcp-2025-210053 |
| Online-Zugang: | Verlag, lizenzpflichtig, Volltext: https://doi.org/10.1136/jcp-2025-210053 Verlag, lizenzpflichtig, Volltext: https://jcp.bmj.com/content/early/2025/05/20/jcp-2025-210053 
|
| Verfasserangaben: | Alessandro Pietro Aldera, Didem Cifci, Gregory Patrick Veldhuizen, Wan-Jung Tsai, Komala Pillay, Adam Boutall, Hermann Brenner, Michael Hoffmeister, Jakob Nikolas Kather, Raj Ramesar |
MARC
| LEADER | 00000caa a2200000 c 4500 | ||
|---|---|---|---|
| 001 | 1940485819 | ||
| 003 | DE-627 | ||
| 005 | 20260112123806.0 | ||
| 007 | cr uuu---uuuuu | ||
| 008 | 251106s2025 xx |||||o 00| ||eng c | ||
| 024 | 7 | |a 10.1136/jcp-2025-210053 |2 doi | |
| 035 | |a (DE-627)1940485819 | ||
| 035 | |a (DE-599)KXP1940485819 | ||
| 035 | |a (OCoLC)1559714141 | ||
| 040 | |a DE-627 |b ger |c DE-627 |e rda | ||
| 041 | |a eng | ||
| 084 | |a 33 |2 sdnb | ||
| 100 | 1 | |a Aldera, Alessandro Pietro |e VerfasserIn |0 (DE-588)138092202X |0 (DE-627)1940487196 |4 aut | |
| 245 | 1 | 0 | |a Deep learning predicts microsatellite instability status in colorectal carcinoma in an ethnically heterogeneous population in South Africa |c Alessandro Pietro Aldera, Didem Cifci, Gregory Patrick Veldhuizen, Wan-Jung Tsai, Komala Pillay, Adam Boutall, Hermann Brenner, Michael Hoffmeister, Jakob Nikolas Kather, Raj Ramesar |
| 264 | 1 | |c 20 May 2025 | |
| 300 | |b Illustrationen, Diagramme | ||
| 300 | |a 7 | ||
| 336 | |a Text |b txt |2 rdacontent | ||
| 337 | |a Computermedien |b c |2 rdamedia | ||
| 338 | |a Online-Ressource |b cr |2 rdacarrier | ||
| 500 | |a Gesehen am 06.11.2025 | ||
| 520 | |a Background Deep learning (DL) models are effective pre-screening tools for detecting mismatch repair deficiency (dMMR) in colorectal carcinoma (CRC). These models have been trained and validated on large cohorts from the Northern Hemisphere, without representation of African samples. We sought to determine the performance of a DL model in an ethnically heterogeneous cohort of patients from South Africa. - Methods Our cohort comprised 197 CRC resection specimens, with scanned whole slide images tessellated and inputted into a transformer-based DL model trained on large international cohorts. Model performance was evaluated using area under the receiver operating characteristic curve (AUROC), sensitivity and specificity. The maximal Youden’s J index was calculated to determine the optimal cut-off threshold for the model prediction score. - Results Our model yielded an AUROC of 0.91 (±0.05). Using a prediction score threshold of 0.620 produced an overall sensitivity of 85.7% (95% CI 73.3% to 92.9%) and a specificity of 82.4% (95% CI 75.5% to 87.7%). The false negative cases were predominantly left-sided (71.4%) and did not show the typical dMMR/microsatellite instability-high histological phenotype. Sensitivity was lower (50%-75%) in cases showing isolated PMS2 or MSH6 loss of staining. Calibrating the classification threshold to 0.470, the sensitivity was optimised to 95.6% (95% CI 86.3% to 98.9%) with a specificity of 69.6% (95% CI 61.8% to 76.4%). This would have resulted in excluding 103 cases (52.3%) from downstream immunohistochemical (IHC) or molecular testing. - Conclusions Following appropriate region-specific calibration, we have shown that this model could be employed to accurately prescreen for dMMR in CRC, thereby reducing the burden of downstream IHC and molecular testing in a resource-limited setting. | ||
| 650 | 4 | |a Artificial Intelligence | |
| 650 | 4 | |a Colorectal Neoplasms | |
| 650 | 4 | |a Medical Oncology | |
| 650 | 4 | |a Neoplastic Syndromes, Hereditary | |
| 700 | 1 | |a Cifci, Didem |e VerfasserIn |4 aut | |
| 700 | 1 | |a Veldhuizen, Gregory Patrick |e VerfasserIn |4 aut | |
| 700 | 1 | |a Tsai, Wan-Jung |e VerfasserIn |4 aut | |
| 700 | 1 | |a Pillay, Komala |e VerfasserIn |4 aut | |
| 700 | 1 | |a Boutall, Adam |e VerfasserIn |4 aut | |
| 700 | 1 | |a Brenner, Hermann |e VerfasserIn |0 (DE-588)1020516445 |0 (DE-627)691247005 |0 (DE-576)360642136 |4 aut | |
| 700 | 1 | |a Hoffmeister, Michael |e VerfasserIn |4 aut | |
| 700 | 1 | |a Kather, Jakob Nikolas |d 1989- |e VerfasserIn |0 (DE-588)1064064914 |0 (DE-627)812897587 |0 (DE-576)423589091 |4 aut | |
| 700 | 1 | |a Ramesar, Raj |e VerfasserIn |4 aut | |
| 773 | 0 | 8 | |i Enthalten in |t Journal of clinical pathology |d London : BMJ Publ. Group, 1947 |g 79(2025), 1, Seite 50-56 |h Online-Ressource |w (DE-627)324614969 |w (DE-600)2028928-5 |w (DE-576)094505659 |x 1472-4146 |7 nnas |a Deep learning predicts microsatellite instability status in colorectal carcinoma in an ethnically heterogeneous population in South Africa |
| 773 | 1 | 8 | |g volume:79 |g year:2025 |g number:1 |g pages:50-56 |g extent:7 |a Deep learning predicts microsatellite instability status in colorectal carcinoma in an ethnically heterogeneous population in South Africa |
| 856 | 4 | 0 | |u https://doi.org/10.1136/jcp-2025-210053 |x Verlag |x Resolving-System |z lizenzpflichtig |3 Volltext |7 1 |
| 856 | 4 | 0 | |u https://jcp.bmj.com/content/early/2025/05/20/jcp-2025-210053 |x Verlag |z lizenzpflichtig |3 Volltext |7 1 |
| 951 | |a AR | ||
| 992 | |a 20251106 | ||
| 993 | |a Article | ||
| 994 | |a 2025 | ||
| 998 | |g 1064064914 |a Kather, Jakob Nikolas |m 1064064914:Kather, Jakob Nikolas |d 910000 |d 910100 |e 910000PK1064064914 |e 910100PK1064064914 |k 0/910000/ |k 1/910000/910100/ |p 9 | ||
| 998 | |g 1020516445 |a Brenner, Hermann |m 1020516445:Brenner, Hermann |d 850000 |d 851600 |d 50000 |e 850000PB1020516445 |e 851600PB1020516445 |e 50000PB1020516445 |k 0/850000/ |k 1/850000/851600/ |k 0/50000/ |p 7 | ||
| 999 | |a KXP-PPN1940485819 |e 4797616121 | ||
| BIB | |a Y | ||
| SER | |a journal | ||
| JSO | |a {"title":[{"title_sort":"Deep learning predicts microsatellite instability status in colorectal carcinoma in an ethnically heterogeneous population in South Africa","title":"Deep learning predicts microsatellite instability status in colorectal carcinoma in an ethnically heterogeneous population in South Africa"}],"origin":[{"dateIssuedDisp":"20 May 2025","dateIssuedKey":"2025"}],"note":["Gesehen am 06.11.2025"],"type":{"media":"Online-Ressource","bibl":"article-journal"},"physDesc":[{"noteIll":"Illustrationen, Diagramme","extent":"7 S."}],"name":{"displayForm":["Alessandro Pietro Aldera, Didem Cifci, Gregory Patrick Veldhuizen, Wan-Jung Tsai, Komala Pillay, Adam Boutall, Hermann Brenner, Michael Hoffmeister, Jakob Nikolas Kather, Raj Ramesar"]},"relHost":[{"recId":"324614969","physDesc":[{"extent":"Online-Ressource"}],"id":{"eki":["324614969"],"zdb":["2028928-5"],"issn":["1472-4146"]},"title":[{"title":"Journal of clinical pathology","title_sort":"Journal of clinical pathology","subtitle":"JCP ; the scientific journal of the Association of Clinical Pathologists"}],"origin":[{"publisherPlace":"London","publisher":"BMJ Publ. Group","dateIssuedKey":"1947","dateIssuedDisp":"1947-"}],"note":["Gesehen am 02.06.22"],"pubHistory":["1.1947 -"],"type":{"bibl":"periodical","media":"Online-Ressource"},"disp":"Deep learning predicts microsatellite instability status in colorectal carcinoma in an ethnically heterogeneous population in South AfricaJournal of clinical pathology","language":["eng"],"part":{"extent":"7","volume":"79","issue":"1","text":"79(2025), 1, Seite 50-56","year":"2025","pages":"50-56"},"titleAlt":[{"title":"JCP"}],"corporate":[{"display":"Association of Clinical Pathologists","role":"isb"}]}],"recId":"1940485819","id":{"doi":["10.1136/jcp-2025-210053"],"eki":["1940485819"]},"person":[{"role":"aut","given":"Alessandro Pietro","family":"Aldera","display":"Aldera, Alessandro Pietro"},{"family":"Cifci","display":"Cifci, Didem","role":"aut","given":"Didem"},{"role":"aut","given":"Gregory Patrick","family":"Veldhuizen","display":"Veldhuizen, Gregory Patrick"},{"given":"Wan-Jung","role":"aut","display":"Tsai, Wan-Jung","family":"Tsai"},{"display":"Pillay, Komala","family":"Pillay","role":"aut","given":"Komala"},{"given":"Adam","role":"aut","display":"Boutall, Adam","family":"Boutall"},{"family":"Brenner","display":"Brenner, Hermann","role":"aut","given":"Hermann"},{"display":"Hoffmeister, Michael","family":"Hoffmeister","given":"Michael","role":"aut"},{"display":"Kather, Jakob Nikolas","family":"Kather","given":"Jakob Nikolas","role":"aut"},{"family":"Ramesar","display":"Ramesar, Raj","role":"aut","given":"Raj"}],"language":["eng"]} | ||
| SRT | |a ALDERAALESDEEPLEARNI2020 | ||