Machine learning identification of thresholds to discriminate osteoarthritis and rheumatoid arthritis synovial inflammation
© 2023. The Author(s)..
BACKGROUND: We sought to identify features that distinguish osteoarthritis (OA) and rheumatoid arthritis (RA) hematoxylin and eosin (H&E)-stained synovial tissue samples.
METHODS: We compared fourteen pathologist-scored histology features and computer vision-quantified cell density (147 OA and 60 RA patients) in H&E-stained synovial tissue samples from total knee replacement (TKR) explants. A random forest model was trained using disease state (OA vs RA) as a classifier and histology features and/or computer vision-quantified cell density as inputs.
RESULTS: Synovium from OA patients had increased mast cells and fibrosis (p < 0.001), while synovium from RA patients exhibited increased lymphocytic inflammation, lining hyperplasia, neutrophils, detritus, plasma cells, binucleate plasma cells, sub-lining giant cells, fibrin (all p < 0.001), Russell bodies (p = 0.019), and synovial lining giant cells (p = 0.003). Fourteen pathologist-scored features allowed for discrimination between OA and RA, producing a micro-averaged area under the receiver operating curve (micro-AUC) of 0.85±0.06. This discriminatory ability was comparable to that of computer vision cell density alone (micro-AUC = 0.87±0.04). Combining the pathologist scores with the cell density metric improved the discriminatory power of the model (micro-AUC = 0.92±0.06). The optimal cell density threshold to distinguish OA from RA synovium was 3400 cells/mm2, which yielded a sensitivity of 0.82 and specificity of 0.82.
CONCLUSIONS: H&E-stained images of TKR explant synovium can be correctly classified as OA or RA in 82% of samples. Cell density greater than 3400 cells/mm2 and the presence of mast cells and fibrosis are the most important features for making this distinction.
| Medienart: |
E-Artikel |
|---|
| Erscheinungsjahr: |
2023 |
|---|---|
| Erschienen: |
2023 |
| Enthalten in: |
Zur Gesamtaufnahme - volume:25 |
|---|---|
| Enthalten in: |
Arthritis research & therapy - 25(2023), 1 vom: 02. März, Seite 31 |
| Sprache: |
Englisch |
|---|
| Beteiligte Personen: |
Mehta, Bella [VerfasserIn] |
|---|
| Links: |
|---|
| Themen: |
Histology |
|---|
| Anmerkungen: |
Date Completed 06.03.2023 Date Revised 25.04.2024 published: Electronic Citation Status MEDLINE |
|---|
| doi: |
10.1186/s13075-023-03008-8 |
|---|
| funding: |
|
|---|---|
| Förderinstitution / Projekttitel: |
|
| PPN (Katalog-ID): |
NLM353703931 |
|---|
| LEADER | 01000caa a22002652 4500 | ||
|---|---|---|---|
| 001 | NLM353703931 | ||
| 003 | DE-627 | ||
| 005 | 20240425232209.0 | ||
| 007 | cr uuu---uuuuu | ||
| 008 | 231226s2023 xx |||||o 00| ||eng c | ||
| 024 | 7 | |a 10.1186/s13075-023-03008-8 |2 doi | |
| 028 | 5 | 2 | |a pubmed24n1386.xml |
| 035 | |a (DE-627)NLM353703931 | ||
| 035 | |a (NLM)36864474 | ||
| 040 | |a DE-627 |b ger |c DE-627 |e rakwb | ||
| 041 | |a eng | ||
| 100 | 1 | |a Mehta, Bella |e verfasserin |4 aut | |
| 245 | 1 | 0 | |a Machine learning identification of thresholds to discriminate osteoarthritis and rheumatoid arthritis synovial inflammation |
| 264 | 1 | |c 2023 | |
| 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 06.03.2023 | ||
| 500 | |a Date Revised 25.04.2024 | ||
| 500 | |a published: Electronic | ||
| 500 | |a Citation Status MEDLINE | ||
| 520 | |a © 2023. The Author(s). | ||
| 520 | |a BACKGROUND: We sought to identify features that distinguish osteoarthritis (OA) and rheumatoid arthritis (RA) hematoxylin and eosin (H&E)-stained synovial tissue samples | ||
| 520 | |a METHODS: We compared fourteen pathologist-scored histology features and computer vision-quantified cell density (147 OA and 60 RA patients) in H&E-stained synovial tissue samples from total knee replacement (TKR) explants. A random forest model was trained using disease state (OA vs RA) as a classifier and histology features and/or computer vision-quantified cell density as inputs | ||
| 520 | |a RESULTS: Synovium from OA patients had increased mast cells and fibrosis (p < 0.001), while synovium from RA patients exhibited increased lymphocytic inflammation, lining hyperplasia, neutrophils, detritus, plasma cells, binucleate plasma cells, sub-lining giant cells, fibrin (all p < 0.001), Russell bodies (p = 0.019), and synovial lining giant cells (p = 0.003). Fourteen pathologist-scored features allowed for discrimination between OA and RA, producing a micro-averaged area under the receiver operating curve (micro-AUC) of 0.85±0.06. This discriminatory ability was comparable to that of computer vision cell density alone (micro-AUC = 0.87±0.04). Combining the pathologist scores with the cell density metric improved the discriminatory power of the model (micro-AUC = 0.92±0.06). The optimal cell density threshold to distinguish OA from RA synovium was 3400 cells/mm2, which yielded a sensitivity of 0.82 and specificity of 0.82 | ||
| 520 | |a CONCLUSIONS: H&E-stained images of TKR explant synovium can be correctly classified as OA or RA in 82% of samples. Cell density greater than 3400 cells/mm2 and the presence of mast cells and fibrosis are the most important features for making this distinction | ||
| 650 | 4 | |a Journal Article | |
| 650 | 4 | |a Research Support, Non-U.S. Gov't | |
| 650 | 4 | |a Histology | |
| 650 | 4 | |a Machine learning | |
| 650 | 4 | |a Osteoarthritis | |
| 650 | 4 | |a Rheumatoid arthritis | |
| 650 | 4 | |a Synovial inflammation | |
| 700 | 1 | |a Goodman, Susan |e verfasserin |4 aut | |
| 700 | 1 | |a DiCarlo, Edward |e verfasserin |4 aut | |
| 700 | 1 | |a Jannat-Khah, Deanna |e verfasserin |4 aut | |
| 700 | 1 | |a Gibbons, J Alex B |e verfasserin |4 aut | |
| 700 | 1 | |a Otero, Miguel |e verfasserin |4 aut | |
| 700 | 1 | |a Donlin, Laura |e verfasserin |4 aut | |
| 700 | 1 | |a Pannellini, Tania |e verfasserin |4 aut | |
| 700 | 1 | |a Robinson, William H |e verfasserin |4 aut | |
| 700 | 1 | |a Sculco, Peter |e verfasserin |4 aut | |
| 700 | 1 | |a Figgie, Mark |e verfasserin |4 aut | |
| 700 | 1 | |a Rodriguez, Jose |e verfasserin |4 aut | |
| 700 | 1 | |a Kirschmann, Jessica M |e verfasserin |4 aut | |
| 700 | 1 | |a Thompson, James |e verfasserin |4 aut | |
| 700 | 1 | |a Slater, David |e verfasserin |4 aut | |
| 700 | 1 | |a Frezza, Damon |e verfasserin |4 aut | |
| 700 | 1 | |a Xu, Zhenxing |e verfasserin |4 aut | |
| 700 | 1 | |a Wang, Fei |e verfasserin |4 aut | |
| 700 | 1 | |a Orange, Dana E |e verfasserin |4 aut | |
| 773 | 0 | 8 | |i Enthalten in |t Arthritis research & therapy |d 2003 |g 25(2023), 1 vom: 02. März, Seite 31 |w (DE-627)NLM124870457 |x 1478-6362 |7 nnns |
| 773 | 1 | 8 | |g volume:25 |g year:2023 |g number:1 |g day:02 |g month:03 |g pages:31 |
| 856 | 4 | 0 | |u http://dx.doi.org/10.1186/s13075-023-03008-8 |3 Volltext |
| 912 | |a GBV_USEFLAG_A | ||
| 912 | |a GBV_NLM | ||
| 951 | |a AR | ||
| 952 | |d 25 |j 2023 |e 1 |b 02 |c 03 |h 31 | ||