Natural language processing to automate a web-based model of care and modernize skin cancer multidisciplinary team meetings
© The Author(s) 2024. Published by Oxford University Press on behalf of BJS Foundation Ltd..
BACKGROUND: Cancer multidisciplinary team (MDT) meetings are under intense pressure to reform given the rapidly rising incidence of cancer and national mandates for protocolized streaming of cases. The aim of this study was to validate a natural language processing (NLP)-based web platform to automate evidence-based MDT decisions for skin cancer with basal cell carcinoma as a use case.
METHODS: A novel and validated NLP information extraction model was used to extract perioperative tumour and surgical factors from histopathology reports. A web application with a bespoke application programming interface used data from this model to provide an automated clinical decision support system, mapped to national guidelines and generating a patient letter to communicate ongoing management. Performance was assessed against retrospectively derived recommendations by two independent and blinded expert clinicians.
RESULTS: There were 893 patients (1045 lesions) used to internally validate the model. High accuracy was observed when compared against human predictions, with an overall value of 0.92. Across all classifiers the virtual skin MDT was highly specific (0.96), while sensitivity was lower (0.72).
CONCLUSION: This study demonstrates the feasibility of a fully automated, virtual, web-based service model to host the skin MDT with good system performance. This platform could be used to support clinical decision-making during MDTs as 'human in the loop' approach to aid protocolized streaming. Future prospective studies are needed to validate the model in tumour types where guidelines are more complex.
| Medienart: |
E-Artikel |
|---|
| Erscheinungsjahr: |
2024 |
|---|---|
| Erschienen: |
2024 |
| Enthalten in: |
Zur Gesamtaufnahme - volume:111 |
|---|---|
| Enthalten in: |
The British journal of surgery - 111(2024), 1 vom: 03. Jan. |
| Sprache: |
Englisch |
|---|
| Beteiligte Personen: |
Ali, Stephen R [VerfasserIn] |
|---|
| Links: |
|---|
| Themen: |
|---|
| Anmerkungen: |
Date Completed 11.01.2024 Date Revised 06.03.2024 published: Print Citation Status MEDLINE |
|---|
| doi: |
10.1093/bjs/znad347 |
|---|
| funding: |
|
|---|---|
| Förderinstitution / Projekttitel: |
|
| PPN (Katalog-ID): |
NLM366887440 |
|---|
| LEADER | 01000caa a22002652 4500 | ||
|---|---|---|---|
| 001 | NLM366887440 | ||
| 003 | DE-627 | ||
| 005 | 20240306232712.0 | ||
| 007 | cr uuu---uuuuu | ||
| 008 | 240114s2024 xx |||||o 00| ||eng c | ||
| 024 | 7 | |a 10.1093/bjs/znad347 |2 doi | |
| 028 | 5 | 2 | |a pubmed24n1318.xml |
| 035 | |a (DE-627)NLM366887440 | ||
| 035 | |a (NLM)38198154 | ||
| 035 | |a (PII)znad347 | ||
| 040 | |a DE-627 |b ger |c DE-627 |e rakwb | ||
| 041 | |a eng | ||
| 100 | 1 | |a Ali, Stephen R |e verfasserin |4 aut | |
| 245 | 1 | 0 | |a Natural language processing to automate a web-based model of care and modernize skin cancer multidisciplinary team meetings |
| 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 11.01.2024 | ||
| 500 | |a Date Revised 06.03.2024 | ||
| 500 | |a published: Print | ||
| 500 | |a Citation Status MEDLINE | ||
| 520 | |a © The Author(s) 2024. Published by Oxford University Press on behalf of BJS Foundation Ltd. | ||
| 520 | |a BACKGROUND: Cancer multidisciplinary team (MDT) meetings are under intense pressure to reform given the rapidly rising incidence of cancer and national mandates for protocolized streaming of cases. The aim of this study was to validate a natural language processing (NLP)-based web platform to automate evidence-based MDT decisions for skin cancer with basal cell carcinoma as a use case | ||
| 520 | |a METHODS: A novel and validated NLP information extraction model was used to extract perioperative tumour and surgical factors from histopathology reports. A web application with a bespoke application programming interface used data from this model to provide an automated clinical decision support system, mapped to national guidelines and generating a patient letter to communicate ongoing management. Performance was assessed against retrospectively derived recommendations by two independent and blinded expert clinicians | ||
| 520 | |a RESULTS: There were 893 patients (1045 lesions) used to internally validate the model. High accuracy was observed when compared against human predictions, with an overall value of 0.92. Across all classifiers the virtual skin MDT was highly specific (0.96), while sensitivity was lower (0.72) | ||
| 520 | |a CONCLUSION: This study demonstrates the feasibility of a fully automated, virtual, web-based service model to host the skin MDT with good system performance. This platform could be used to support clinical decision-making during MDTs as 'human in the loop' approach to aid protocolized streaming. Future prospective studies are needed to validate the model in tumour types where guidelines are more complex | ||
| 650 | 4 | |a Journal Article | |
| 700 | 1 | |a Dobbs, Thomas D |e verfasserin |4 aut | |
| 700 | 1 | |a Tarafdar, Adib |e verfasserin |4 aut | |
| 700 | 1 | |a Strafford, Huw |e verfasserin |4 aut | |
| 700 | 1 | |a Fonferko-Shadrach, Beata |e verfasserin |4 aut | |
| 700 | 1 | |a Lacey, Arron S |e verfasserin |4 aut | |
| 700 | 1 | |a Pickrell, William Owen |e verfasserin |4 aut | |
| 700 | 1 | |a Hutchings, Hayley A |e verfasserin |4 aut | |
| 700 | 1 | |a Whitaker, Iain S |e verfasserin |4 aut | |
| 773 | 0 | 8 | |i Enthalten in |t The British journal of surgery |d 1945 |g 111(2024), 1 vom: 03. Jan. |w (DE-627)NLM000001465 |x 1365-2168 |7 nnns |
| 773 | 1 | 8 | |g volume:111 |g year:2024 |g number:1 |g day:03 |g month:01 |
| 856 | 4 | 0 | |u http://dx.doi.org/10.1093/bjs/znad347 |3 Volltext |
| 912 | |a GBV_USEFLAG_A | ||
| 912 | |a GBV_NLM | ||
| 951 | |a AR | ||
| 952 | |d 111 |j 2024 |e 1 |b 03 |c 01 | ||