Natural language processing to evaluate texting conversations between patients and healthcare providers during COVID-19 Home-Based Care in Rwanda at scale.
Community isolation of patients with communicable infectious diseases limits spread of pathogens but our understanding of isolated patients' needs and challenges is incomplete. Rwanda deployed a digital health service nationally to assist public health clinicians to remotely monitor and support...
Saved in:
| Main Authors: | , , , , , , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Public Library of Science (PLoS)
2025-01-01
|
| Series: | PLOS Digital Health |
| Online Access: | https://doi.org/10.1371/journal.pdig.0000625 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1850075327317934080 |
|---|---|
| author | Richard T Lester Matthew Manson Muhammed Semakula Hyeju Jang Hassan Mugabo Ali Magzari Junhong Ma Blackmer Fanan Fattah Simon Pierre Niyonsenga Edson Rwagasore Charles Ruranga Eric Remera Jean Claude S Ngabonziza Giuseppe Carenini Sabin Nsanzimana |
| author_facet | Richard T Lester Matthew Manson Muhammed Semakula Hyeju Jang Hassan Mugabo Ali Magzari Junhong Ma Blackmer Fanan Fattah Simon Pierre Niyonsenga Edson Rwagasore Charles Ruranga Eric Remera Jean Claude S Ngabonziza Giuseppe Carenini Sabin Nsanzimana |
| author_sort | Richard T Lester |
| collection | DOAJ |
| description | Community isolation of patients with communicable infectious diseases limits spread of pathogens but our understanding of isolated patients' needs and challenges is incomplete. Rwanda deployed a digital health service nationally to assist public health clinicians to remotely monitor and support SARS-CoV-2 cases via their mobile phones using daily interactive short message service (SMS) check-ins. We aimed to assess the texting patterns and communicated topics to better understand patient experiences. We extracted data on all COVID-19 cases and exposed contacts who were enrolled in the WelTel text messaging program between March 18, 2020, and March 31, 2022, and linked demographic and clinical data from the national COVID-19 registry. A sample of the text conversation corpus was English-translated and labeled with topics of interest defined by medical experts. Multiple natural language processing (NLP) topic classification models were trained and compared using F1 scores. Best performing models were applied to classify unlabeled conversations. Total 33,081 isolated patients (mean age 33·9, range 0-100), 44% female, including 30,398 cases and 2,683 contacts) were registered in WelTel. Registered patients generated 12,119 interactive text conversations in Kinyarwanda (n = 8,183, 67%), English (n = 3,069, 25%) and other languages. Sufficiently trained large language models (LLMs) were unavailable for Kinyarwanda. Traditional machine learning (ML) models outperformed fine-tuned transformer architecture language models on the native untranslated language corpus, however, the reverse was observed of models trained on English-only data. The most frequently identified topics discussed included symptoms (69%), diagnostics (38%), social issues (19%), prevention (18%), healthcare logistics (16%), and treatment (8·5%). Education, advice, and triage on these topics were provided to patients. Interactive text messaging can be used to remotely support isolated patients in pandemics at scale. NLP can help evaluate the medical and social factors that affect isolated patients which could ultimately inform precision public health responses to future pandemics. |
| format | Article |
| id | doaj-art-d6b4884fadf74c05aec52ef452cf356b |
| institution | DOAJ |
| issn | 2767-3170 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | Public Library of Science (PLoS) |
| record_format | Article |
| series | PLOS Digital Health |
| spelling | doaj-art-d6b4884fadf74c05aec52ef452cf356b2025-08-20T02:46:20ZengPublic Library of Science (PLoS)PLOS Digital Health2767-31702025-01-0141e000062510.1371/journal.pdig.0000625Natural language processing to evaluate texting conversations between patients and healthcare providers during COVID-19 Home-Based Care in Rwanda at scale.Richard T LesterMatthew MansonMuhammed SemakulaHyeju JangHassan MugaboAli MagzariJunhong Ma BlackmerFanan FattahSimon Pierre NiyonsengaEdson RwagasoreCharles RurangaEric RemeraJean Claude S NgabonzizaGiuseppe CareniniSabin NsanzimanaCommunity isolation of patients with communicable infectious diseases limits spread of pathogens but our understanding of isolated patients' needs and challenges is incomplete. Rwanda deployed a digital health service nationally to assist public health clinicians to remotely monitor and support SARS-CoV-2 cases via their mobile phones using daily interactive short message service (SMS) check-ins. We aimed to assess the texting patterns and communicated topics to better understand patient experiences. We extracted data on all COVID-19 cases and exposed contacts who were enrolled in the WelTel text messaging program between March 18, 2020, and March 31, 2022, and linked demographic and clinical data from the national COVID-19 registry. A sample of the text conversation corpus was English-translated and labeled with topics of interest defined by medical experts. Multiple natural language processing (NLP) topic classification models were trained and compared using F1 scores. Best performing models were applied to classify unlabeled conversations. Total 33,081 isolated patients (mean age 33·9, range 0-100), 44% female, including 30,398 cases and 2,683 contacts) were registered in WelTel. Registered patients generated 12,119 interactive text conversations in Kinyarwanda (n = 8,183, 67%), English (n = 3,069, 25%) and other languages. Sufficiently trained large language models (LLMs) were unavailable for Kinyarwanda. Traditional machine learning (ML) models outperformed fine-tuned transformer architecture language models on the native untranslated language corpus, however, the reverse was observed of models trained on English-only data. The most frequently identified topics discussed included symptoms (69%), diagnostics (38%), social issues (19%), prevention (18%), healthcare logistics (16%), and treatment (8·5%). Education, advice, and triage on these topics were provided to patients. Interactive text messaging can be used to remotely support isolated patients in pandemics at scale. NLP can help evaluate the medical and social factors that affect isolated patients which could ultimately inform precision public health responses to future pandemics.https://doi.org/10.1371/journal.pdig.0000625 |
| spellingShingle | Richard T Lester Matthew Manson Muhammed Semakula Hyeju Jang Hassan Mugabo Ali Magzari Junhong Ma Blackmer Fanan Fattah Simon Pierre Niyonsenga Edson Rwagasore Charles Ruranga Eric Remera Jean Claude S Ngabonziza Giuseppe Carenini Sabin Nsanzimana Natural language processing to evaluate texting conversations between patients and healthcare providers during COVID-19 Home-Based Care in Rwanda at scale. PLOS Digital Health |
| title | Natural language processing to evaluate texting conversations between patients and healthcare providers during COVID-19 Home-Based Care in Rwanda at scale. |
| title_full | Natural language processing to evaluate texting conversations between patients and healthcare providers during COVID-19 Home-Based Care in Rwanda at scale. |
| title_fullStr | Natural language processing to evaluate texting conversations between patients and healthcare providers during COVID-19 Home-Based Care in Rwanda at scale. |
| title_full_unstemmed | Natural language processing to evaluate texting conversations between patients and healthcare providers during COVID-19 Home-Based Care in Rwanda at scale. |
| title_short | Natural language processing to evaluate texting conversations between patients and healthcare providers during COVID-19 Home-Based Care in Rwanda at scale. |
| title_sort | natural language processing to evaluate texting conversations between patients and healthcare providers during covid 19 home based care in rwanda at scale |
| url | https://doi.org/10.1371/journal.pdig.0000625 |
| work_keys_str_mv | AT richardtlester naturallanguageprocessingtoevaluatetextingconversationsbetweenpatientsandhealthcareprovidersduringcovid19homebasedcareinrwandaatscale AT matthewmanson naturallanguageprocessingtoevaluatetextingconversationsbetweenpatientsandhealthcareprovidersduringcovid19homebasedcareinrwandaatscale AT muhammedsemakula naturallanguageprocessingtoevaluatetextingconversationsbetweenpatientsandhealthcareprovidersduringcovid19homebasedcareinrwandaatscale AT hyejujang naturallanguageprocessingtoevaluatetextingconversationsbetweenpatientsandhealthcareprovidersduringcovid19homebasedcareinrwandaatscale AT hassanmugabo naturallanguageprocessingtoevaluatetextingconversationsbetweenpatientsandhealthcareprovidersduringcovid19homebasedcareinrwandaatscale AT alimagzari naturallanguageprocessingtoevaluatetextingconversationsbetweenpatientsandhealthcareprovidersduringcovid19homebasedcareinrwandaatscale AT junhongmablackmer naturallanguageprocessingtoevaluatetextingconversationsbetweenpatientsandhealthcareprovidersduringcovid19homebasedcareinrwandaatscale AT fananfattah naturallanguageprocessingtoevaluatetextingconversationsbetweenpatientsandhealthcareprovidersduringcovid19homebasedcareinrwandaatscale AT simonpierreniyonsenga naturallanguageprocessingtoevaluatetextingconversationsbetweenpatientsandhealthcareprovidersduringcovid19homebasedcareinrwandaatscale AT edsonrwagasore naturallanguageprocessingtoevaluatetextingconversationsbetweenpatientsandhealthcareprovidersduringcovid19homebasedcareinrwandaatscale AT charlesruranga naturallanguageprocessingtoevaluatetextingconversationsbetweenpatientsandhealthcareprovidersduringcovid19homebasedcareinrwandaatscale AT ericremera naturallanguageprocessingtoevaluatetextingconversationsbetweenpatientsandhealthcareprovidersduringcovid19homebasedcareinrwandaatscale AT jeanclaudesngabonziza naturallanguageprocessingtoevaluatetextingconversationsbetweenpatientsandhealthcareprovidersduringcovid19homebasedcareinrwandaatscale AT giuseppecarenini naturallanguageprocessingtoevaluatetextingconversationsbetweenpatientsandhealthcareprovidersduringcovid19homebasedcareinrwandaatscale AT sabinnsanzimana naturallanguageprocessingtoevaluatetextingconversationsbetweenpatientsandhealthcareprovidersduringcovid19homebasedcareinrwandaatscale |