Predicting Hospital Readmission for Campylobacteriosis from Electronic Health Records: A Machine Learning and Text Mining Perspective
(1) Background: This study investigates influential risk factors for predicting 30-day readmission to hospital for Campylobacter infections (CI). (2) Methods: We linked general practitioner and hospital admission records of 13,006 patients with CI in Wales (1990–2015). An approach called TF-zR (term...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-01-01
|
| Series: | Journal of Personalized Medicine |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2075-4426/12/1/86 |
| _version_ | 1797492809450651648 |
|---|---|
| author | Shang-Ming Zhou Ronan A. Lyons Muhammad A. Rahman Alexander Holborow Sinead Brophy |
| author_facet | Shang-Ming Zhou Ronan A. Lyons Muhammad A. Rahman Alexander Holborow Sinead Brophy |
| author_sort | Shang-Ming Zhou |
| collection | DOAJ |
| description | (1) Background: This study investigates influential risk factors for predicting 30-day readmission to hospital for Campylobacter infections (CI). (2) Methods: We linked general practitioner and hospital admission records of 13,006 patients with CI in Wales (1990–2015). An approach called TF-zR (term frequency-zRelevance) technique was presented to evaluates how relevant a clinical term is to a patient in a cohort characterized by coded health records. The zR is a supervised term-weighting metric to assign weight to a term based on relative frequencies of the term across different classes. Cost-sensitive classifier with swarm optimization and weighted subset learning was integrated to identify influential clinical signals as predictors and optimal model for readmission prediction. (3) Results: From a pool of up to 17,506 variables, 33 most predictive factors were identified, including age, gender, Townsend deprivation quintiles, comorbidities, medications, and procedures. The predictive model predicted readmission with 73% sensitivity and 54% specificity. Variables associated with readmission included male gender, recurrent tonsillitis, non-healing open wounds, operation for in-gown toenails. Cystitis, paracetamol/codeine use, age (21–25), and heliclear triple pack use, were associated with a lower risk of readmission. (4) Conclusions: This study gives a profile of clustered variables that are predictive of readmission associated with campylobacteriosis. |
| first_indexed | 2024-03-10T01:09:03Z |
| format | Article |
| id | doaj.art-238c3add27274cf9ae7959246fe56b6a |
| institution | Directory Open Access Journal |
| issn | 2075-4426 |
| language | English |
| last_indexed | 2024-03-10T01:09:03Z |
| publishDate | 2022-01-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Journal of Personalized Medicine |
| spelling | doaj.art-238c3add27274cf9ae7959246fe56b6a2023-11-23T14:20:19ZengMDPI AGJournal of Personalized Medicine2075-44262022-01-011218610.3390/jpm12010086Predicting Hospital Readmission for Campylobacteriosis from Electronic Health Records: A Machine Learning and Text Mining PerspectiveShang-Ming Zhou0Ronan A. Lyons1Muhammad A. Rahman2Alexander Holborow3Sinead Brophy4Centre for Health Technology, Faculty of Health, University of Plymouth, Plymouth PL4 8AA, UKHealth Data Research UK, Swansea University Medical School, Swansea University, Swansea SA2 8PP, UKDepartment of Computer Science, Cardiff Metropolitan University, Cardiff CF5 2YB, UKSouth West Wales Cancer Centre, Singleton Hospital, Swansea SA2 8QA, UKHealth Data Research UK, Swansea University Medical School, Swansea University, Swansea SA2 8PP, UK(1) Background: This study investigates influential risk factors for predicting 30-day readmission to hospital for Campylobacter infections (CI). (2) Methods: We linked general practitioner and hospital admission records of 13,006 patients with CI in Wales (1990–2015). An approach called TF-zR (term frequency-zRelevance) technique was presented to evaluates how relevant a clinical term is to a patient in a cohort characterized by coded health records. The zR is a supervised term-weighting metric to assign weight to a term based on relative frequencies of the term across different classes. Cost-sensitive classifier with swarm optimization and weighted subset learning was integrated to identify influential clinical signals as predictors and optimal model for readmission prediction. (3) Results: From a pool of up to 17,506 variables, 33 most predictive factors were identified, including age, gender, Townsend deprivation quintiles, comorbidities, medications, and procedures. The predictive model predicted readmission with 73% sensitivity and 54% specificity. Variables associated with readmission included male gender, recurrent tonsillitis, non-healing open wounds, operation for in-gown toenails. Cystitis, paracetamol/codeine use, age (21–25), and heliclear triple pack use, were associated with a lower risk of readmission. (4) Conclusions: This study gives a profile of clustered variables that are predictive of readmission associated with campylobacteriosis.https://www.mdpi.com/2075-4426/12/1/86hospitalisationreadmission<i>Campylobacter</i> infectionsmachine learningtext miningfeature selection |
| spellingShingle | Shang-Ming Zhou Ronan A. Lyons Muhammad A. Rahman Alexander Holborow Sinead Brophy Predicting Hospital Readmission for Campylobacteriosis from Electronic Health Records: A Machine Learning and Text Mining Perspective Journal of Personalized Medicine hospitalisation readmission <i>Campylobacter</i> infections machine learning text mining feature selection |
| title | Predicting Hospital Readmission for Campylobacteriosis from Electronic Health Records: A Machine Learning and Text Mining Perspective |
| title_full | Predicting Hospital Readmission for Campylobacteriosis from Electronic Health Records: A Machine Learning and Text Mining Perspective |
| title_fullStr | Predicting Hospital Readmission for Campylobacteriosis from Electronic Health Records: A Machine Learning and Text Mining Perspective |
| title_full_unstemmed | Predicting Hospital Readmission for Campylobacteriosis from Electronic Health Records: A Machine Learning and Text Mining Perspective |
| title_short | Predicting Hospital Readmission for Campylobacteriosis from Electronic Health Records: A Machine Learning and Text Mining Perspective |
| title_sort | predicting hospital readmission for campylobacteriosis from electronic health records a machine learning and text mining perspective |
| topic | hospitalisation readmission <i>Campylobacter</i> infections machine learning text mining feature selection |
| url | https://www.mdpi.com/2075-4426/12/1/86 |
| work_keys_str_mv | AT shangmingzhou predictinghospitalreadmissionforcampylobacteriosisfromelectronichealthrecordsamachinelearningandtextminingperspective AT ronanalyons predictinghospitalreadmissionforcampylobacteriosisfromelectronichealthrecordsamachinelearningandtextminingperspective AT muhammadarahman predictinghospitalreadmissionforcampylobacteriosisfromelectronichealthrecordsamachinelearningandtextminingperspective AT alexanderholborow predictinghospitalreadmissionforcampylobacteriosisfromelectronichealthrecordsamachinelearningandtextminingperspective AT sineadbrophy predictinghospitalreadmissionforcampylobacteriosisfromelectronichealthrecordsamachinelearningandtextminingperspective |