Predictive model for a second hip fracture occurrence using natural language processing and machine learning on electronic health records
Abstract Hip fractures (HFx) are associated with a higher morbidity and mortality rates, leading to a significant reduction in life quality and in limitation of patient´s mobility. The present study aimed to obtain real-world evidence on the clinical characteristics of patients with an initial and a...
| Main Authors: | , , , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Nature Portfolio
2024-01-01
|
| Series: | Scientific Reports |
| Online Access: | https://doi.org/10.1038/s41598-023-50762-5 |
| _version_ | 1797363304274853888 |
|---|---|
| author | Ricardo Larrainzar-Garijo Esther Fernández-Tormos Carlos Alberto Collado-Escudero María Alcantud Ibáñez Fernando Oñorbe-San Francisco Judith Marin-Corral David Casadevall David Donaire-Gonzalez Luisa Martínez-Sanchez Lucia Cabal-Hierro Diego Benavent Fátima Brañas |
| author_facet | Ricardo Larrainzar-Garijo Esther Fernández-Tormos Carlos Alberto Collado-Escudero María Alcantud Ibáñez Fernando Oñorbe-San Francisco Judith Marin-Corral David Casadevall David Donaire-Gonzalez Luisa Martínez-Sanchez Lucia Cabal-Hierro Diego Benavent Fátima Brañas |
| author_sort | Ricardo Larrainzar-Garijo |
| collection | DOAJ |
| description | Abstract Hip fractures (HFx) are associated with a higher morbidity and mortality rates, leading to a significant reduction in life quality and in limitation of patient´s mobility. The present study aimed to obtain real-world evidence on the clinical characteristics of patients with an initial and a second hip fracture (HFx) and develop a predictive model for second HFx using artificial intelligence. Electronic health records from one hospital centre in Spain from January 2011 to December 2019 were analysed using EHRead® technology, based on natural language processing and machine learning. A total of 1,960 patients with HFx were finally included during the study period after meeting all inclusion and exclusion criteria. From this total, 1835 (93.6%) patients were included in the HFx subgroup, while 124 (6.4%) were admitted to the second HFx (2HFx) subgroup. The mean age of the participants was 84 years and 75.5% were female. Most of comorbidities were more frequently identified in the HFx group, including hypertension (72.0% vs. 67.2%), cognitive impairment (33.0% vs. 31.2%), diabetes mellitus (28.7% vs. 24.8%), heart failure (27.6% vs. 22.4%) and chronic kidney disease (26.9% vs. 16.0%). Based on clinical criteria, 26 features were selected as potential prediction factors. From there, 16 demographics and clinical characteristics such as comorbidities, medications, measures of disabilities for ambulation and type of refracture were selected for development of a competitive risk model. Specifically, those predictors with different associated risk ratios, sorted from higher to lower risk relevance were visual deficit, malnutrition, walking assistance, hypothyroidism, female sex, osteoporosis treatment, pertrochanteric fracture, dementia, age at index, osteoporosis, renal failure, stroke, COPD, heart disease, anaemia, and asthma. This model showed good performance (dependent AUC: 0.69; apparent performance: 0.75) and could help the identification of patients with higher risk of developing a second HFx, allowing preventive measures. This study expands the current available information of HFx patients in Spain and identifies factors that exhibit potential in predicting a second HFx among older patients. |
| first_indexed | 2024-03-08T16:19:26Z |
| format | Article |
| id | doaj.art-72a4b825900347b28f139e6d05187f37 |
| institution | Directory Open Access Journal |
| issn | 2045-2322 |
| language | English |
| last_indexed | 2024-03-08T16:19:26Z |
| publishDate | 2024-01-01 |
| publisher | Nature Portfolio |
| record_format | Article |
| series | Scientific Reports |
| spelling | doaj.art-72a4b825900347b28f139e6d05187f372024-01-07T12:27:12ZengNature PortfolioScientific Reports2045-23222024-01-0114111010.1038/s41598-023-50762-5Predictive model for a second hip fracture occurrence using natural language processing and machine learning on electronic health recordsRicardo Larrainzar-Garijo0Esther Fernández-Tormos1Carlos Alberto Collado-Escudero2María Alcantud Ibáñez3Fernando Oñorbe-San Francisco4Judith Marin-Corral5David Casadevall6David Donaire-Gonzalez7Luisa Martínez-Sanchez8Lucia Cabal-Hierro9Diego Benavent10Fátima Brañas11Orthopedic and Trauma Department, Hospital Universitario Infanta Leonor, Medical School, Universidad ComplutenseOrthopedic and Trauma Department, Hospital Universitario Infanta LeonorOrthopedic and Trauma Department, Hospital Universitario Infanta LeonorGeriatric Department, Hospital Universitario Infanta Leonor, Medical School, Universidad ComplutenseOrthopedic and Trauma Department, Hospital Universitario Infanta LeonorSavana Research Group: Medsavana & Savana Research S.L.Savana Research Group: Medsavana & Savana Research S.L.Savana Research Group: Medsavana & Savana Research S.L.Savana Research Group: Medsavana & Savana Research S.L.Savana Research Group: Medsavana & Savana Research S.L.Savana Research Group: Medsavana & Savana Research S.L.Geriatric Department, Hospital Universitario Infanta Leonor, Medical School, Universidad ComplutenseAbstract Hip fractures (HFx) are associated with a higher morbidity and mortality rates, leading to a significant reduction in life quality and in limitation of patient´s mobility. The present study aimed to obtain real-world evidence on the clinical characteristics of patients with an initial and a second hip fracture (HFx) and develop a predictive model for second HFx using artificial intelligence. Electronic health records from one hospital centre in Spain from January 2011 to December 2019 were analysed using EHRead® technology, based on natural language processing and machine learning. A total of 1,960 patients with HFx were finally included during the study period after meeting all inclusion and exclusion criteria. From this total, 1835 (93.6%) patients were included in the HFx subgroup, while 124 (6.4%) were admitted to the second HFx (2HFx) subgroup. The mean age of the participants was 84 years and 75.5% were female. Most of comorbidities were more frequently identified in the HFx group, including hypertension (72.0% vs. 67.2%), cognitive impairment (33.0% vs. 31.2%), diabetes mellitus (28.7% vs. 24.8%), heart failure (27.6% vs. 22.4%) and chronic kidney disease (26.9% vs. 16.0%). Based on clinical criteria, 26 features were selected as potential prediction factors. From there, 16 demographics and clinical characteristics such as comorbidities, medications, measures of disabilities for ambulation and type of refracture were selected for development of a competitive risk model. Specifically, those predictors with different associated risk ratios, sorted from higher to lower risk relevance were visual deficit, malnutrition, walking assistance, hypothyroidism, female sex, osteoporosis treatment, pertrochanteric fracture, dementia, age at index, osteoporosis, renal failure, stroke, COPD, heart disease, anaemia, and asthma. This model showed good performance (dependent AUC: 0.69; apparent performance: 0.75) and could help the identification of patients with higher risk of developing a second HFx, allowing preventive measures. This study expands the current available information of HFx patients in Spain and identifies factors that exhibit potential in predicting a second HFx among older patients.https://doi.org/10.1038/s41598-023-50762-5 |
| spellingShingle | Ricardo Larrainzar-Garijo Esther Fernández-Tormos Carlos Alberto Collado-Escudero María Alcantud Ibáñez Fernando Oñorbe-San Francisco Judith Marin-Corral David Casadevall David Donaire-Gonzalez Luisa Martínez-Sanchez Lucia Cabal-Hierro Diego Benavent Fátima Brañas Predictive model for a second hip fracture occurrence using natural language processing and machine learning on electronic health records Scientific Reports |
| title | Predictive model for a second hip fracture occurrence using natural language processing and machine learning on electronic health records |
| title_full | Predictive model for a second hip fracture occurrence using natural language processing and machine learning on electronic health records |
| title_fullStr | Predictive model for a second hip fracture occurrence using natural language processing and machine learning on electronic health records |
| title_full_unstemmed | Predictive model for a second hip fracture occurrence using natural language processing and machine learning on electronic health records |
| title_short | Predictive model for a second hip fracture occurrence using natural language processing and machine learning on electronic health records |
| title_sort | predictive model for a second hip fracture occurrence using natural language processing and machine learning on electronic health records |
| url | https://doi.org/10.1038/s41598-023-50762-5 |
| work_keys_str_mv | AT ricardolarrainzargarijo predictivemodelforasecondhipfractureoccurrenceusingnaturallanguageprocessingandmachinelearningonelectronichealthrecords AT estherfernandeztormos predictivemodelforasecondhipfractureoccurrenceusingnaturallanguageprocessingandmachinelearningonelectronichealthrecords AT carlosalbertocolladoescudero predictivemodelforasecondhipfractureoccurrenceusingnaturallanguageprocessingandmachinelearningonelectronichealthrecords AT mariaalcantudibanez predictivemodelforasecondhipfractureoccurrenceusingnaturallanguageprocessingandmachinelearningonelectronichealthrecords AT fernandoonorbesanfrancisco predictivemodelforasecondhipfractureoccurrenceusingnaturallanguageprocessingandmachinelearningonelectronichealthrecords AT judithmarincorral predictivemodelforasecondhipfractureoccurrenceusingnaturallanguageprocessingandmachinelearningonelectronichealthrecords AT davidcasadevall predictivemodelforasecondhipfractureoccurrenceusingnaturallanguageprocessingandmachinelearningonelectronichealthrecords AT daviddonairegonzalez predictivemodelforasecondhipfractureoccurrenceusingnaturallanguageprocessingandmachinelearningonelectronichealthrecords AT luisamartinezsanchez predictivemodelforasecondhipfractureoccurrenceusingnaturallanguageprocessingandmachinelearningonelectronichealthrecords AT luciacabalhierro predictivemodelforasecondhipfractureoccurrenceusingnaturallanguageprocessingandmachinelearningonelectronichealthrecords AT diegobenavent predictivemodelforasecondhipfractureoccurrenceusingnaturallanguageprocessingandmachinelearningonelectronichealthrecords AT fatimabranas predictivemodelforasecondhipfractureoccurrenceusingnaturallanguageprocessingandmachinelearningonelectronichealthrecords |