Predictive model for a second hip fracture occurrence using natural language processing and machine learning on electronic health records.

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.

Risk factors for a second nonsimultaneous hip fracture in a prospective cohort study.

INTRODUCTION: The risk factors for a second nonsimultaneous hip fracture are unclear, and in general, it is empirically assumed that they are similar to those associated with the first hip fracture. We aimed to determine the incidence of a second hip fracture and define the characteristics of the patients sustaining the event in a prospective cohort study in a Spanish population. MATERIALS AND METHODS: We conducted a multicentric, prospective cohort study in a representative sample of 45 hospitals from 15 autonomic regions in Spain. In total, the study included 994 patients. One hundred and one patients presented a nonsimultaneous contralateral hip fracture, constituting the intervention group. The remaining 893 patients presenting with a hip fracture formed the control group. The main outcome measures of this study were sociodemographic characteristics of the patient, comorbid conditions, and baseline and postfracture clinical outcomes (inpatient complications and acute mortality). RESULTS: The key fracture risk factors were a history of fragility fractures, the need for assistance when walking outdoors and a history of falls. There were no associations between the groups in any of the common fragility risk factors, including rheumatoid arthritis, secondary osteoporosis, or steroid consumption. The results showed that patients suffering a nonsimultaneous hip fracture had an increased risk of mortality after discharge compared with the control group. CONCLUSION: A nonsimultaneous second hip fracture leads to a near-significant increase in four-month mortality. In our study, this fracture was associated with a history of falls, prior fragility fractures, and the need for a walking aid.

Infection Due to Saksenaea vasiformis Following a Spider Bite.

Cutaneous mucormycosis due to Saksenaea vasiformis species is exceptional. There have been about 40 reported cases worldwide, with most being fatal. We report an exceptional nonlethal case of mucormycosis due to S. vasiformis following a spider bite. The patient was in an immunosuppressed state owing to previous chemotherapy and diabetes mellitus. The origin of the inoculation was the bite of a Loxosceles laeta spider, which caused loxoscelism. The initial skin injury was quickly progressive, requiring amputation of the right upper limb. After surgical intervention and suitable antifungal treatment, the patient was discharged with resolution of accompanying pulmonary disease. Infections due to S. vasiformis are probably underdiagnosed. To avoid fatal outcomes, a high index of clinical suspicion in patients with quickly progressive necrotic lesions of soft tissues and systemic dissemination is important.