A survey of patient acceptability of the use of artificial intelligence in the diagnosis of paediatric fractures: an observational study.

INTRODUCTION: This study aimed to assess carer attitudes towards the use of artificial intelligence (AI) in management of fractures in paediatric patients. As fracture clinic services come under increasing pressure, innovative solutions are needed to combat rising demand. AI programs can be used to diagnosis fractures, but patient perceptions towards its use are uncertain. METHODS: We conducted a cross-sectional survey of carers of paediatric patients presenting to fracture clinic at a tertiary care centre, combining single-best-answer questions and Likert-type questions. We investigated patient perception of clinical review in the emergency department (ED), disruption to school to attend fracture clinic, and attitudes towards AI. RESULTS: Of the paediatric fracture patients participating in this study, 45% were seen within two hours, 29% were seen between two and four hours, and 26% were seen after four hours; 75% were seen by both a nurse and a doctor, 16% were seen only by a nurse and 9% only by a doctor. A total of 61% of children had to take time off school for their appointment and 59% of parents had to take time off. Of all respondents, 56% agreed that more research is needed to reduce waiting times, 76% preferred a nurse or doctor to review their child's radiograph, 64% were happy for an AI program to diagnose their child's fracture, and 82% were happy with an AI program being used as an adjunct to a clinician's diagnosis. CONCLUSIONS: Carer perceptions towards the use of AI in this setting are positive. However, they are not yet ready to relinquish human decision making to automated systems.

Developing an artificial intelligence diagnostic tool for paediatric distal radius fractures, a proof of concept study.

INTRODUCTION: In the UK, 1 in 50 children sustain a fractured bone yearly, yet studies have shown that 34% of children sustaining an injury do not have a visible fracture on initial radiographs. Wrist fractures are particularly difficult to identify because the growth plate poses diagnostic challenges when interpreting radiographs. METHODS: We developed Convolutional Neural Network (CNN) image recognition software to detect fractures in radiographs from children. A consecutive data set of 5,000 radiographs of the distal radius in children aged less than 19 years from 2014 to 2019 was used to train the CNN. In addition, transfer learning from a VGG16 CNN pretrained on non-radiological images was applied to improve generalisation of the network and the classification of radiographs. Hyperparameter tuning techniques were used to compare the model with the radiology reports that accompanied the original images to determine diagnostic test accuracy. RESULTS: The training set consisted of 2,881 radiographs with a fracture and 1,571 without; 548 radiographs were outliers. With additional augmentation, the final data set consisted of 15,498 images. The data set was randomly split into three subsets: training (70%), validation (10%) and test (20%). After training for 20 epochs, the diagnostic test accuracy was 85%. DISCUSSION: A CNN model is feasible in diagnosing paediatric wrist fractures. We demonstrated that this application could be utilised as a tool for improving diagnostic accuracy. Future work would involve developing automated treatment pathways for diagnosis, reducing unnecessary hospital visits and allowing staff redeployment to other areas.

Paediatric tibial shaft fractures: an instructional review for the FRCS exam.

This instructional review presents the literature and guidelines relevant to the classification, management and prognosis of paediatric tibial shaft fractures at a level appropriate for the FRCS exit examination in Trauma and Orthopaedic surgery.

Paediatric distal radius fractures: an instructional review for the FRCS examination.

An instructional review of the literature and guidelines relevant for the classification, management and prognosis of paediatric distal radius fractures. Aimed at the knowledge level required for the trauma and orthopaedic FRCS examination.

Does idiopathic congenital talipes equinovarus have an impact on attainment of developmental milestones? A multicentre international study.

PURPOSE: The Ponseti method is a well-established approach to treating clubfoot. Potentially, both the underlying pathology and adherence to post-correction bracing can affect lower limb function and age of independent standing and walking. This cohort study investigates the age at which infants with idiopathic clubfoot treated using the Ponseti method achieved three selected developmental milestones and whether or not this correlated with treatment compliance. METHODS: A prospectively collected database from four centres was visited. Inclusion criteria were patients with idiopathic clubfoot with no comorbidities or prior treatment. Age at attainment of independent standing, walking, nocturnal continence was compared across three groups: I) congenital talipes equinovarus (CTEV) children compliant with treatment; II) CTEV children non-compliant with treatment; and III) typically-developed siblings. Minimum follow-up was five years. RESULTS: In all, 130 patients (198 feet) fitted the inclusion criteria: 43:87 (F:M). Standing was achieved by a mean 12.0 months in group I (sd 2.50); 12.0 months (sd 2.0) in II and ten months (sd 3.0) in III. Walking was achieved by a mean 15 months (sd 4.0) in group I, 14 months (sd 1.75) in II and 12 months (sd 3) in III, respectively. Both the compliant and non-compliant CTEV children were significantly slower at achieving standing and walking compared to sibling controls (p < 0.0001). There was no significant difference between age of nocturnal continence between the three groups. CONCLUSION: Infants with idiopathic clubfoot treated according to the Ponseti method achieve independent standing and walking approximately two months later than their typically-developed siblings. The delay is not related to the use of the foot abduction brace. LEVEL OF EVIDENCE: III.

Congenital talipes equinovarus: a systematic review of relapse as a primary outcome of the Ponseti method.

AIMS: The Ponseti method is the benchmark treatment for the correction of clubfoot. The primary rate of correction is very high, but outcome further down the treatment pathway is less predictable. Several methods of assessing severity at presentation have been reported. Classification later in the course of treatment is more challenging. This systematic review considers the outcome of the Ponseti method in terms of relapse and determines how clubfoot is assessed at presentation, correction, and relapse. PATIENTS AND METHODS: A prospectively registered systematic review was carried out according to Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) guidelines. Studies that reported idiopathic clubfoot treated by the Ponseti method between 1 January 2012 and 31 May 2017 were included. The data extracted included demographics, Ponseti methodology, assessment methods, and rates of relapse and surgery. RESULTS: A total of 84 studies were included (7335 patients, 10 535 clubfeet). The relapse rate varied between 1.9% and 45%. The rates of relapse and major surgery (1.4% to 53.3%) and minor surgery (0.6% to 48.8%) both increased with follow-up time. There was high variability in the assessment methods used across timepoints; only 57% of the studies defined relapse. Pirani scoring was the method most often used. CONCLUSION: Recurrence and further surgical intervention in idiopathic clubfoot increases with the duration of follow-up. The corrected and the relapsed foot are poorly defined, which contributes to variability in outcome. The results suggest that a consensus for a definition of relapse is needed. Cite this article: Bone Joint J 2019;101-B:639-645.

The challenge of differentiating vaso-occlusive crises from osteomyelitis in children with sickle cell disease and bone pain: A 15-year retrospective review.

PURPOSE: The paediatric sickle cell disease (SCD) osteomyelitis (OM) incidence is 0.3% to 12%. Differentiating vaso-occlusive crises (VOC) from OM is a diagnostic challenge, with limited evidence guiding management. We present a 15-year review of a paediatric sickle cell cohort. We aim to identify OM incidence and provide a management protocol for these children presenting with bone pain. METHODS: A prospective database of children with haemoglobinopathies (2002 to 2017) was analyzed for temperature, C-reactive protein (CRP) and white cell count (WCC) on admission as well as imaging, treatment and cultures. OM diagnosis was supported by imaging and blood cultures. VOC was defined as bone pain that improved without antibiotics. RESULTS: Over 15 years, 96 children with SCD presented 358 times to hospital. Empirical antibiotics were given in 308 presentations. There were five cases of OM (1.4%); two acute and three chronic. In all, 50 presentations of VOC were identified. No significant differences in age were noted between the OM and VOC group. Temperature and CRP were significantly elevated in the OM group with no significant difference in WCC. Cultures were only positive in the chronic OM admissions. There were no cases of septic arthritis. No surgical intervention was required. CONCLUSION: In children with SCD presenting with persistent bone pain, fever, elevated CRP and WCC, OM should be suspected and prompt antibiotic treatment started. Our treatment pathway was successful avoiding OM in 98.6% and septic arthritis in 100%. Further research on novel biological markers distinguishing OM from VOC should be investigated. LEVEL OF EVIDENCE: III.

Clavicle fracture nonunion in the paediatric population: a systematic review of the literature.

AIMS: Clavicle fracture nonunions are extremely rare in children. The aim of this systematic review was to assess what factors may predispose children to form clavicle fracture nonunions and evaluate the treatment methods and outcomes. METHODS: We performed a systematic review according to Preferred Reporting Items for Systematic Reviews and Meta-Analyses guidelines, aiming to find papers reporting clavicle fracture nonunion in children under the age of 18 years. Data was collected on patient demographics, fracture type, mechanism of injury (MOI), surgical intervention and reported outcome. Two independent reviewers evaluated all the data. RESULTS: A total of 13 articles reporting 21 cases of clavicle fracture nonunion were identified. The mean age at time of injury was 11.4 years (4 to 17). Falls were the most common MOI. The majority of nonunions occurred after displaced fractures on the right side. Six were refractures. Mean time of presentation following injury was 13.5 months (4 to 60). In all, 16 were treated surgically. Radiographic union was eventually achieved in 12 cases, with functional outcome satisfactory in all cases. CONCLUSION: Clavicle nonunion is an extremely rare but possible complication in children. The majority occur after displaced right-sided fractures or refractures and present around one year after injury. Surgical fixation provides good radiographic healing and functional outcomes. LEVEL OF EVIDENCE: IV.

Evertor muscle activity as a predictor of the mid-term outcome following treatment of the idiopathic and non-idiopathic clubfoot.

Previous studies have identified clinical and demographic risk factors for recurrence in the treatment of idiopathic clubfoot (congenital talipes equinovarus). Evertor muscle activity is not usually considered amongst them. This study aimed to evaluate whether recurrence could be predicted by demographic, clinical and gait parameters. From a series of 103 children with clubfeet, 67 had completed a follow-up of two years: 41 male and 26 female, 38 with idiopathic and 29 with non-idiopathic deformities. The mean age was 3.2 years (2.1 to 6.3). Primary correction was obtained in all 38 children (100%) with an idiopathic deformity, and in 26 of 29 patients (90%) with a non-idiopathic deformity. Overall, 60 children (90%) complied with the abduction brace regime. At a mean follow-up of 31.4 months (24 to 62), recurrence was noted in six children (15.8%) in the idiopathic and 14 children (48.3%) in the non-idiopathic group. Significant correlation was found between poor evertor activity and recurrence in both groups. No statistically significant relationship was found between the rate of recurrence and the severity of the initial deformity, the age at the time of treatment, the number of casts required or the compliance with the brace. After correction of idiopathic and non-idiopathic clubfoot using the Ponseti method, only poor evertor muscle activity was statistically associated with recurrence. The identification of risk factors for recurrent deformity allows clinicians to anticipate problems and advocate early additional treatment to improve muscle balance around the ankle.

Prevalence and clinical significance of fever in acute exacerbations of chronic obstructive pulmonary disease.

Fever is an important, although not always present, sign in acute exacerbation of chronic obstructive pulmonary disease (AECOPD). The objective of this study was to determine the prevalence of fever and its clinical significance in these episodes. Two hundred seventeen AECOPD hospitalizations were included in a prospective study and were categorized as febrile (FH) or afebrile (AFH), using as a cutoff a rectal temperature measurement of 37.8 degrees C during hospitalization. Eighty-six hospitalizations (39.6%) were identified as AFH. The patients in this group had significantly more severe airway obstruction and hypoxemia, a higher rate of chronic obstructive pulmonary disease (COPD) complications, a higher rate of type 3 exacerbation, a shorter length of hospitalization and a higher rate of readmissions than patients in the FH group. The results of this study show that more than one-third of AECOPD hospitalizations are attributable to afebrile episodes. These episodes are characterized by lower rates of bronchitis manifestations in patients with more severe disease. Although the length of hospitalization for these episodes is shorter, the readmission rate is higher.

Serological evidence of Mycoplasma pneumoniae infection in acute exacerbation of COPD.

A prospective study was conducted to identify and characterize hospitalizations for acute exacerbation of chronic obstructive pulmonary disease (AECOPD) with serologic evidence of infection with Mycoplasma pneumoniae (Mp). Two hundred forty hospitalizations for AECOPD were included in a 17-month prospective study. Paired sera were obtained for each of the hospitalizations and were tested serologically for Mp using a commercial enzyme immunoassay (EIA) kit. Only significant changes, according to the formula in the manufacturer's instructions, in antibody titers for IgM and/or IgG and/or IgA were considered diagnostic for Mp infection. In 34 hospitalizations (14.2%) the serologic tests for Mp were positive (MpH). In 29 of these hospitalizations (85%) a significant change in IgA was found. In 11 of these hospitalizations (32%) the only change identified was in IgA. In 24 MpH (71%) there was serologic evidence for infection with at least one other respiratory pathogen. In comparison to the 206 hospitalizations without serologic evidence of infection with Mp, MpH had higher rates of inhaled steroid therapy (41% vs. 24%, p = 0.033) and a longer time interval between the appearance of dyspnea and hospitalization (6.6 +/- 3.8 days vs. 5.0 +/- 3.5 days, p = 0.012). There were no significant differences between these two groups in a broad spectrum of patient- and exacerbation-related clinical variables. Specific antibiotic therapy for Mp in the MpH group did not shorten the hospital stay. Serologic evidence of Mp infection is common in patients hospitalized for AECOPD, and is usually based on changes in specific IgA antibody titers. In most MpH another respiratory pathogen can be identified. The vast majority of clinical characteristics are the same in patients with and without serologic evidence of infection with Mp. The practical implications of these findings should be clarified in further studies.

Serological evidence of Legionella species infection in acute exacerbation of COPD.

A prospective study was conducted to identify and characterize hospitalizations for acute exacerbations of chronic obstructive pulmonary disease (AECOPD) with serological evidence of infection with Legionella spp. (Lsp). Two-hundred and forty hospital admissions for AECOPD of 213 patients were included in the study. Paired sera were obtained for each of the admissions and were tested for 41 different serogroups of Lsp, using microimmunofluorescence-serology. Only a significant change in immunoglobulin-G and/or immunoglobulin-M antibody titres was considered diagnostic. In 40 admissions (16.7%) there was serological evidence of infection with Lsp (LspH). Legionella pneumophila 1 was identified in nine admissions, L. pneumophila 3-15 in 19 and nonpneumophila in 22. In 26 LspH (65%) there was serological evidence of infection with at least one other respiratory pathogen. Compared to the 200 admissions without Lsp (NLspH), the LspH patients were younger (p<0.05) and more hypoxaemic (p<0.04). None of the cases in the LspH group had an abrupt onset of disease, compared to 58 (29.0%) in the NLspH group (p<0.0001). The incidence of myalgia/arthralgia was 55% for LspH compared to 37% for NLspH (p<0.03). To conclude, serological evidence of infection with Legionella spp. is common among patients hospitalized with acute exacerbations of chronic obstructive pulmonary disease. In most hospital admissions with serological evidence of infection with Legionella spp. an additional respiratory pathogen can be identified. Acute exacerbation develops gradually in these patients and is characterized clinically by more systemic manifestations than hospital admissions without serological evidence of infection with Legionella spp. The true interpretation and practical relevance of these findings should be determined in further studies.