ABSTRACT
Deep learning applications are emerging as promising new tools that can support the diagnosis and classification of different cancer types. While such solutions hold great potential for hematological malignancies, there have been limited studies describing the use of such applications in this field. The rapid diagnosis of double/triple-hit lymphomas (DHLs/THLs) involving MYC, BCL2 and/or BCL6 rearrangements is obligatory for optimal patient care. Here, we present a novel deep learning tool for diagnosing DHLs/THLs directly from scanned images of biopsy slides. A total of 57 biopsies, including 32 in a training set (including five DH lymphoma cases) and 25 in a validation set (including 10 DH/TH cases), were included. The DHL-classifier demonstrated a sensitivity of 100%, a specificity of 87% and an AUC of 0.95, with only two false positive cases, compared to FISH. The DHL-classifier showed a 92% predictive value as a screening tool for performing conventional FISH analysis, over-performing currently used criteria. The work presented here provides the proof of concept for the potential use of an AI tool for the identification of DH/TH events. However, more extensive follow-up studies are required to assess the robustness of this tool and achieve high performances in a diverse population.
ABSTRACT
OBJECTIVE: This study aimed to explore risk factors for dental intervention in patients presenting to the pediatric emergency department (PED) after dental injury. METHODS: We retrospectively explored patients aged 0 to 18 years who presented to our PED between 2017 and 2021 after dental injury. RESULTS: Of the total of 830 patients (mean age 7.1 ± 3.9 years, 589 [71.0%] male patients), 237 (28.5%) required dental intervention. All patients with alveolar fractures and those with involvement of permanent teeth with extrusive luxation mandated urgent dental consultation. Additional independent predictors for dental intervention for primary tooth injury were: root fracture (adjusted odds ratio [aOR] 38.4; 95% confidence interval [CI], 3.95-373.22; P = 0.002), facial bone involvement (aOR 12.40; 95% CI, 2.33-65.93; P = 0.003), lateral luxation (aOR 6.9; 95% CI, 4.27-11.27; P < 0.001), extrusive luxation (aOR 6.44; 95% CI, 2.74-15.14; P < 0.001), and avulsion (aOR 2.06; 95% CI, 1.23-3.45; P = 0.006). Additional independent predictors for permanent tooth injury were lateral luxation (aOR 27.8; 95% CI, 6.1-126.6; P < 0.001) and avulsion (aOR 6.8; 95% CI, 2.9-15.9; P < 0.001). CONCLUSIONS: Alveolar fracture is a severe dental injury, requiring intervention, for primary and permanent teeth injuries. Tooth luxation with significant mobility or malocclusion, incomplete avulsion, a suspected root involvement, or facial bone injury in the primary teeth and tooth luxation (extrusive/lateral) and avulsion in the permanent teeth dictate urgent dental consultation and intervention. Clinical algorithms for dental injury management are suggested.
ABSTRACT
OBJECTIVES: This study aimed to explore risk factors for failure of forearm fracture closed reduction in the pediatric emergency department (ED) and to suggest indications for initial surgery. METHODS: This retrospective cohort study included all patients aged 0 to 18 years who presented to our pediatric ED with an extraarticular forearm fracture treated with closed reduction between May 2017 and April 2021. We explored risk factors for procedural failure, defined as a need for surgical intervention within 6 weeks of the closed reduction attempt. RESULTS: Of 375 patients (median age 8.1 years, 294 [78.2%] boys), 44 (11.7%) patients sustained a reduction failure, of whom 42 (95.5%) had both radius and ulna fractures. Of the 259 patients with fractures of both bones, the following parameters were independent predictors for reduction failure: refracture (adjusted odds ratio [aOR] 17.6, P < 0.001), open fracture (aOR 10.1, P = 0.007), midshaft fracture (aOR 2.6, P = 0.004), radial translation rate 37% and higher in either plane (aOR 5.1, P = 0.004), and age of 10 years and older (aOR 2.9, P = 0.01). CONCLUSIONS: Most pediatric forearm fractures can be successfully managed by closed reduction in the ED. Two-bone fractures had the strongest association with reduction failure. Refracture, open fracture, midshaft location, initial radius bone translation of 37% and higher (and not initial angulation), and patient age of 10 years and older are independent risk factors for reduction failure in two-bone fractures. We propose a risk score for reduction failure that can serve as a decision-making tool.
Subject(s)
Forearm Injuries , Fractures, Closed , Fractures, Open , Radius Fractures , Ulna Fractures , Male , Child , Humans , Female , Closed Fracture Reduction , Forearm , Retrospective Studies , Fractures, Open/complications , Radius Fractures/surgery , Radius Fractures/complications , Forearm Injuries/surgery , Forearm Injuries/complications , Ulna Fractures/surgery , Ulna Fractures/complications , Emergency Service, Hospital , Risk Factors , Treatment OutcomeABSTRACT
This prospective study evaluated seroconversion rates in response to BNT162b2 (Pfizer-BioNTech) COVID-19 vaccine booster in 44 B-cell non-Hodgkin lymphoma (B-NHL) patients who failed to respond to two prior doses [42 previously exposed to anti-CD20 monoclonal antibodies (moAbs) including 13 under maintenance treatment]. Seroconversion was obtained in 29.5% of the patients. Longer time from last anti-CD20 moAb (>6 months) and diagnosis of aggressive lymphoma compared to other, incurable B-NHLs were associated with increased seroconversion rates (47.8% vs.10.5%, p = 0.019 and 50% vs. 17.9%, p = 0.025 respectively). Thus, seronegative patients with B-NHL that completed anti-CD20 therapy more than 6 months prior to the booster have greater chances to achieve seroconversion.