RESUMO
The gold standard for otosclerosis diagnosis, aside from surgery, is high-resolution temporal bone computed tomography (TBCT), but it can be compromised by the small size of the lesions. Many artificial intelligence (AI) algorithms exist, but they are not yet used in daily practice for otosclerosis diagnosis. The aim was to evaluate the diagnostic performance of AI in the detection of otosclerosis. This case-control study included patients with otosclerosis surgically confirmed (2010-2020) and control patients who underwent TBCT and for whom radiological data were available. The AI algorithm interpreted the TBCT to assign a positive or negative diagnosis of otosclerosis. A double-blind reading was then performed by two trained radiologists, and the diagnostic performances were compared according to the best combination of sensitivity and specificity (Youden index). A total of 274 TBCT were included (174 TBCT cases and 100 TBCT controls). For the AI algorithm, the best combination of sensitivity and specificity was 79% and 98%, with an ideal diagnostic probability value estimated by the Youden index at 59%. For radiological analysis, sensitivity was 84% and specificity 98%. The diagnostic performance of the AI algorithm was comparable to that of a trained radiologist, although the sensitivity at the estimated ideal threshold was lower.
Assuntos
Colesterol , Doenças do Nervo Facial/etiologia , Paralisia Facial/etiologia , Granuloma de Corpo Estranho/complicações , Síndromes de Compressão Nervosa/etiologia , Osso Petroso/diagnóstico por imagem , Adulto , Doenças do Nervo Facial/diagnóstico por imagem , Doenças do Nervo Facial/cirurgia , Feminino , Granuloma de Corpo Estranho/diagnóstico por imagem , Granuloma de Corpo Estranho/cirurgia , Humanos , Imageamento por Ressonância Magnética , Síndromes de Compressão Nervosa/diagnóstico por imagem , Síndromes de Compressão Nervosa/cirurgia , Osso Petroso/cirurgia , Tomografia Computadorizada por Raios XRESUMO
PURPOSE: To evaluate the safety and efficacy of cryoneurolysis (CNL) in patients with refractory thoracic neuropathic pain related to tumor invasion. MATERIALS AND METHODS: Between January 2013 and May 2017, this single-center and retrospective study reviewed 27 computed tomography-guided CNLs performed on 26 patients for refractory thoracic neuropathic pain related to tumor invasion. Patients with cognitive impairment were excluded. Pain levels were recorded on a visual analog scale (VAS) before the procedure, on days 1, 7, 14, 28 and at each subsequent follow-up appointment. CNL was clinically successful if the postprocedural VAS decreased by 3 points or more. To determine the duration of clinical success, the end of pain relief was defined as either an increased VAS of 2 or more points, the introduction of a new analgesic treatment, a death with controlled pain, or for lost to follow-up patients, the latest follow-up appointment date with controlled pain. RESULTS: Technical success rate was 96.7% and clinical success rate was 100%. Mean preprocedural pain score was 6.4 ± 1.7 and decreased to 2.4 ± 2.4 at day 1; 1.8 ± 1.7 at day 7 (P < .001); 3.3 ± 2.5 at day 14; 3.4 ± 2.6 at day 28 (P < .05). The median duration of pain relief was 45 days (range 14-70). Two minor complications occurred. CONCLUSIONS: Cryoneurolysis is a safe procedure that significantly decreased pain scores in patients with thoracic neuropathic pain related to tumor invasion, with a median duration of clinical success of 45 days.