Efficacy of a Trial Oral Appliance in OSAS Management: A New Protocol to Recognize Responder/Nonresponder Patients

Oral appliances (OAs) of various types have shown variable success in the treatment of mild-to-moderate obstructive sleep apnoea (OSA). In an OSA sample, this study evaluated the efficacy of a diagnostic trial OA (myTAP™); the efficacy of a definitive custom-fitted mandibular advancement device (MAD) (SomnoDent Flex™); and whether a trial device can be used to distinguish treatment responder from nonresponder patients. Patients underwent overnight home sleep recordings prior to and after fitting of these appliances in order to objectively assess their sleep quality in terms of polysomnographic (PSG) respiratory measures: apnoea-hypopnoea index (AHI), oxygen desaturation index (ODI), and minimum oxygen saturation (LowSpO2). 40 patients with symptomatic OSAS were enrolled, 33 males and 7 females, with a mean age of 55.6 ± 12.73 years and an initial (T0) AHI of 26.51 ± 14.79. Trial devices were used in 16 patients (AHI: 29.9 ± 19.97, ODI: 21.06 ± 16.05, and LowSpO2: 82 ± 10.22 at T0) and definitive MADs in 28 (AHI: 23.90 ± 9.19, ODI: 16.27 ± 11.34, and LowSpO2: 82.87 ± 6.04 at T0). Statistically significant decreases in AHI (9.59 ± 8.94, p < 0.0023 ) and ODI (8.20 ± 9.67, p < 0.0129 ) were observed after treatment with the trial device. Only 8 of the patients in the trial device group went on to use the definitive device. Treatment with the definitive MAD produced statistically significant decreases in AHI (11.46 ± 9.65, p < 0.0001 ) and ODI (9.10 ± 8.47, p < 0.0016 ) and a significant improvement in LowSpO2 (85.09 ± 6.86, p < 0.0004 ). Thus, both types of device proved effective in improving the PSG parameters. This study showed that introducing an easy-to-make and low-cost trial device into the therapeutic pathway of OSAS patients can circumvent the problem of individual responses to treatment by allowing effective classification of patients: in short, it allows a first distinction to be drawn between responders and nonresponders to treatment.

Expert-level classification of gastritis by endoscopy using deep learning: a multicenter diagnostic trial

Background and study aims Endoscopy plays a crucial role in diagnosis of gastritis. Endoscopists have low accuracy in diagnosing atrophic gastritis with white-light endoscopy (WLE). High-risk factors (such as atrophic gastritis [AG]) for carcinogenesis demand early detection. Deep learning (DL)-based gastritis classification with WLE rarely has been reported. We built a system for improving the accuracy of diagnosis of AG with WLE to assist with this common gastritis diagnosis and help lessen endoscopist fatigue. Methods We collected a total of 8141 endoscopic images of common gastritis, other gastritis, and non-gastritis in 4587 cases and built a DL -based system constructed with UNet + + and Resnet-50. A system was developed to sort common gastritis images layer by layer: The first layer included non-gastritis/common gastritis/other gastritis, the second layer contained AG/non-atrophic gastritis, and the third layer included atrophy/intestinal metaplasia and erosion/hemorrhage. The convolutional neural networks were tested with three separate test sets. Results Rates of accuracy for classifying non-atrophic gastritis/AG, atrophy/intestinal metaplasia, and erosion/hemorrhage were 88.78 %, 87.40 %, and 93.67 % in internal test set, 91.23 %, 85.81 %, and 92.70 % in the external test set ,and 95.00 %, 92.86 %, and 94.74 % in the video set, respectively. The hit ratio with the segmentation model was 99.29 %. The accuracy for detection of non-gastritis/common gastritis/other gastritis was 93.6 %. Conclusions The system had decent specificity and accuracy in classification of gastritis lesions. DL has great potential in WLE gastritis classification for assisting with achieving accurate diagnoses after endoscopic procedures.

Presepsin (Soluble CD14 Subtype) as an Early Marker of Neonatal Sepsis and Septic Shock: A Prospective Diagnostic Trial

In the context of suspected neonatal sepsis, early diagnosis and stratification of patients according to clinical severity is not yet effectively achieved. In this diagnostic trial, we aimed to assess the accuracy of presepsin (PSEP) for the diagnosis and early stratification of supposedly septic neonates. PSEP, C-reactive protein (CRP), and procalcitonin (PCT) were assessed at the onset of sepsis suspicion (T0), every 12–24 h for the first 48 h (T1–T4), and at the end of antibiotic therapy (T5). Enrolled neonates were stratified into three groups (infection, sepsis, septic shock) according to Wynn and Wong’s definitions. Sensitivity, specificity, and area under the ROC curve (AUC) according to the severity of clinical conditions were assessed. We enrolled 58 neonates with infection, 77 with sepsis, and 24 with septic shock. PSEP levels were higher in neonates with septic shock (median 1557.5 pg/mL) and sepsis (median 1361 pg/mL) compared to those with infection (median 977.5 pg/mL) at T0 (p < 0.01). Neither CRP nor PCT could distinguish the three groups at T0. PSEP’s AUC was 0.90 (95% CI: 0.854–0.943) for sepsis and 0.94 (95% CI: 0.885–0.988) for septic shock. Maximum Youden index was 1013 pg/mL (84.4% sensitivity, 88% specificity) for sepsis, and 971.5 pg/mL for septic shock (92% sensitivity, 86% specificity). However, differences in PSEP between neonates with positive and negative blood culture were limited. Thus, PSEP was an early biomarker of neonatal sepsis severity, but did not support the early identification of neonates with positive blood culture.

Artificial Intelligence Algorithm with SVM Classification using Dermascopic Images for Melanoma Diagnosis

Of all suspicious pigmented skin lesions considered for analysis, a large portion is often benign. The pressure of pathology services and secondary care must be reduced throughout the patient trials using modern techniques for improving the melanoma diagnosis accuracy. Dermoscopic images obtained from digital single-lens reflex (DSLR) cameras, smartphones and a lightweight USB camera are compared using artificial intelligence (AI) algorithm for determining the accuracy of melanoma identification. Datasets are obtained from thousand test samples undergoing plastic surgery. The diagnostic trial is masked, single arm and multicentered. The controlled and suspicious skin lesions as well as the suspicious pigmented skin lesion are captured on the aforementioned cameras while scheduling for biopsy. The possibility of melanoma is assessed using deep learning (DL) techniques on the pigmented skin lesions seen in the dermascopic images for identifying melanoma. For this purpose, we train a deterministic AI algorithm based on malignancy recognition by deep ensemble and inputs from clinicians. The histopathology diagnosis is used as a standard criterion for determining the specialist assessment, algorithmic specificity, sensitivity and the area under the receiver operating characteristic curve (AUROC).