SAMI: an M-Health application to telemonitor intelligibility and speech disorder severity in head and neck cancers.

Perceptual measures, such as intelligibility and speech disorder severity, are widely used in the clinical assessment of speech disorders in patients treated for oral or oropharyngeal cancer. Despite their widespread usage, these measures are known to be subjective and hard to reproduce. Therefore, an M-Health assessment based on an automatic prediction has been seen as a more robust and reliable alternative. Despite recent progress, these automatic approaches still remain somewhat theoretical, and a need to implement them in real clinical practice rises. Hence, in the present work we introduce SAMI, a clinical mobile application used to predict speech intelligibility and disorder severity as well as to monitor patient progress on these measures over time. The first part of this work illustrates the design and development of the systems supported by SAMI. Here, we show how deep neural speaker embeddings are used to automatically regress speech disorder measurements (intelligibility and severity), as well as the training and validation of the system on a French corpus of head and neck cancer. Furthermore, we also test our model on a secondary corpus recorded in real clinical conditions. The second part details the results obtained from the deployment of our system in a real clinical environment, over the course of several weeks. In this section, the results obtained with SAMI are compared to an a posteriori perceptual evaluation, conducted by a set of experts on the new recorded data. The comparison suggests a high correlation and a low error between the perceptual and automatic evaluations, validating the clinical usage of the proposed application.

Structural and chemical heterogeneities of primary hyperoxaluria kidney stones from pediatric patients.

OBJECTIVE: Calcium oxalate stones are the most common type among stone-forming patients and in some cases result from predisposed genetic conditions. In this work, we examined the differences in structure and chemical composition between oxalate stones from patients from three groups: 1) pediatric patients that were genetically predisposed (primary hyperoxaluria) to form stones (PPH); 2) control pediatric patients that did not have such genetic predisposition (PN-PH); 3) adult patients that formed oxalate stones without the genetic predisposition (A-CaOx). A variety of instrumental analyses were conducted to identify physicochemical properties of stones characteristic of predisposed pediatric (PPH), pediatric hyperoxaluria (PN-PH), and adult (A-CaOx) patient populations. METHODS: Genetic variants of 16 stone-forming patients were determined using whole-exome gene sequencing. Components of stones from PPH (n = 6), PN-PH (n = 5), and A-CaOx (n = 5) groups were identified using Fourier transform infrared (FTIR) spectroscopy. Stone morphology and density were evaluated using high resolution X-ray computed tomography (micro-XCT). Stone microstructure and elemental composition were mapped with scanning electron microscopy (SEM) and energy dispersive X-ray (EDX) spectroscopy, respectively. RESULTS: Calcium oxalate bipyramidal crystals were found on stones from all groups. Stones from PPH patients with PH types I and II were composed of calcium oxalate monohydrate (COM) with relatively uniform mineral density (1224 ± 277 mg/cc) and distinct smooth surfaces. By contrast, micro-spherical calcium phosphate particles were found only on PN-PH stones, which also showed a broader range of mineral densities (1266 ± 342 mg/cc). Stones from the PN-PH group also contained phosphorus (P), which was absent in NP-PH stones. A-CaOx stones were of significantly lower mineral density (645 ± 237 mg/cc) than pediatric stones and were more heterogeneous in their elemental composition. CONCLUSION: Unique structural and compositional characteristics were identified in stones from pediatric patients with primary hyperoxaluria. These include the absence of phosphorus, a narrower mineral density distribution, and a uniform elemental composition compared to stones from pediatric patients without the genetic predisposition. Thus, characterization of stones at the macro- and micro-scales in combination with genetic testing of patients can provide insights and accurate diagnosis to develop a treatment plan for effective patient care.

Initial multicenter experience with a new high-density coloring module: impact for complex atrial arrhythmias interpretation.

BACKGROUND: High-density automated mapping of complex atrial tachycardias (ATs) requires accurate assessment of activation maps. A new local activation display module (HD coloring, Biosense Webster®) provides higher map resolution, a better delineation of potential block reducing color interpolation, and a new propagation display. We evaluated the accuracy of a dedicated local activation display compared with standard algorithm. METHODS: High-density maps from 10 AT were collected with a multipolar catheter and were displayed with standard activation or HD coloring. Six expert operators retrospectively analyzed activation maps and were asked to define (1) the tachycardia mechanism, (2) ablation target, and (3) level of difficulty to interpret those maps. RESULTS: Using HD coloring, operators were able to reach a correct diagnosis in 93% vs. 63%, p < 0.05 compared to standard activation maps. Time to diagnosis was shorter 1.9 ± 1.0 min vs. 3.9 ± 2.1 min, p < 0.05. Confidence level would have allowed ablation without necessity for entrainment maneuvers in 87% vs. 53%, p < 0.05. Operators would have needed to remap or proceed with multiple entrainments in 3% vs. 13% of cases, p < 0.05. Finally, ablation strategy was more accurately identified in 97% vs. 67%, p < 0.05. CONCLUSION: Activation mapping with the new HD coloring module allowed a more accurate, reliable, and faster interpretation of complex ATs mechanisms compared to standard activation maps.