Pediatric tympanostomy tube assessment via deep learning.

PURPOSE: Tympanostomy tube (TT) placement is the most frequently performed ambulatory surgery in children under 15. After the procedure it is recommended that patients follow up regularly for "tube checks" until TT extrusion. Such visits incur direct and indirect costs to families in the form of days off from work, copays, and travel expenses. This pilot study aims to compare the efficacy of tympanic membrane (TM) evaluation by an artificial intelligence algorithm with that of clinical staff for determining presence or absence of a tympanostomy tube within the TM. METHODS: Using a digital otoscope, we performed a prospective study in children (ages 10 months-10 years) with a history of TTs who were being seen for follow up in a pediatric otolaryngology clinic. A smartphone otoscope was used by study personnel who were not physicians to take ear exam images, then through conventional otoscopic exam, ears were assessed by a clinician for tubes being in place or tubes having extruded from the TM. We trained and tested a deep learning (artificial intelligence) algorithm to assess the images and compared that with the clinician's assessment. RESULTS: A total of 123 images were obtained from 28 subjects. The algorithm classified images as TM with or without tube in place. Overall classification accuracy was 97.7 %. Recall and precision were 100 % and 96 %, respectively, for TM without a tube present, and 95 % and 100 %, respectively, for TM with a tube in place. DISCUSSION: This is a promising deep learning algorithm for classifying ear tube presence in the TM utilizing images obtained in awake children using an over-the-counter otoscope available to the lay population. We are continuing enrollment, with the goal of building an algorithm to assess tube patency and extrusion.

An experimental model of sudden death due to low-energy chest-wall impact (commotio cordis)

BACKGROUND: The syndrome of sudden death due to low-energy trauma to the chest wall (commotio cordis) has been described in young sports participants, but the mechanism is unknown. METHODS: We developed a swine model of commotio cordis in which a low-energy impact to the chest wall was produced by a wooden object the size and weight of a regulation baseball. This projectile was thrust at a velocity of 30 miles per hour and was timed to the cardiac cycle. RESULTS: We first studied 18 young pigs, 6 subjected to multiple chest impacts and 12 to single impacts. Of the 10 impacts occurring within the window from 30 to 15 msec before the peak of the T wave on the electrocardiogram, 9 produced ventricular fibrillation. Ventricular fibrillation was not produced by impacts at any other time during the cardiac cycle. Of the 10 impacts sustained during the QRS complex, 4 resulted in transient complete heart block. We also studied whether the use of safety baseballs, which are softer than standard ones, would reduce the risk of arrhythmia. A total of 48 additional animals sustained up to three impacts during the T-wave window of vulnerability to ventricular fibrillation with a regulation baseball and safety baseballs of three degrees of hardness. We found that the likelihood of ventricular fibrillation was proportional to the hardness of the ball, with the softest balls associated with the lowest risk (two instances of ventricular fibrillation after 26 impacts, as compared with eight instances after 23 impacts with regulation baseballs). CONCLUSIONS: This experimental model of commotio cordis closely resembles the clinical profile of this catastrophic event. Whether ventricular fibrillation occurred depended on the precise timing of the impact. Safety baseballs, as compared with regulation balls, may reduce the risk of commotio cordis.