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.

Stereoselective metabolism of tazofelone, an anti-inflammatory bowel disease agent, in rats and dogs and in human liver microsomes.

Incubation of (R)-tazofelone and (S)-tazofelone in rat, dog, and human liver microsomes demonstrated that the (R)-tazofelone enantiomer was more rapidly metabolized, with two diastereomeric sulfoxides as the major metabolites formed in all three species. The two diasteresomers epimerized at physiological pH, therefore total sulfoxide formation rates were measured. The formation of the total sulfoxide metabolites followed Michaelis-Menten kinetics. The K(m), Vmax, and intrinsic formation clearance (Vmax/K(m)) values were determined in rat, dog, and human liver microsomes. The intrinsic formation clearance of sulfoxide from (R)-tazofelone exceeded that of (S)-tazofelone in all three species. In vivo studies in rats and dogs dosed orally and intravenously confirmed the stereoselective metabolism of tazofelone observed in vitro. Plasma concentrations of (S)-tazofelone exceeded (R)-tazofelone in rats and dogs by a factor of 3 to 4. In rat portal plasma, both enantiomers were of approximately equal concentration after oral dosing, indicating similar absorption. The half-lives of tazofelone and total sulfoxides in rats were 3.5 and 2.8 h, respectively. In dogs, the half-lives of tazofelone and total sulfoxides were 2.2 and 5.5 h, respectively. Plasma clearance was 2.3 l/h in rats and 1.4 l/h in dogs, and the volumes of distribution were 12 and 4.5 l, respectively, in rats and dogs. Both enantiomers were highly bound to plasma proteins to a similar extent in both species.

In vitro biotransformation and identification of human cytochrome P450 isozyme-dependent metabolism of tazofelone.

Tazofelone is a new inflammatory bowel disease agent. The biotransformation of tazofelone in human livers and the cytochrome P450 responsible for the biotransformation has been studied. Two metabolites of tazofelone were formed in vitro. A sulfoxide metabolite was identified by cochromatography with authentic standards, and a quinol metabolite of tazofelone was identified by mass spectrometry and proton NMR. Sulfoxidation was catalyzed by a single enzyme system while formation of the quinol metabolite was catalyzed by a two enzyme system. The Km and Vmax values for sulfoxidation were 12.4 microM and 0.27 nmol/min/mg protein, respectively. The high affinity Km and Vmax values for the formation of the quinol metabolite were 7.5 microM and 0.17 nmol/min/mg protein, respectively. Tazofelone was incubated at 20 microM concentration with human microsomes to determine which of the cytochrome P450 isozyme(s) is involved in the oxidation of tazofelone. A strong correlation was found between the immunoquantified concentrations of CYP3A and the rates of formation of the sulfoxide and quinol metabolites of tazofelone. Similarly, significant correlations were observed between the formation of midazolam 1'-hydroxylation and the rates of formation of both metabolites of tazofelone. Inhibition studies have indicated that triacetyloleandomycin, a CYP3A specific inhibitor, almost completely inhibited the formation of both of these tazofelone metabolites. Incubations with specific cDNA expressed microsomes indicated that the formation of both the sulfoxide and quinol metabolites was highest with CYP3A4 containing microsomes. The correlation data was confirmed by inhibition studies and cDNA expressed cytochrome P450 systems demonstrating that the biotransformation of tazofelone to its metabolites is primarily mediated by CYP3A.