Newborn Cry Acoustics in the Assessment of Neonatal Opioid Withdrawal Syndrome Using Machine Learning.

Importance: The assessment of opioid withdrawal in the neonate, or neonatal opioid withdrawal syndrome (NOWS), is problematic because current assessment methods are based on subjective observer ratings. Crying is a distinctive component of NOWS assessment tools and can be measured objectively using acoustic analysis. Objective: To evaluate the feasibility of using newborn cry acoustics (acoustics referring to the physical properties of sound) as an objective biobehavioral marker of NOWS. Design, Setting, and Participants: This prospective controlled cohort study assessed whether acoustic analysis of neonate cries could predict which infants would receive pharmacological treatment for NOWS. A total of 177 full-term neonates exposed and not exposed to opioids were recruited from Women & Infants Hospital of Rhode Island between August 8, 2016, and March 18, 2020. Cry recordings were processed for 118 neonates, and 65 neonates were included in the final analyses. Neonates exposed to opioids were monitored for signs of NOWS using the Finnegan Neonatal Abstinence Scoring Tool administered every 3 hours as part of a 5-day observation period during which audio was recorded continuously to capture crying. Crying of healthy neonates was recorded before hospital discharge during routine handling (eg, diaper changes). Exposures: The primary exposure was prenatal opioid exposure as determined by maternal receipt of medication-assisted treatment with methadone or buprenorphine. Main Outcomes and Measures: Neonates were stratified by prenatal opioid exposure and receipt of pharmacological treatment for NOWS before discharge from the hospital. In total, 775 hours of audio were collected and trimmed into 2.5 hours of usable cries, then acoustically analyzed (using 2 separate acoustic analyzers). Cross-validated supervised machine learning methods (combining the Boruta algorithm and a random forest classifier) were used to identify relevant acoustic parameters and predict pharmacological treatment for NOWS. Results: Final analyses included 65 neonates (mean [SD] gestational age at birth, 36.6 [1.1] weeks; 36 [55.4%] female; 50 [76.9%] White) with usable cry recordings. Of those, 19 neonates received pharmacological treatment for NOWS, 7 neonates were exposed to opioids but did not receive pharmacological treatment for NOWS, and 39 healthy neonates were not exposed to opioids. The mean of the predictions of random forest classifiers predicted receipt of pharmacological treatment for NOWS with high diagnostic accuracy (area under the curve, 0.90 [95% CI, 0.83-0.98]; accuracy, 0.85 [95% CI, 0.74-0.92]; sensitivity, 0.89 [95% CI, 0.67-0.99]; specificity, 0.83 [95% CI, 0.69-0.92]). Conclusions and Relevance: In this study, newborn acoustic cry analysis had potential as an objective measure of opioid withdrawal. These findings suggest that acoustic cry analysis using machine learning could improve the assessment, diagnosis, and management of NOWS and facilitate standardized care for these infants.

A flexible analysis tool for the quantitative acoustic assessment of infant cry.

PURPOSE: In this article, the authors describe and validate the performance of a modern acoustic analyzer specifically designed for infant cry analysis. METHOD: Utilizing known algorithms, the authors developed a method to extract acoustic parameters describing infant cries from standard digital audio files. They used a frame rate of 25 ms with a frame advance of 12.5 ms. Cepstral-based acoustic analysis proceeded in 2 phases, computing frame-level data and then organizing and summarizing this information within cry utterances. Using signal detection methods, the authors evaluated the accuracy of the automated system to determine voicing and to detect fundamental frequency (F 0) as compared to voiced segments and pitch periods manually coded from spectrogram displays. RESULTS: The system detected F 0 with 88% to 95% accuracy, depending on tolerances set at 10 to 20 Hz. Receiver operating characteristic analyses demonstrated very high accuracy at detecting voicing characteristics in the cry samples. CONCLUSIONS: This article describes an automated infant cry analyzer with high accuracy to detect important acoustic features of cry. A unique and important aspect of this work is the rigorous testing of the system's accuracy as compared to ground-truth manual coding. The resulting system has implications for basic and applied research on infant cry development.

Head-motion-controlled video goggles: preliminary concept for an interactive laparoscopic image display (i-LID).

BACKGROUND: Light-weight, low-profile, and high-resolution head-mounted displays (HMDs) now allow personalized viewing, of a laparoscopic image. The advantages include unobstructed viewing, regardless of position at the operating table, and the possibility to customize the image (i.e., enhanced reality, picture-in-picture, etc.). The bright image display allows use in daylight surroundings and the low profile of the HMD provides adequate peripheral vision. Theoretic disadvantages include reliance for all on the same image capture and anticues (i.e., reality disconnect) when the projected image remains static, despite changes in head position. This can lead to discomfort and even nausea. MATERIALS AND METHODS: We have developed a prototype of interactive laparoscopic image display that allows hands-free control of the displayed image by changes in spatial orientation of the operator's head. The prototype consists of an HMD, a spatial orientation device, and computer software to enable hands-free panning and zooming of a video-endoscopic image display. The spatial orientation device uses magnetic fields created by a transmitter and receiver, each containing three orthogonal coils. The transmitter coils are efficiently driven, using USB power only, by a newly developed circuit, each at a unique frequency. The HMD-mounted receiver system links to a commercially available PC-interface PCI-bus sound card (M-Audiocard Delta 44; Avid Technology, Tewksbury, MA). Analog signals at the receiver are filtered, amplified, and converted to digital signals, which are processed to control the image display. RESULTS: The prototype uses a proprietary static fish-eye lens and software for the distortion-free reconstitution of any portion of the captured image. Left-right and up-down motions of the head (and HMD) produce real-time panning of the displayed image. Motion of the head toward, or away from, the transmitter causes real-time zooming in or out, respectively, of the displayed image. CONCLUSIONS: This prototype of the interactive HMD allows hands-free, intuitive control of the laparoscopic field, independent of the captured image.

Factors affecting the performance of large-aperture microphone arrays.

Large arrays of microphones have been proposed and studied as a possible means of acquiring data in offices, conference rooms, and auditoria without requiring close-talking microphones. When such an array essentially surrounds all possible sources, it is said to have a large aperture. Large-aperture arrays have attractive properties of spatial resolution and signal-to-noise enhancement. This paper presents a careful comparison of theoretical and measured performance for an array of 256 microphones using simple delay-and-sum beamforming. This is the largest currently functional, all digital-signal-processing array that we know of. The array is wall-mounted in the moderately adverse environment of a general-purpose laboratory (8 m x 8 m x 3 m). The room has a T60 reverberation time of 550 ms. Reverberation effects in this room severely impact the array's performance. However, the width of the main lobe remains comparable to that of a simplified prediction. Broadband spatial resolution shows a single central peak with 10 dB gain about 0.4 m in diameter at the -3 dB level. Away from that peak, the response is approximately flat over most of the room. Optimal weighting for signal-to-noise enhancement degrades the spatial resolution minimally. Experimentally, we verify that signal-to-noise gain is less than proportional to the square root of the number of microphones probably due to the partial correlation of the noise between channels, to variation of signal intensity with polar angle about the source, and to imperfect correlation of the signal over the array caused by reverberations. We show measurements of the relative importance of each effect in our environment.