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.

Comparison of In-Hospital Outcomes of Patients With-Versus-Without Atrial Fibrillation and Alcohol Withdrawal Syndrome.

Alcohol withdrawal syndrome (AWS) has been associated with significant medical complications and length of stay. Cardiovascular effects from AWS include a physiologic tachycardia and hypertensive response. Although atrial fibrillation (AF) is one of the most common arrhythmias, the impact of a known history of AF on AWS is unclear. The purpose of our study is to assess the impact of history of AF on clinical outcomes, cost, and length of stay on AWS. The Nationwide Inpatient Sample was used to identify patients aged 18 years or older who underwent AWS with or without AF using the International Classification of Disease 9 Clinical Modification codes from January 2010 to December 2014. Outcomes were compared between those with or without AF using propensity score method-stratified morbidity ratio weighing- to adjust for baseline patient and hospital characteristics. A total of 280,451 patients with AWS of which 14,459 (5.2%) had history of AF. Patients with AF was older, less likely female, and more had higher burden of co-morbidities. In an adjusted model, in-hospital mortality (odds ratio [OR] 1.98 95% confidence interval [CI] 1.61 to 2.45), ischemic stroke (OR 1.67 95% CI 1.42 to 1.95), acute kidney injury (OR 1.36 95% CI 1.24 to 1.49), acute kidney injury requiring dialysis (OR 1.89 95% CI 1.39 to 2.50), and cost (mean ratio 1.27 95% CI 1.21 to 1.33) were higher in the AF cohort. Length of stay was shorter in patients with AF (mean ratio 0.85 95% CI 0.81 to 0.90). In conclusion, a known history of AF increased the risk of in-hospital mortality, morbidity, and hospital expense in AWS.

Our Ethical Obligation to Treat Opioid Use Disorder in Prisons: A Patient and Physician's Perspective.

The opioid epidemic has claimed the lives of more than 183,000 individuals since 1999 and is now the leading cause of accidental death in the United States. Meanwhile, rates of incarceration have quadrupled in recent decades, and drug use is the leading cause of incarceration. Medication-assisted treatment or MAT (i.e. methadone, buprenorphine) is the gold standard for treatment of opioid use disorder. Incarcerated individuals with opioid use disorder treated with methadone or buprenorphine have a lower risk of overdose, lower rates of hepatitis C transmission, and lower rates of re-incarceration. Despite evidence of improved outcomes, many jails and prisons do not offer MAT to individuals with opioid use disorder. This seems partly due to a scientifically unjustified preference for an abstinence-only treatment approach. The absence of MAT in prisons and jails results in poor outcomes for individuals and poses a public health threat to communities. Furthermore, it disproportionately harms poor communities and communities of color. Health care providers in prisons and jails have an ethical obligation to offer MAT to individuals with opioid use disorder to mitigate risk of infectious diseases, opioid overdose and health disparities associated with incarceration.

Reasons for misuse of prescription medication among physicians undergoing monitoring by a physician health program.

OBJECTIVES: Substance-related impairment of physicians is a small but serious problem, with significant consequences for patient safety and public health. The purpose of this study was to identify reasons for prescription drug misuse among physicians referred to a physician health program for monitoring because of substance-related impairment, to develop better mechanisms for prevention and intervention. METHODS: A total of 55 physicians (94.5% male) who were being monitored by their State physician health program because of substance-related impairment participated in guided focus group discussions. Participation was anonymous. Discussions were transcribed from 9 separate focus groups, lasting 60 to 90 minutes each. Qualitative analyses were conducted to examine themes. RESULTS: All participants were diagnosed with substance dependence, and 69.1% of them endorsed a history of misusing prescription drugs. Participants documented the following 5 primary reasons for prescription drug misuse: (1) to manage physical pain, (2) to manage emotional/psychiatric distress, (3) to manage stressful situations, (4) to serve recreational purposes, and (5) to avoid withdrawal symptoms. CONCLUSIONS: Our results emphasize the importance of self-medication as a leading reason for misusing prescription medications, although recreational use was also an important factor. Prevention efforts targeting prescription drug misuse among physicians should be initiated during medical training, with continuing education requirements throughout the physicians' careers.

Risk assessment of moderate to severe alcohol withdrawal--predictors for seizures and delirium tremens in the course of withdrawal.

AIMS: To develop a prediction model for withdrawal seizures (WS) and delirium tremens (DT) during moderate to severe alcohol withdrawal syndrome (AWS) in a large cohort of inpatients treated for AWS (n = 827). METHODS: Re-analysis of a cohort study population treated between 2000 and 2009. All patients received a score-guided and symptom-triggered therapy for AWS. Multivariable binary logistic regression models with stepwise variable selection procedures were conducted providing odds ratio (OR) estimates. RESULTS: In the multivariable regression, significant predictors of WS during AWS therapy were a delayed climax of withdrawal severity since admission [OR/10 h: 1.23; 95% confidence interval (CI): 1.1-1.4; P < 0.001)], prevalence of structural brain lesions in the patient's history (OR 6.5; 95% CI: 3.0-14.1; P < 0.001) and WS as the cause of admittance (OR 2.6; 95% CI: 1.4-4.8; P = 0.002). Significant predictors at admission for the occurrence of DT were lower serum potassium (OR/1 mmol/l 0.33; 95% CI: 0.17-0.65; P = 0.001), a lower platelet count (OR/100.000 0.42; 95% CI: 0.26-0.69; P = 0.001) and prevalence of structural brain lesions (OR 5.8; 95% CI: 2.6-12.9; P < 0.001). CONCLUSION: In this large retrospective cohort, some easily determinable parameters at admission may be useful to predict a complicated course of alcohol withdrawal regarding the occurrence of WS or DT. Using the provided nomograms, clinicians can estimate the percentage likelihood of patients to develop either WS or DT during their course of withdrawal. Prevalence of structural brain lesions in the patient's history does strongly warrant a careful observation of patients.

Alcohol withdrawal syndrome: Turning minor injuries into a major problem.

BACKGROUND: Abrupt cessation of chronic drinking patterns places hospitalized patients at risk for alcohol withdrawal syndrome (AWS). The purpose of this study was to investigate the effect of AWS on length of stay, morbidity, mortality, and cost in low injury acuity trauma patients. METHODS: A retrospective review of the National Trauma Registry of the American College of Surgeons database from July 1999 to February 2004 was performed. All patients 15 years or older admitted to our Level I trauma center with an Injury Severity Score (ISS) <16 were included. AWS patients were compared with those without AWS. Demographics, mechanism of injury (MOI), ISS, revised trauma score, Glasgow Coma score, hospital course, morbidity, requirement of additional procedures, mortality, and cost were compared. Analysis was done with chi2 test and Student's t test. A p value of < or =0.05 determined significance. RESULTS: Of 6,431 patients, 55 (0.9%) developed AWS. AWS patients were likely men (p < 0.001); had a higher ISS (p = 0.001) and lower Glasgow Coma score (p = 0.01); had more ventilator days (p = 0.008), intensive care unit days (p < 0.0001), and hospital days (p < 0.0001); suffered more complications, including respiratory failure (p < 0.0001), pneumonia (p < 0.0001), urinary tract infection (p = 0.0005), sepsis (p < 0.0001), tracheostomy (p < 0.0001), and percutaneous endoscopic gastrostomy (p < 0.0001); and had higher cost (p < 0.0001). Mortality was similar (p = 0.38) among groups. CONCLUSIONS: Low injury acuity patients with AWS have increased morbidity, leading to increased hospital stay and cost. To allow minor injuries to remain minor problems, the best modality to identify patients at risk and to achieve AWS prophylaxis require further investigation.

Introducing an in-patient treatment for alcohol detoxification into a community setting.

Alcohol detoxification in the UK is not standardized and treatment is usually determined by local policies. Drug regimens are often predetermined and unrelated to the extent and duration of dependence, recent consumption, or previous withdrawal symptoms. Diazepam loading shortens the detoxification period and avoids the indiscriminate use of medication. It has been shown to be effective as an in-patient treatment. This paper examines the feasibility of introducing diazepam loading in a community setting, and discusses the implications that this would have for clinical practice.

Opiate dependence and withdrawal: preliminary assessment using single photon emission computerized tomography (SPECT).

Naloxone (0.8 mg, s.c.) effects on opiate withdrawal signs and symptoms and regional brain function were assessed in 10 methadone-maintained patients and 10 healthy subjects in a double-blind, placebo-controlled study. Regional brain function was assessed using single photon emission computerized tomography (SPECT) by evaluating the uptake of [99mTc]d,l-hexamethylpropyleneamine oxime (HMPAO) in the brain, a process related to regional cerebral perfusion. Comparisons of patients and healthy subjects after saline infusion suggested that chronic opiate dependence was associated with lower corrected activity ratios (regional count density/whole brain count density) in frontal and parietal cortices and greater activity ratios in the thalamus. Opiate-dependent patients, but not healthy subjects, developed opiate withdrawal signs and symptoms after naloxone administration. Following naloxone administration, patients undergoing opiate withdrawal exhibited lower whole brain count density than healthy subjects. They also had lower activity ratios in frontal and parietal cortices and increased thalamic activity ratios relative to healthy subjects receiving naloxone. Naloxone administration in healthy subjects, but not opiate withdrawal in patients, was associated with decreased right parietal cortex and increased right temporal cortex and left basal ganglia activity ratios. Relative to naloxone effects in healthy subjects, opiate withdrawal was associated with decreased whole brain count density and a reduced right temporal cortex activity ratio. This preliminary study reports an initial evaluation of HMPAO-SPECT imaging for assessing regional alterations in brain function during opiate dependence and withdrawal. While group differences were reported, the small magnitude of regional alterations in patients undergoing opiate withdrawal raised concern that HMPAO-SPECT methods employed were inadequate for assessing human regional brain function during phases of opiate addiction. Other emerging functional brain imaging technologies should be evaluated relative to improved HMPAO-SPECT methods for this purpose.