Applications of artificial intelligence and bioinformatics methodologies in the analysis of ocular biofluid markers: a scoping review.

PURPOSE: This scoping review summarizes the applications of artificial intelligence (AI) and bioinformatics methodologies in analysis of ocular biofluid markers. The secondary objective was to explore supervised and unsupervised AI techniques and their predictive accuracies. We also evaluate the integration of bioinformatics with AI tools. METHODS: This scoping review was conducted across five electronic databases including EMBASE, Medline, Cochrane Central Register of Controlled Trials, Cochrane Database of Systematic Reviews, and Web of Science from inception to July 14, 2021. Studies pertaining to biofluid marker analysis using AI or bioinformatics were included. RESULTS: A total of 10,262 articles were retrieved from all databases and 177 studies met the inclusion criteria. The most commonly studied ocular diseases were diabetic eye diseases, with 50 papers (28%), while glaucoma was explored in 25 studies (14%), age-related macular degeneration in 20 (11%), dry eye disease in 10 (6%), and uveitis in 9 (5%). Supervised learning was used in 91 papers (51%), unsupervised AI in 83 (46%), and bioinformatics in 85 (48%). Ninety-eight papers (55%) used more than one class of AI (e.g. > 1 of supervised, unsupervised, bioinformatics, or statistical techniques), while 79 (45%) used only one. Supervised learning techniques were often used to predict disease status or prognosis, and demonstrated strong accuracy. Unsupervised AI algorithms were used to bolster the accuracy of other algorithms, identify molecularly distinct subgroups, or cluster cases into distinct subgroups that are useful for prediction of the disease course. Finally, bioinformatic tools were used to translate complex biomarker profiles or findings into interpretable data. CONCLUSION: AI analysis of biofluid markers displayed diagnostic accuracy, provided insight into mechanisms of molecular etiologies, and had the ability to provide individualized targeted therapeutic treatment for patients. Given the progression of AI towards use in both research and the clinic, ophthalmologists should be broadly aware of the commonly used algorithms and their applications. Future research may be aimed at validating algorithms and integrating them in clinical practice.

Supporting Type 1 and Type 2 Diabetes Care in the Hemodialysis Unit: A Quality-improvement Initiative Throughout the COVID-19 Pandemic.

OBJECTIVE: People living with diabetes mellitus (DM) and chronic kidney disease can have difficulty attending multiple appointments to receive DM care. We developed and studied the utility of a DM outreach program to offer in the hemodialysis (HD) unit. METHODS: We conducted a quality improvement project in a satellite HD unit in London, Ontario, Canada, between August 1, 2019, and July 31, 2022. We assessed for baseline gaps in DM care among those with DM, performed root-cause analysis with key stakeholders to identify critical drivers of gaps, and conceptualized a certified diabetes educator-led outreach program to offer in the HD unit. We aimed to improve DM self-monitoring, hypo- and hyperglycemia, and DM-related screening. We used run and control charts to track outcome measures over time and modified our outreach program iteratively. RESULTS: Fifty-eight persons with DM receiving HD participated in our program. Support spanned multiple waves of the COVID-19 pandemic. With 4 tests of change, we observed improvement in DM self-monitoring with a modest decline in self-reported hyperglycemia. There were no adverse consequences, and satisfaction with our program was high. CONCLUSIONS: Although we did not meet all measures of success during the pandemic, outreach DM support in the HD unit appeared to improve self-monitoring and self-reported hyperglycemia. Similar programs could be modified and implemented in other centres.

Optimal Dose of Intranasal Dexmedetomidine for Laceration Repair in Children: A Phase II Dose-Ranging Study.

STUDY OBJECTIVE: To determine the optimal sedative dose of intranasal dexmedetomidine for children undergoing laceration repair. METHODS: This dose-ranging study employing the Bayesian Continual Reassessment Method enrolled children aged 0 to 10 years with a single laceration (<5 cm), requiring single-layer closure, who received topical anesthetic. Children were administered 1, 2, 3, or 4 mcg/kg intranasal dexmedetomidine. The primary outcome was the proportion with adequate sedation (Pediatric Sedation State Scale score of 2 or 3 for ≥90% of the time from sterile preparation to tying of the last suture). Secondary outcomes included the Observational Scale of Behavior Distress-Revised (range: 0 [no distress] to 23.5 [maximal distress]), postprocedure length of stay, and adverse events. RESULTS: We enrolled 55 children (35/55 [64%] males; median [interquartile range {IQR}] age 4 [2, 6] years). At 1, 2, 3, and 4 mcg/kg intranasal dexmedetomidine, respectively, the proportion of participants "adequately" sedated was 1/3 (33%), 2/9 (22%), 13/21 (62%), and 12/21 (57%); the posterior mean (95% equitailed credible intervals) for the probability of adequate sedation was 0.38 (0.04, 0.82), 0.25 (0.05, 0.54), 0.61 (0.41, 0.80), and 0.57 (0.36, 0.76); the median (IQR) Observational Scale of Behavior Distress-Revised scores during suturing was 2.7 (0.3, 3), 0 (0, 3.8), 0.6 (0, 5), and 0 (0, 3.7); the median (IQR) postprocedure length of stay was 67 (60, 78), 76 (60, 100), 89 (76, 109), and 113 (76, 150) minutes. There was 1 adverse event, a decrease in oxygen saturation at 4 mcg/kg, which resolved with head repositioning. CONCLUSION: Despite limitations, such as our limited sample size and subjectivity in Pediatric Sedation State Scale scoring, sedation efficacy for 3 and 4 mcg/kg were similarly based on equitailed credible intervals suggesting either could be considered optimal.

A survey of minimally invasive surfactant therapy in Canada.

Introduction: Minimally invasive surfactant therapy (MIST) can be used to treat neonatal respiratory distress syndrome in neonatal intensive care units (NICUs). Clinical and institutional variances in MIST utilization persist globally with little published research regarding MIST utilization in Canada. Therefore, the objective of this study was to survey MIST utilization in NICUs in Canada. Methods: An online survey was emailed to the 33 participating centres of Canadian Neonatal NetworkTM (CNN) Evidence-based Practice for Improving Quality (EPIQ) Lung Health Group (LHG). Site demographics and surfactant therapy procedural details were categorically collected. Free text and multiple-choice questions were utilized to capture perceived barriers and individual preferences for MIST use. Results: Twenty-eight of 33 participating members of the CNN EPIQ-LHG completed the survey between April 2021 and October 2021 (85%); 17/28 (61%) respondents reported ongoing MIST utilization at their center. Most centers that used MIST techniques administered bovine lipid extract surfactant (68%), commonly using angiocatheters (47%) and purpose-built catheters (41%). MIST was widely used for patients at 26-33 weeks gestational age (88%). Nine centres had never used MIST (32%), and 3 indicated a plan to implement MIST within the next 2 years. Common barriers to MIST use included lack of consensus amongst clinicians (78%), lack of training (56%), and lack of experience with MIST (56%). Conclusion: While MIST is being increasingly used in Canadian NICUs, universal use is yet to be seen. Clinician inexperience and lack of consensus, formal training, and local guidelines contribute to underutilization of MIST. Training workshops, country-wide data collection, and uniform operating protocols are needed to standardize practice.

Hyoscine butylbromide versus acetaminophen for nonspecific colicky abdominal pain in children: a randomized controlled trial.

BACKGROUND: Less than two-thirds of children with abdominal pain in the emergency department receive analgesia. We sought to determine whether hyoscine butylbromide was superior to acetaminophen for children with nonspecific colicky abdominal pain. METHODS: We randomly allocated children aged 8-17 years with nonspecific colicky abdominal pain who presented to the pediatric emergency department of London Health Sciences Centre, London, Ontario to receive hyoscine butylbromide, 10 mg given orally, or acetaminophen, 15 mg/kg given orally (maximum 975 mg). We considered the minimal clinically important difference for the primary outcome (self-reported pain at 80 min) to be 13 mm on a 100 mm visual analogue scale. Secondary outcomes included administration of rescue analgesia, adverse effects and pain score less than 30 mm at 80 minutes. RESULTS: A total of 236 participants (120 in the hyoscine butylbromide group and 116 in the acetaminophen group) were included in the trial. The mean visual analogue scale scores at 80 minutes were 29 mm (standard deviation [SD] 26 mm) and 30 mm (SD 29 mm) with hyoscine butylbromide and acetaminophen, respectively (adjusted difference 1, 95% confidence interval -7 to 7). Rescue analgesia was administered to 4 participants (3.3%) in the hyoscine butylbromide group and 1 participant (0.9%) in the acetaminophen groups (p = 0.2). We found no significant differences in rates of adverse effects between hyoscine butylbromide (32/116 [27.6%]) and acetaminophen (28/115 [24.3]) (p = 0.5); no serious adverse effects were observed. The proportion with a pain score less than 30 mm at 80 minutes was 66 (55.0%) with hyoscine butylbromide and 63 (54.3%) with acetaminophen (p = 0.9). INTERPRETATION: Hyoscine butylbromide was not superior to acetaminophen in this setting. Both agents were associated with clinically important pain reduction, and either can be considered for children presenting to the emergency department with nonspecific colicky abdominal pain. Trial registration: Clinicaltrials.gov, no. NCT02582307.

Video Discharge Instructions for Acute Otitis Media in Children: A Randomized Controlled Open-label Trial.

BACKGROUND: Thirty percent of children with acute otitis media (AOM) experience symptoms < 7 days after initiating treatment, highlighting the importance of comprehensive discharge instructions. METHODS: We randomized caregivers of children 6 months to 17 years presenting to the emergency department (ED) with AOM to discharge instructions using a video on management of pain and fever to a paper handout. The primary outcome was the AOM Severity of Symptom (AOM-SOS) score at 72 hours postdischarge. Secondary outcomes included caregiver knowledge (10-item survey), absenteeism, recidivism, and satisfaction (5-item Likert scale). RESULTS: A total of 219 caregivers were randomized and 149 completed the 72-hour follow-up (72 paper and 77 video). The median (IQR) AOM-SOS score for the video was significantly lower than paper, even after adjusting for preintervention AOM-SOS score and medication at home (8 [7-11] vs. 10 [7-13], respectively; p = 0.004). There were no significant differences between video and paper in mean (±SD) knowledge score (9.2 [±1.3] vs. 8.8 [±1.8], respectively; p = 0.07), mean (±SD) number of children that returned to a health care provider (8/77 vs. 10/72, respectively; p = 0.49), mean (±SD) number of daycare/school days missed by child (1.2 [±1.5] vs. 1.1 [±2.1], respectively; p = 0.62), mean (±SD) number of workdays missed by caregiver (0.5 [±1] vs. 0.8 [±2], respectively; p = 0.05), or median (IQR) satisfaction score (5 [4-5] vs. 5 [4-5], respectively; p = 0.3). CONCLUSIONS: Video discharge instructions in the ED are associated with less perceived AOM symptomatology compared to a paper handout.