Workforce Shortage for Retinopathy of Prematurity Care and Emerging Role of Telehealth and Artificial Intelligence

Quality Indices and Outcomes of a Neonatology Telerounding Program in a Level II Neonatal Intensive Care Unit: Single-Center Experience during the COVID-19 Pandemic

OBJECTIVE

 The objective of this program evaluation was to describe the outcomes of daily neonatologist telerounding with the onsite advanced practice provider (APP) in a Level II neonatal intensive care unit (NICU), before and during the coronavirus disease 2019 (COVID-19) pandemic.

STUDY DESIGN

 Bedside telerounding occurred with an onsite APP using a telehealth cart and paired Bluetooth stethoscope. Data collected by longitudinal and cross-sectional surveys and chart review before (May 2019-February 2020) and during (March 2020-February 2021) the COVID-19 pandemic were analyzed using descriptive statistics and thematic analysis.

RESULTS

 A total of 258 patients were admitted to the Level II NICU before (May 2019-February 2020) and during (March 2020-February 2021) the COVID-19 pandemic. Demographic characteristics and outcomes, including breastfeeding at discharge and length of stay were similar pre- and postonset of the COVID-19 pandemic. Postrounding surveys by 10 (response rate 83%) neonatologists indicated parents were present in 80 (77%) of rounds and video was at least somewhat helpful in 94% of cases. Cross-sectional survey responses of 23 neonatologists and APPs (response rate 62%) indicated satisfaction with the program. Common themes on qualitative analysis of open-ended survey responses were "need for goodness of fit" and "another set of eyes" and "opportunities for use."

CONCLUSION

 Daily telerounding with neonatologists and APPs in a Level II NICU supported neonatal care. Quality metrics and clinical outcomes are described with no differences seen before and during the COVID-19 pandemic.

KEY POINTS

· Little is known about Level II NICU quality metrics and outcomes.. · Daily bedside telerounding with neonatologists and APPs is described.. · Telerounding supported neonatal care before and during the COVID-19 pandemic.. · Neonatologists found visual exam helpful in the majority of cases.. · No differences in NICU clinical outcomes were seen during the COVID-19 pandemic..

Diagnostic Accuracy of Pediatrician-performed Digital Retinal Imaging with 3nethra neo for ROP Screening

OBJECTIVES

To evaluate the accuracy of pediatrician-performed wide-field digital retinal imaging (WFDRI) for diagnosing Retinopathy of prematurity (ROP), as compared to binocular indirect ophthalmoscopy (BIO) as the reference standard.

METHODS

Eligible infants undergoing ROP screening were enrolled consecutively. BIO was performed by trained ophthalmologists, followed by WFDRI (using "3nethra neo" camera) by a pediatrician. An expert pediatric ophthalmologist reviewed de-identified images for quality, presence, and severity of ROP. She was masked to the findings of BIO and the pediatrician. Diagnostic accuracy for detecting any ROP, ROP requiring treatment (Type 1), and ROP requiring referral (Type 1 or 2) were calculated for WFDRI, considering BIO as the reference standard.

RESULTS

The analysis included 427 eyes. The sensitivity, specificity, positive likelihood ratio (PLR), negative likelihood ratio (NLR), diagnostic accuracy, and diagnostic odds ratio of WFDRI were 0.88 (95% CI: 0.81, 0.93), 0.89 (0.85, 0.92), 7.8 (5.7, 10.9), 0.14 (0.09, 0.21), 0.89 (0.85, 0.91), and 58.3 (31, 110) respectively for detection of 'any ROP'. For detecting ROP requiring treatment (Type 1), the sensitivity, specificity, NLR, and diagnostic accuracy were 0.90 (0.75, 0.97), 1.00 (0.99, 1.00), 0.11 (0.04, 0.27), and 0.99 (0.98, 1.00) respectively. For ROP requiring referral, the sensitivity, specificity, NLR, and diagnostic accuracy of pediatrician-performed WFDRI were 0.92 (0.80, 0.98), 1.00 (0.99, 1.00), 0.08 (0.03, 0.21), and 0.99 (0.98, 1.00) respectively. No serious adverse events were noted. The pediatrician and ophthalmologist had a near-perfect (k-1.00) and strong (k-0.88) agreement for ROP requiring treatment and any ROP, respectively.

CONCLUSIONS

Pediatrician-performed WFDRI is feasible, safe, and has excellent diagnostic accuracy for identifying ROP requiring treatment.

The incidence of retinopathy of prematurity in neonates in Germany in 2019; a nationwide epidemiological cohort study

Retinopathy of prematurity (ROP) is a leading cause of childhood blindness in preterm infants. The incidence of ROP varies widely across countries, with rates as high as 30% in some regions. This study investigated the incidence, risk factors, treatment, and mortality of ROP patients in Germany. Data were extracted from the German Federal Statistical Office (Destatis) diagnosis-related group (DRG) and Institute for the Remuneration System in Hospitals (InEK) databases. Patients with a secondary diagnosis of ROP (ICD-10 code H35.1) in the first 28 days of life were included. Data were extracted for patients admitted between January 1, 2019 and December 31, 2019. The diagnoses and procedures were determined using the German version of the International Classification of Diseases (ICD-10-GM) and the German procedure coding system (OPS). The codes 5-154.xx, 5-155.xx, 8-020.xx, 5-156.9, 6-003.(c&d), 6-007.(2&8) were utilised to denote different ocular treatments. Patient Clinical Complexity Levels were extracted and used to compare ROP with non-ROP patients. A total of 1326 patients with ROP were identified. The incidence of ROP is estimated to be 17.04 per 10,000 live births. The incidence was highest in infants with birth weights less than 500 g and decreased with increasing birth weight. The most common risk factors for ROP were low birth weight, male sex, and prematurity. Of the infants with ROP, 7.2% required ocular treatment. The most common treatment was intraocular injections, followed by photocoagulation. No surgical treatment was required for any of the infants during the study period. The mortality rate for infants with ROP was 60.33 per 10,000. This is higher than the overall neonatal death rate of 24.2 per 10,000.

CONCLUSIONS

This study found that the incidence of ROP in Germany is similar to that in other developed countries. The study also found that the mortality rate for infants with ROP is higher than the overall neonatal death rate. These findings highlight the importance of early detection and treatment of ROP in preterm infants.

WHAT IS KNOWN

• ROP is a severe eye condition often affecting preterm infants. • Previous data are limited in scope and generalizability.

WHAT IS NEW

• Based on a national database, our study found ROP incidence to be 17.04 per 10,000 new births, higher in males (17.71) than in females (16.34). • 7.2% of ROP cases required ocular treatment, inversely correlated with birth weight. • High rates of multimorbidity such as neonatal jaundice (84.69%), respiratory distress syndrome (80.84%), and apnea (78.88%) were observed.

The past, current, and future of neonatal intensive care units with artificial intelligence: a systematic review

Machine learning and deep learning are two subsets of artificial intelligence that involve teaching computers to learn and make decisions from any sort of data. Most recent developments in artificial intelligence are coming from deep learning, which has proven revolutionary in almost all fields, from computer vision to health sciences. The effects of deep learning in medicine have changed the conventional ways of clinical application significantly. Although some sub-fields of medicine, such as pediatrics, have been relatively slow in receiving the critical benefits of deep learning, related research in pediatrics has started to accumulate to a significant level, too. Hence, in this paper, we review recently developed machine learning and deep learning-based solutions for neonatology applications. We systematically evaluate the roles of both classical machine learning and deep learning in neonatology applications, define the methodologies, including algorithmic developments, and describe the remaining challenges in the assessment of neonatal diseases by using PRISMA 2020 guidelines. To date, the primary areas of focus in neonatology regarding AI applications have included survival analysis, neuroimaging, analysis of vital parameters and biosignals, and retinopathy of prematurity diagnosis. We have categorically summarized 106 research articles from 1996 to 2022 and discussed their pros and cons, respectively. In this systematic review, we aimed to further enhance the comprehensiveness of the study. We also discuss possible directions for new AI models and the future of neonatology with the rising power of AI, suggesting roadmaps for the integration of AI into neonatal intensive care units.

A MULTICENTER STUDY OF RETINOPATHY OF PREMATURITY FOLLOW-UP ADHERENCE

PURPOSE

Characterize clinical and socioeconomic factors that impact follow-up to complete retinal vascularization and subsequent pediatric ophthalmology follow-up in neonates with retinopathy of prematurity.

METHODS

Medical records of 402 neonates diagnosed with retinopathy of prematurity from neonatal intensive care units at the University of California, Los Angeles Mattel Children's Hospital and the University of California, Los Angeles Santa Monica Hospital, both academic medical centers, and the Harbor-University of California, Los Angeles Medical Center, a safety-net county hospital, were reviewed. Primary study outcomes were the rate of follow-up to complete retinal vascularization and adequate pediatric ophthalmology follow-up. Secondary outcome was the rate of nonretinal ocular comorbidity.

RESULTS

In whole-cohort analysis, 93.6% of neonates were followed to complete retinal vascularization, and 53.5% had adequate pediatric ophthalmology follow-up. Public insurance was associated with lower rates of pediatric ophthalmology follow-up (Odds ratio 0.66, 95% confidence interval 0.45-0.98, P = 0.04). Participants screened at the academic medical center had lower rates of pediatric ophthalmology follow-up compared with the safety-net county hospital (50.7% vs. 63.5%, P = 0.034). In subgroup analysis, academic medical center participants with public insurance were less likely to have pediatric ophthalmology follow-up than safety-net county hospital participants with public insurance (36.5% vs. 63.8%, P < 0.001) or those with private insurance at the academic medical center (36.5% vs. 59.2%, P< 0.001).

CONCLUSION

This study identified high follow-up rates to complete retinal vascularization, lower pediatric ophthalmology follow-up rates, and nonretinal ocular comorbidity at all hospitals. Insurance status relative to hospital type was identified as a risk factor for loss to follow-up. This demonstrates a need to further study health care disparities in retinopathy of prematurity infants.

Telemedicine retinopathy of prematurity severity score (TeleROP-SS) versus modified activity score (mROP-ActS) retrospective comparison in SUNDROP cohort

Identifying and planning treatment for retinopathy of prematurity (ROP) using telemedicine is becoming increasingly ubiquitous, necessitating a grading system to help caretakers of at-risk infants gauge disease severity. The modified ROP Activity Scale (mROP-ActS) factors zone, stage, and plus disease into its scoring system, addressing the need for assessing ROP's totality of binocular burden via indirect ophthalmoscopy. However, there is an unmet need for an alternative score which could facilitate ROP identification and gauge disease improvement or deterioration specifically on photographic telemedicine exams. Here, we propose such a system (Telemedicine ROP Severity Score [TeleROP-SS]), which we have compared against the mROP-ActS. In our statistical analysis of 1568 exams, we saw that TeleROP-SS was able to return a score in all instances based on the gradings available from the retrospective SUNDROP cohort, while mROP-ActS obtained a score of 80.8% in right eyes and 81.1% in left eyes. For treatment-warranted ROP (TW-ROP), TeleROP-SS obtained a score of 100% and 95% in the right and left eyes respectively, while mROP-ActS obtained a score of 70% and 63% respectively. The TeleROP-SS score can identify disease improvement or deterioration on telemedicine exams, distinguish timepoints at which treatments can be given, and it has the adaptability to be modified as needed.

Research progress on diagnosing retinal vascular diseases based on artificial intelligence and fundus images

As the only blood vessels that can directly be seen in the whole body, pathological changes in retinal vessels are related to the metabolic state of the whole body and many systems, which seriously affect the vision and quality of life of patients. Timely diagnosis and treatment are key to improving vision prognosis. In recent years, with the rapid development of artificial intelligence, the application of artificial intelligence in ophthalmology has become increasingly extensive and in-depth, especially in the field of retinal vascular diseases. Research study results based on artificial intelligence and fundus images are remarkable and provides a great possibility for early diagnosis and treatment. This paper reviews the recent research progress on artificial intelligence in retinal vascular diseases (including diabetic retinopathy, hypertensive retinopathy, retinal vein occlusion, retinopathy of prematurity, and age-related macular degeneration). The limitations and challenges of the research process are also discussed.

LGBTQ+ Identity and Ophthalmologist Burnout

PURPOSE

To evaluate lesbian, gay, bisexual, transgender, questioning, and other sexual/gender minority (LGBTQ+) orientation as a burnout risk factor among an international ophthalmologist cohort.

METHODS

An anonymous, cross-sectional electronic survey was distributed via an Internet platform to characterize the relationship among demographic factors, including LGBTQ+ orientation, and burnout as measured by the Copenhagen Burnout Inventory (CBI). Univariable data analysis (linear) by sexual orientation was performed and variables with an association with a P value of <0.15 in univariable analysis were included in the multiple linear regression modeling.

RESULTS

A total of 403 ophthalmologists participated in the survey. The majority self-identified as "White" (69.2%), were from North America (72.0% United States, 18.6% Canada) and were evenly distributed between age of 30 and 65 years. Overall, 13.2% of participants identified as LGBTQ+ and 98.2% as cisgender. Approximately 12% had witnessed or experienced LGBTQ+-related workplace discrimination or harassment. The personal and work-related burnout scores and confidence limits of persons identified as LGBTQ+ were higher and nonoverlapping compared with those reported as non-LGBTQ+. Multivariable analysis identified significant risk factors for higher personal and work-related burnout scores: LGBTQ+ (11.8 and 11.1, P = .0005 and .0023), female gender (5.36 and 4.83, P = .0153 and .0434), older age (19.1 and 19.2, P = .0173 and .0273). and caretaker stress (6.42 and 5.97, P = .0085 and .0239).

CONCLUSIONS

LGBTQ+ orientation is a burnout risk factor among ophthalmologists, and LGBTQ+ workplace discrimination may be a contributing factor. Support from ophthalmology organizations to address LGBTQ+-, gender-, and age-related workplace discrimination may decrease burnout. NOTE: Publication of this article is sponsored by the American Ophthalmological Society.

Identification of treatment-warranted retinopathy of prematurity by neonatal nurse specialist

OBJECTIVE

To determine the accuracy in the identification of infants with treatment-warranted retinopathy of prematurity (ROP) by a trained and experienced ROP neonatal nurse specialist compared with skilled ophthalmologists.

METHODS

A single-centre, prospective, blinded, agreement study was performed on a cohort of infants undergoing ROP screening. An experienced ROP neonatal nurse specialist obtained retinal images using a wide field digital retinal imaging system (WFDRI) on 127 infants and identified those with treatment-warranted ROP. This interpretation was compared with the interpretation of the same images by skilled ophthalmologists. The accuracy of the ROP nurse specialist's interpretation was assessed for sensitivity and specificity compared with the gold standard interpretation by the ophthalmologists.

RESULTS

The ROP nurse specialist performed 345 ROP screens on both eyes of 127 infants. The mean (SD) gestation age (weeks) and birth weight (g) of the infants screened was 26.8 (2.8) and 929 (327), respectively. The nurse specialist correctly identified all 8 infants with treatment-warranted ROP and 118/119 infants without. The sensitivity and specificity (95% CI) of ROP screening episodes were 100% (63% to 100%) and 99.7% (98.4% to 100.0%), respectively.

CONCLUSION

A trained and experienced ROP neonatal nurse specialist can correctly identify infants with treatment-warranted ROP using WFDRI. Further work is required to examine the generalisability of this finding and its impact on ROP screening services.

Remote Stewardship for Medically Underserved Nurseries: A Stepped-Wedge, Cluster Randomized Study

BACKGROUND AND OBJECTIVES

Antibiotic overuse is associated with adverse neonatal outcomes. Many medically underserved centers lack pediatric antibiotic stewardship program (ASP) support. Telestewardship may mitigate this disparity. Authors of this study aimed to determine the effectiveness and safety of a nursery-specific ASP delivered remotely.

METHODS

Remote ASP was implemented in 8 medically underserved newborn nurseries using a stepped-wedge, cluster-randomized design over 3 years. This included a 15-month baseline period, a 9-month "step-in" period using random nursery order, and a 12-month postintervention period. The program consisted of education, audit, and feedback; and 24/7 infectious diseases provider-to-provider phone consultation availability. Outcomes included each center's volume of antibiotic use and the proportion of infants exposed to any antibiotics. Safety measures included length of stay, transfer to another facility, sepsis, and mortality.

RESULTS

During the study period, there were 9277 infants born (4586 preintervention, 4691 postintervention). Infants exposed to antibiotics declined from 6.2% pre-ASP to 4.2% post-ASP (relative risk 0.68 [95% confidence interval, 0.63% to 0.75%]). Total antibiotic use declined from 117 to 84.1 days of therapy per 1000 patient-days (-28% [95% confidence interval -22% to -34%]. No safety signals were observed. Most provider-to-provider consultations were <5 minutes in duration and occurred during normal business hours.

CONCLUSIONS

The number of infants exposed to antibiotics and total antibiotic use declined in medically underserved nurseries after implementing a remote ASP. No adverse safety events were seen, and the remote ASP time demands were manageable. Remote stewardship may be a safe and effective strategy for optimizing antibiotic use in medically underserved newborn nurseries.

Simulating Telehealth Experiences in the Neonatal Care Environment: Improving Access to Care

Telehealth in the neonatal environment can improve remote medical care and access to specialized care and training eliminating barriers for effective health care delivery. Clinicians are utilizing telehealth in their practice to provide specialized care and training in areas that have little access. Educating health care clinicians on the basics of telehealth is an essential component of clinical training programs. Use of simulation-based telehealth experiences as part of that training can provide hands-on learning in a safe, realistic environment. Simulation can prepare health care teams in using telehealth technology in managing patient care, postdischarge care, and specialized care programs.