•Novel artificial intelligence identification tool for rare diseases registry.•Patient identification tool using big data analysis has 92.3% sensitivity.•The tool enables a centralized rare disease ...patient registry to be established.
Patient registries are crucial for rare disease management. However, manual registry construction is labor-intensive and often not user-friendly. Our goal is to establish Hong Kong’s first computer-assisted patient identification tool for rare diseases, starting with inborn errors of metabolism (IEM).
Patient data from 2010 to 2019 was retrieved from electronic databases. Through big data analytics, patient data were filtered based on specific IEM-related biochemical and genetic tests. Clinical notes were analyzed using a rule-based natural language processing technique called regular expression. The algorithm classified each extracted paragraph as “IEM-related” or “not IEM-related.” Pathologists reviewed the paragraphs for curation, and the algorithm’s performance was evaluated.
Out of 46,419 patients with IEM-related tests, the algorithm identified 100 as “IEM-related.” After pathologists’ validation, 96 cases were confirmed as true IEM, with 1 uncertain case and 3 false positives. A secondary ascertainment yielded a sensitivity of 92.3% compared to our previously published IEM cohort.
Our artificial intelligence approach provides a novel method to identify IEM patients, facilitating the creation of a centralized, computer-assisted rare disease patient registry at the local and national levels. This data can potentially be accessed by multiple stakeholders for collaborative research and to enhance healthcare management for rare diseases.
Schools were closed intermittently across Hong Kong to control the COVID-19 outbreak, which led to significant physical and psychosocial problems among children and youths.
To compare the clinical ...characteristics and sources of infection among children and youths with COVID-19 during the 3 waves of outbreaks in Hong Kong in 2020.
This cross-sectional study involved children and youths aged 18 years or younger with COVID-19 in the 3 waves of outbreaks from January 23 through December 2, 2020. Data were analyzed from December 2020 through January 2021.
Demographic characteristics, travel and contact histories, lengths of hospital stay, and symptoms were captured through the central electronic database. Individuals who were infected without recent international travel were defined as having domestic infections.
Among 397 children and youths confirmed with COVID-19 infections, the mean (SD) age was 9.95 (5.34) years, 220 individuals (55.4%) were male, and 154 individuals (38.8%) were asymptomatic. There were significantly more individuals who were infected without symptoms in the second wave (59 of 118 individuals 50.0%) and third wave (94 of 265 individuals 35.5%) than in the first wave (1 of 14 individuals 7.1%) (P = .001). Significantly fewer individuals who were infected in the second and third waves, compared with the first wave, had fever (first wave: 10 individuals 71.4%; second wave: 22 individuals 18.5%; third wave: 98 individuals 37.0%; P < .001) or cough (first wave: 6 individuals 42.9%; second wave: 15 individuals 12.7%; third wave: 52 individuals 19.6%; P = .02). Among all individuals, 394 individuals (99.2%) had mild illness. One patient developed chilblains (ie, COVID toes), 1 patient developed multisystem inflammatory syndrome in children, and 1 patient developed post-COVID-19 autoimmune hemolytic anemia. In all 3 waves, 204 patients with COVID-19 (51.4%) had domestic infections. Among these individuals, 186 (91.2%) reported having a contact history with another individual with COVID-19, of which most (183 individuals 90.0%) were family members. In the third wave, 18 individuals with domestic infections had unknown contact histories. Three schoolmates were confirmed with COVID-19 on the same day and were reported to be close contacts.
This cross-sectional study found that nearly all children and youths with COVID-19 in Hong Kong had mild illness. These findings suggest that household transmission was the main source of infection for children and youths with domestic infections and that the risk of being infected at school was small.
As another wave of COVID-19 outbreak has approached in July 2020, a larger scale COVID-19 pediatric Asian cohort summarizing the clinical observations is warranted. Children confirmed with COVID-19 ...infection from the Republic of Korea, the Hong Kong Special Administrative Region (HKSAR) and Wuhan, China, during their first waves of local outbreaks were included. Their clinical characteristics and the temporal sequences of the first waves of local paediatric outbreaks were compared. Four hundred and twenty three children with COVID-19 were analyzed. Wuhan had the earliest peak, followed by Korea and HKSAR. Compared with Korea and Wuhan, patients in HKSAR were significantly older (mean age: 12.9 vs. 10.8 vs. 6.6 years, p < 0.001, respectively) and had more imported cases (87.5% vs. 16.5% vs. 0%, p < 0.001, respectively). The imported cases were also older (13.4 vs. 7.6 years, p < 0.001). More cases in HKSAR were asymptomatic compared to Korea and Wuhan (45.5% vs. 22.0% vs. 20.9%, p < 0.001, respectively), and significantly more patients from Wuhan developed fever (40.6% vs. 29.7% vs. 21.6%, p=0.003, respectively). There were significantly less imported cases than domestic cases developing fever after adjusting for age and region of origin (p = 0.046). 5.4% to 10.8% of patients reported anosmia and ageusia. None developed pediatric multisystem inflammatory syndrome temporally associated with SARS-CoV-2 (PMIS-TS). In general, adolescents were more likely to be asymptomatic and less likely to develop fever, but required longer hospital stays. In conclusion, majority patients in this pediatric Asian cohort had a mild disease. None developed PIMS-TS. Their clinical characteristics were influenced by travel history and age.