Search

Use of machine learning (ML) in the early detection of developmental delay is possible through the analysis of infant motor skills, though the large number of potential indicators limits the speed at which the system can be trained. Body joint obstructions, the inability to infer aspects of movement such as muscle tone and volition, and the complexities of the home environment - confound machine learning's ability to distinguish between some motor items. To train the system efficiently requires using an excerpted list of validated items, a salient set, which uses only those motor items that are the 'easiest' to see and identify, while being the most highly correlated to a low/qualifying score. This work describes the examination of motor items, selection of 15 items that comprise the salient set, and the ability of the set to reliably screen for motor delay in the first-year infant., (Copyright © 2023 Elsevier B.V. All rights reserved.)

Background: Stroke incidence has fallen since 1950. Recent trends suggest that stroke incidence may be stabilizing or increasing. We investigated time trends in stroke occurrence and in-hospital morbidity and mortality in the Calgary Health Region., Methods: All patients admitted to hospitals in the Calgary Health Region between 1994 and 2002 with a primary discharge diagnosis code (ICD-9 or ICD-10) of stroke were included. In-hospital strokes were also included. Stroke type, date of admission, age, gender, discharge disposition (died, discharged) and in-hospital complications (pneumonia, pulmonary embolism, deep venous thrombosis) were recorded. Poisson and simple linear regression was used to model time trends of occurrence by stroke type and age-group and to extrapolate future time trends., Results: From 1994 to 2002, 11642 stroke events were observed. Of these, 9879 patients (84.8%) were discharged from hospital, 1763 (15.1%) died in hospital, and 591 (5.1%) developed in-hospital complications from pneumonia, pulmonary embolism or deep venous thrombosis. Both in-hospital mortality and complication rates were highest for hemorrhages. Over the period of study, the rate of stroke admission has remained stable. However, total numbers of stroke admission to hospital have faced a significant increase (p=0.012) due to the combination of increases in intracerebral hemorrhage (p=0.021) and ischemic stroke admissions (p=0.011). Sub-arachnoid hemorrhage rates have declined. In-hospital stroke mortality has experienced an overall decline due to a decrease in deaths from ischemic stroke, intracerebral hemorrhage and sub-arachnoid hemorrhage., Conclusions: Although age-adjusted stroke occurrence rates were stable from 1994 to 2002, this is associated with both a sharp increase in the absolute number of stroke admissions and decline in proportional in-hospital mortality. Further research is needed into changes in stroke severity over time to understand the causes of declining in-hospital stroke mortality rates.