Affiliations Robarts Research Institute, University of Western Ontario, London, ON, Canada, CIARS (Centre for Intelligent Antenna and Radio Systems), Department of Electrical and Computer Engineering, University of Waterloo, Waterloo, ON, Canada
Auto-generated profile, based on publicly available information
Ehsan Kamrani
Affiliations Robarts Research Institute, University of Western Ontario, London, ON, Canada, CIARS (Centre for Intelligent Antenna and Radio Systems), Department of Electrical and Computer Engineering, University of Waterloo, Waterloo, ON, Canada
Early prediction of patient mortality risks during a pandemic can decrease mortality by assuring efficient resource allocation and treatment planning. This study aimed to develop and compare prognosis prediction machine learning models based on invasive laboratory and noninvasive clinical and demographic data from patients’ day of admission. Three Support Vector Machine (SVM) models were developed and compared using invasive, non-invasive, and both groups. The results suggested that non-invasive features could provide mortality predictions that are similar to the invasive and roughly on par with the joint model. Feature inspection results from SVM-RFE and sparsity analysis displayed that, compared with the invasive model, the non-invasive model can provide better performances with a fewer number of features, pointing to the presence of high predictive information contents in several non-invasive features, including SPO2, age, and cardiovascular disorders. Furthermore, while the invasive model was able to provide better mortality predictions for the imminent future, non-invasive features displayed better performance for more distant expiration intervals. Early mortality prediction using non-invasive models can give us insights as to where and with whom to intervene. Combined with novel technologies, such as wireless wearable devices, these models can create powerful frameworks for various medical assignments and patient triage.
24 April 2014 in Journal of the Marine Biological Association of the United Kingdom
In a study of the age and growth of Platycephalus indicus, a total of 1106 fish were collected from May 2011 to March 2012 in the coastal waters of Iran, Persian Gulf. The ages of 279 specimens were determined by sectioned otoliths. The ages of the females were estimated to be between 0+ to 7+ , while the ages of the males were from 0+ to 4+. The von Bertalanffy growth curve was well suited to the age/total length data of males and females as follows: Lt = 43.40{1–exp[−0.45(t + 0.328)]} for males, and Lt = 63 {1–exp[−0.50(t + 0.30)]} for females. linf = 43.40, k = 0.45, t0 = −0.328 for females and linf = 63, k = 0.50, t0 = −0.30 for males. The estimated values of natural mortality (M) were M = 0.886 yr−1 for females and 0.736 yr−1 for males, and the estimated Z values were 1.43 yr−1 for females and 1.62 yr−1 for males. The mean value of the gonadosomatic index for males and females was 0.82 ± 0.25 and 2.48 ± 0.59, respectively, in each year. The mean values of the hepatosomatic index (HSI) were 0.89 ± 0.20 for males and 1.28 ± 0.16 for females. The highest HSI values for this location were observed in January, and the lowest were in April.
17 February 2019 in Journal of Applied Ichthyology
This study presents length‐weight relationships (LWRs) of Liza klunzingeri (Day, 1888), Cociella crocodilus (Cuvier, 1829), Platycephalus indicus (Linnaeus, 1758) belonging to two Families (Mugilidae and Platycephalidae) from northern coastline of Gulf of Oman (Hormozgan province). Samples were collected by artisanal trawl and beach seine (both with 11 mm effective mesh size) monthly during 2010 to 2015. The presented models were highly significant (p < 0.01) with a reliable coefficient of determination (R2 > 0.90) that provides a reliable basic information for ichthyologists and fisheries scientists.
With no effective treatment currently available and maximum preventive measures already in place, more interventions in the clinical field are needed to decrease COVID-19 patient mortality. Early prediction of mortality risk in COVID-19 patients can decrease mortality by assuring efficient resource allocation and treatment planning. This study conducts an early prediction of COVID-19 prognosis using laboratory, clinical, and demographic data collected from patients in the first day of admission. Three machine learning models were developed to investigate and compare the prediction power of invasive and noninvasive biomarkers. The results suggest that early mortality prediction of patients via non-invasive biomarkers provides significant accuracy and can be used as a triage assisting tool without the need for additional costs or waiting time of laboratory tests.
The relationships between somatic growth and otolith dimensions, otolith size to estimated age and growth parameters of the tigertooth croaker (Otolithes ruber) were investigated in 100 specimens (size range: 19.1–52.0 cm, total length) from the Oman Sea area, September 2014. All 100 otoliths were sectioned and determined by age. The oldest specimen was a 4.5-year-old female with a total length of 40.6 cm; the youngest specimen was also a female estimated at 1 year of age with a total length of 19.1 cm. The von Bertalanffy growth equation was estimated as Lt = 54.70 (1 − exp (−0.37 (t + 0.21))). Concluded was that there is a significant relationship between body size, otolith dimensions and estimated age of Otolithes ruber.