Diagnostic Medical Information Research Articles

Distinguishing Septal Heart Defects from the Valvular Regurgitation Using Intelligent Phonocardiography.

This paper presents an original machine learning method for extracting diagnostic medical information from heart sound recordings. The method is proposed to be integrated with an intelligent phonocardiography in order to enhance diagnostic value of this technology. The method is tailored to diagnose children with heart septal defects, the pathological condition which can bring irreversible and sometimes fatal consequences to the children. The study includes 115 children referrals to an university hospital, consisting of 6 groups of the individuals: atrial septal defects (10), healthy children with innocent murmur (25), healthy children without any murmur (25), mitral regurgitation (15), tricuspid regurgitation (15), and ventricular septal defect (25). The method is trained to detect the atrial or ventricular septal defects versus the rest of the groups. Accuracy/sensitivity and the structural risk of the method is estimated to be 91.6%/88.4% and 9.89%, using the repeated random sub sampling and the A-Test method, respectively.

Demographics and Costs of Colic in Swedish Horses

Colic is an important cause of morbidity and mortality in horses. In Sweden, an insurance database with diagnostic medical information is maintained on >30% of the nation's horse population. The objective was to describe the occurrence of colic, defined by costly veterinary care and life claims, in horses at 1 insurance company during 1997-2002. HORSES: All horses (<21 years of age) with complete insurance for veterinary care and life during the period 1997-2002 were included. Colic was defined as conditions where the main clinical sign was abdominal pain and the problem was related to the gastrointestinal system. The analyses included measures of incidence by sex, breed group, age categories, geographical location (urban/other), survival to and survival after colic, medical cost for colic, and multivariable modeling of risk factors related to the event of colic. In all, 116,288 horses contributed to 341,564 horse years at risk (HYAR). There were 3,100 horses with a colic diagnosis, of which 27% were settled for life insurance. The median gross cost for veterinary care was 4,729 Swedish Kronor (SEK). The overall occurrence and mortality rate of colic was 91 and 24 events per 10,000 HYAR. Survival after colic at 1 month was 76% (95% confidence interval: 75-78%). The occurrence of colic varied with breed group, age, and season. The mortality rates probably reflected the true mortality of colic. The veterinary care rates most likely underestimated of the risk colic because they represent relatively costly events.