[Prognosis for life expectancy using the inductive learning method].

M Rimac; J Kern

PubMed · 10377696

[Prognosis for life expectancy using the inductive learning method].

Abstract

The aim of this paper was to find out the possibility of life expectancy achievement (LEA) prognosis in open population by using epidemiological data, to improve it and to determine the differences between regions. We were using inductive learning software tool, ASSISTANT Professional, based on modified Quinlan's inductive learning method. Data from an epidemiological study of oil/fat consuming influence on diabetes incidence in different regions in Croatia, 1887 examinees, have been used. In spite of limited number of attributes that were available, an improvement in prognosis of LEA has been made by selecting the proper attributes and by changing the limiting values of attributes (values that change the meaning of attributes). We reached the absolute accuracy of 75.54%. Even after further pruning of decision tree that lowered this value, Assistant showed 13% better result than those of random selected outcome. Differences between regions were also established that could not been explained with attributes that were used. Expanding the list of attributes and analysis of their influence in particular region can make further improvement in prognosis of LEA.

Explore related subjects

Croatia Decision Trees Diabetes Mellitus Dietary Fats Epidemiologic Methods Humans Life Expectancy Middle Aged Prognosis Software English Abstract Journal Article

Keep this discovery

Explore connections, maps & timelines

BibTeX RIS

M Rimac, J Kern. [Prognosis for life expectancy using the inductive learning method].. https://pubmed.ncbi.nlm.nih.gov/10377696/

Cite the original work for its findings. Save a collection to share your selection of sources.

KEEP EXPLORING

Related citations

PubMed2003

The molecular basis of phenylalanine hydroxylase deficiency in Croatia.

We present the results of a comprehensive analysis of mutations, polymorphisms and haplotypes in the phenylalanine hydroxylase (PAH) gene in 39 Croatian families with phenylketonuria (PKU). A total of 21 disease-causing mutations was identified on 78 out of 79 independent chromosomes. The commonest mutation, R408W on haplotype 2 was found with a relative frequency of 37 %. P281L accounted for 11 %, R261Q and E390G each for 9 % of mutant chromosomes. There were three novel mutations: L249P (c.746T>C) in exon 7, IVS8+2T>C (c.912T>C) in intron 8, and F402L (c.1206T>G) in exon 12 of the PAH gene. Two known PKU mutations were found in cis on the same chromosome in one family, highlighting the need to perform full mutation scanning in recessive disease genes for molecular diagnosis even if two known mutations have been identified in a patient. This is the first comprehensive report on PKU mutations in southeastern Europe, adding to the growing bulk of molecular data for population genetic investigations.

Croatia↗

PubMed2003

The water quality of the Vrgorska Matica River.

The article presents the results of investigations carried out on the 42 km long Vrgorska Matica River, which flows through the 15 km long Vrgorsko polje (polje = field) which covers an area of 3000 ha, and is at 24 m a.s.l., located in Southern Croatia. It covers the years 1997-2000 after this field had been reclaimed for agricultural use. The purpose of the investigations was to evaluate the influence of the Vrgorska Matica River which is part of the catchment area of the Trebizat River, on the water quality in Modro Oko Lake and Prud Spring, which are used for water supply and are located downstream of the Vrgorska Matica River on the right bank of the Neretva River. The water quality was evaluated by using the quality index based on the following nine parameters: temperature, mineralization, corrosion coefficient, K = (Cl + SO4)/HCO3, dissolved oxygen, BOD5, total N, protein N, total phosphorus and total coliform bacteria (100 mL)-1 (MPN coli (100 mL)-1) for which concentrations C95 are calculated. After completing the nine parameters the results of C95 were recorded and transferred to the score table to obtain the q-value. The q-value used is an attempt to quantify environmental factors which would otherwise be qualitative. For each parameter the q-value was multiplied by a weighting factor based upon the relative significance of the parameter. The nine resulting scores values were then added to arrive at an overall water quality index (sigmaS95). According to this index the water can be classified into four categories. The first category, according to the Croatian Water Classification Act (Official Bulletin No. 77,1998), includes ground and surface waters used for drinking or in the food industry either in its natural state or after disinfection, and surface water used for raising high-quality species of fish, ranging from 85-100 scores; the second category includes water used in its natural state for swimming and recreation, sports or for other species of fish and the treated water used for drinking and other industrial purposes ranging between 70-85 scores. The third category includes water used in industry with no specific requests upon water quality and in agriculture ranging from 50-70 scores; the fourth category includes water used only after being treated in areas with water shortage which is less than 50 scores. According to results obtained by investigations, the water of the Vrgorska Matica River and Prud Spring falls into the second (II) category, while water from the Modro Oko Lake belongs to the first (I) category. This means that the Matica River water does not influence the water quality of the Modro Oko Lake. This lake water quality is influenced by the Rastocka Matica River from the Rastocko polje which is located upstream from the Vrgorska Matica River. This has been proved by dyeing tests.

Croatia↗

PubMed2003

Role of epidemiologic information system in sudden death prevention among Croatia's haemodialysis patients.

The main aim of Croatia's epidemiological information system is to enable the monitoring of infectious diseases as well as to enable necessary interventions. Its 24-hour epidemiologic alert mechanism made it possible for initial reports of sudden death clusters in haemodialysis units to reach epidemiologists on the night of 12 October 2001. The alert about the sudden deaths among haemodialysis patients in two hospitals has prompted us to do an epidemiological inquiry during that night and early the next morning. It looked at suspicions of a possible link between Baxter Plivadial P-15 lot 2001F075 dialyser and these deaths. As the suspicion was based on a small amount of data, it needed confirmation from a countrywide inquiry involving the other 40 haemodialysis units. A phone inquiry showed that 23 haemodialysis deaths occurred on 8-13 October 2001. It suggested that also dialyser of a different type and lot (P-18 2001B17R) should be incriminated. During the inquiry (October 13), all haemodialysis units were informed of the suspicions regarding incriminated dialysers, and of the necessity of temporary withdrawal of these from use. The withdrawal on 13 October of incriminated dialysers stopped the deaths among haemodialysis patients. No more such sudden deaths have been recorded since that could be linked either to the described period or to this clinical picture.

Croatia↗