New algorithms for automated phylogenetic reconstruction using artificial intelligence and data mining techniques

Academic and industrial research in the late 90s have brought about an exponential explosion of DNA sequence data. Automated expert systems are being created to help biologists to extract patterns, trends and links from this ever-deepening ocean of information. Two such systems aimed on retrieving and subsequently utilizing phylogenetically relevant information have been developed in this dissertation, the major objective of which was to automate the often difficult and confusing phylogenetic reconstruction process. ^ Popular phylogenetic reconstruction methods, such as distance-based methods, attempt to find an optimal tree topology (that reflects the relationships among related sequences and their evolutionary history) by searching through the topology space. Various compromises between the fast (but incomplete) and exhaustive (but computationally prohibitive) search heuristics have been suggested. An intelligent compromise algorithm that relies on a flexible “beam” search principle from the Artificial Intelligence domain and uses the pre-computed local topology reliability information to adjust the beam search space continuously is described in the second chapter of this dissertation. ^ However, sometimes even a (virtually) complete distance-based method is inferior to the significantly more elaborate (and computationally expensive) maximum likelihood (ML) method. In fact, depending on the nature of the sequence data in question either method might prove to be superior. Therefore, it is difficult (even for an expert) to tell a priori which phylogenetic reconstruction method—distance-based, ML or maybe maximum parsimony (MP)—should be chosen for any particular data set. ^ A number of factors, often hidden, influence the performance of a method. For example, it is generally understood that for a phylogenetically “difficult” data set more sophisticated methods (e.g., ML) tend to be more effective and thus should be chosen. However, it is the interplay of many factors that one needs to consider in order to avoid choosing an inferior method (potentially a costly mistake, both in terms of computational expenses and in terms of reconstruction accuracy.) ^ Chapter III of this dissertation details a phylogenetic reconstruction expert system that selects a superior proper method automatically. It uses a classifier (a Decision Tree-inducing algorithm) to map a new data set to the proper phylogenetic reconstruction method. ^

Corporate decision-making: A case study of decision support systems and financial performance in health care organizations

The purpose of this study was twofold: (1) To describe the relation of the intensity of DSS implementation to financial performance as an empirical exploration of improved performance at the organizational level. (2) To describe the relation of the intensity of DSS implementation to the type of organizational decision culture. A multiple case study design was utilized to compare three groups of paired cases. A pattern matching strategy was applied in this study. Four predictions were specified and compared to the empirical data. A progressively upward trend in the scores was predicted for the following theoretical relationships. (1) The greater the number of DSSs, the higher the sophistication index. (2) The greater the number of DSSs, the higher the financial ratios. (3) The greater the number of DSSs, the higher the culture score. (4) The higher the culture score, the higher the financial ratios. The data did not support any of the predicted trends except the relation between the number of DSSs and the financial ratios. The Income/Revenue ratio indicates the efficiency of a company's operations. One would expect that this ratio would be most affected by the operational and financial decision support systems. The majority of the systems measured in the study supported decisions tangential to the patient service areas. The evidence suggested that the type and number of decision support systems affects the bottom line. ^

A study of the relationship of support systems and adolescent pregnancy outcomes in an adolescent family life project

This study analyzed the relationship of family support systems and adolescent pregnancy outcomes. The population for the study was 390 adolescents who had attended the Marion County Health Department Adolescent Family Life Project in Indianapolis, Indiana during a two-year period.^ The study is unique in that it afforded the opportunity to compare adolescent pregnancy-related characteristics, of white and non-white adolescents in the same study.^ The pregnancy outcomes studied were: Infant birthweight, school attendance, and pregnancy recidivism.^ Significant results were found in the analysis that supported other research in regard to factors that are associated with school attendance when family support, adolescent's age, and ethnicity were controlled. Infant birthweight and repeat pregnancy outcome relationships were not found to have any consistently significant relationship with independent variables anticipated to be associated. However, the comparisons of infant birthweight among the adolescents with, and without, family support, by ethnicity resulted in some interesting findings. Repeat pregnancy proved an enigma, in that there seemed to be almost no variables in this study that were associated with the adolescent having a repeat pregnancy.^ Familial support in this study seemed to be of less importance as a factor in adolescent pregnancy outcomes than was ethnicity. The non-white adolescents in this study had a better record for remaining in school, both those non-white adolescents who lived with parents, and those who did not live with parents. More low birthweight occurred in the non-white adolescent, both those adolescents who lived with parents, and those who did not live with parents. Repeat pregnancy occurred more in the non-white adolescent whether she lived with parents, or did not live with parents. ^