Shigeki Yokoyama

Risk Mining in Medicine: Application of Data Mining to Medical Risk Management

Organizations in our modern society grow larger and more complex to provide advanced services due to the varieties of social demands. Such organizations are highly efficient for routine work processes but known to be not robust to unexpected situations. According to this observation, the importance of the organizational risk management has been noticed in recent years. On the other hand, a large amount of data on the work processes has been automatically stored since information technology was introduced to the organizations. Thus, it has been expected that reuse of collected data should contribute to risk management for large-scale organizations. This paper proposes risk mining, where data mining techniques were applied to detection and analysis of risks potentially existing in the organizations and to usage of risk information for better organizational management. We applied this technique to the following three medical domains: risk aversion of nurse incidents, infection control and hospital management. The results show that data mining methods were effective to detection of risk factors.

Mining Risk Information in Hospital Information Systems as Risk Mining

This paper focuses on application of data mining to medical risk management. To err is human. However, medical practice should avoid as many errors as possible to achieve safe medicine. Thus, it is a very critical issue in clinical environment how we can avoid the near misses and achieve the medical safety. Errors can be classified into the following three type of errors. First one is systematic errors, which occur due to problems of system and workflow. Second one is personal errors, which occur due to lack of expertise of medical staff. Finally, the third one is random error. The important point is to detect systematic errors and personal errors, which may be prevented by suitable actions, and data mining is expected as a tool for analysis of those errors. For this purpose, this paper proposes risk mining where data including risk information is analyzed by using data mining methods and mining results are used for risk prevention.

Extraction of Sectorial Episodes Representing Changes for Drug Resistance and Replacements of Bacteria

A sectorial episode is of the form Crarr r, where C is a set of events and r is an event. Katoh et al. (2006) have designed the algorithm SECT to extract all of the sectorial episodes that are frequent and accurate. In this paper, by applying the algorithm SECT to bacterial culture data, we extract sectorial episodes representing changes for drug resistance and replacements of bacteria.

Extracting sequential episodes representing replacements of bacteria from bacterial culture data

A sequential episode, which is the simplest form of serial episodes, is an episode of the form A → B. This sequential episode means that an event type A is precedent to an event type B. In this paper, we extract the sequential episodes representing the replacements of bacteria from Osaka Prefecture General Medical Center in year from 2000 to 2005.

Application of data mining to medical risk management

This paper proposes an application of data mining to medical risk management, where data mining techniques were applied to detection, analysis and evaluation of risks potentially existing in clinical environments. We applied this technique to the following two medical domains: risk aversion of nurse incidents and infection control. The results show that data mining methods were effective to detection and aversion of risk factors.

Risk mining for infection control

This paper proposes risk mining, where data mining techniques were applied to detection and analysis of risks potentially existing in the organizations and to usage of risk information for better organizational management. We applied this technique to the following two medical domains: risk aversion of nurse incidents and infection control. The results show that data mining methods were effective to detection of risk factors.

Extracting Propagation Patterns from Bacterial Culture Data in Medical Facility

In this paper, we formulate propagation patterns as the pairs of records in the same bacterial culture occurring within a fixed span in bacterial culture data. Then, we design the exhaustive search algorithm to extract all of the propagation patterns from bacterial culture data based on the extended principle of the 2-dimensional career map to determine whether two records in bacterial culture data belong to the same bacterial culture or the different ones. In particular, we focus on infectious propagation patterns, in which two patients are not identical, and they are in the same room and/or treated by the same physician. Finally, we give the experimental results to extract all of the propagation patterns and analyze them.

Temporal interrelations of bacteria based on the occurrence time

In this paper, for two different bacteria a and b, we introduce a temporal interrelation a ◃ b from a to b satisfying that the starting time of a is precedent to one of b. Also we introduce a sliding temporal interrelation satisfying that the ending time of a is precedent to one of b, and a non-overlapping temporal interrelation satisfying that the ending time of a is precedent to the starting time of b. Then, we extract such temporal interrelations from bacterial culture data provided from Osaka Prefectural General Medical Center in years from 2001 to 2007.

Aligned bipartite episodes between the genera of bacteria

An aligned bipartite episode between the genera of bacteria is of the form A → B, where A and B are the sets of genera of bacteria, satisfying that every genus in A has the same earliest occurrence time, every genus in B has the same earliest occurrence time, and the former is precedent to the latter. In this paper, we extract such aligned bipartite episodes from bacterial culture data provided from Osaka Prefectural General Medical Center in years from 1999 to 2007.

Attribute Selection Measures with Possibility and Their Application to Classifying MRSA from MSSA

In this paper, we investigate the construction of decision trees with possibility. First we introduce a threshold d of possibility (0 ≤ δ ≤ 1). Then, we formulate new measures for an attribute selection called a gain with possibility, a gain ratio with possibility and a GINI index with possibility. An intuitive idea for the gain and the gain ratio with possibility is that, for a probability p of the class +, the probability 1-p of the class - is replaced with max(d-p,0) and one for the GINI index with possibility that the value 1is replaced with d. Under the above new measures, we design a new algorithm to construct decision trees with possibility of which leaf is labeled by either d+ or −. Finally, we construct decision trees separating MRSA data from MSSA data in bacterial culture data by the new algorithm.