In order to set an adequate lifetime target for each market, quantitative evaluation of variation of lifetime characteristics is required. In particular, the lifetime of vehicle unit depends heavily on customer’s usage (e.g. gross vehicle weight, road gradient, acceleration operation). We thus have developed an online monitoring system that continually collects some information such as usage and environmental conditions. A method has been developed for predicting vehicle component lifetimes using data from an online monitoring system that collects an extensive amount of data during vehicle operation. The linear model used for prediction takes into account variations in usage conditions and models data as covariates. The prediction procedure was generalized to enable it to make predictions using a new data sample. The large amount of information on usage and environmental conditions obtained with the online monitoring system enabled the usage of each sample to be quantified and treated as a stratification factor. A stratified analysis produced fairly accurate results, meaning that using online monitoring data should be useful for lifetime prediction.
To operate successfully, surgeons must plan surgical operations appropriately. However, it is difficult to plan operations adequately because they are often complicated and involve substantial amounts of medical knowledge and information concerning patients. Therefore, it is necessary to develop a process model for surgical operation planning.
In the present study, we divided surgical operation planning into three processes, “Process for understanding the patient’s condition,” “Process for designing the surgical operation plan,” and “Process for reviewing the plan.” We identified that an ideal surgery is one that can lead to a radical cure, and can minimize the adverse effect on the QOL of the patient. Based on this, we designed the basic concept of the best surgical operation plan, and developed a process model to facilitate its use. We first identified the components of surgical operation plan and information necessary to the processes for understanding and designing. We then identified functions of the processes and visualized information and functions with a data flow diagram. Finally, we developed a tool for quality assurance in planning, and tested the model by applying it to 9 cases. Subsequently, we proved that the model marshaled the complex process and facilitated the retrospective detection of problems.
The intent of robust parameter design is to make a system insensitive to noise factors by choosing optimum levels for the controllable factors. This is conducted by finding the interactions between noise factors and control factors. In general, it is necessary to control the levels of noise factors; however, there are some that cannot be controlled. On the other hand, there are some which can be observed as covariates.
Hirano and Miyakawa (2007) proposed a method based on linear regression to analyze the interactions between a single noise factor and the control factors, when the noise factor is observed as a covariate.
This paper discusses robust parameter designs when multiple noise factors are observed as covariates. We propose two extensions of the Hirano and Miyakawa method: extended methods 1 and 2. We perform Monte Carlo simulations under several data models to estimate the accuracy of these methods. It is shown that the extended methods are able to analyze the interactions between each of the control factors and the noise factors, when multiple noise factors are observed as covariates. Since the noise factors are combined in extended method 1, it cannot detect which noise factor influences the control factors. On the other hand, extended method 2 distinguishes between noise factors, and thus it can detect the interactions between the control factors and each of the noise factors.
In these days, online monitoring becomes a common tool for keeping highly reliability of products and systems. The online monitoring information which includes usage history, system conditions, and environmental conditions is reported and stored as big data. On statistical modeling, these variables from the online monitoring are primary candidates for covariates which affect the failure mechanism. There is some literature on modeling by the cumulative exposure model for the products lifetime distribution with covariate effects. The existing literatures require the already known parametric baseline distribution of the cumulative exposure. However such knowledge may be difficult to acquire in advance in some cases. When an incorrect baseline distribution is assumed, it is called misspecification. This paper proposes the strategy which use a likelihood function under a log-normal distribution to estimate parameters which represent covariate effects when the truly underlying baseline distribution is either a Weibull distribution or a log-normal distribution. In this paper, it is derived that the score function of a likelihood function under a log-normal baseline distribution is identified as the approximation for a Weibull cases. Besides, the simulation study and the discussion for the bias of estimation are shown, and this paper clarify the relationship among distribution parameters and the bias of estimation under misspecification.
Medical accidents are typically classified into two types: accidents caused by healthcare staff while providing services, and accidents caused by patients. Among the latter type, patient falls account for a significant percentage, and have a significant impact on patients. The goal of our research here is to establish a methodology to prevent patient falls by identifying situations that are dangerous for patients and formulating concrete countermeasures based on the results of an assessment to prevent such situations from arising.
Kato et al. (2013b) evaluated risk factors, those are included in the existing assessment sheet, through Cox regression analysis by using data from approximately 1,000 cases at Iizuka Hospital, located in Fukuoka Prefecture. However, the number of this dataset was insufficient for a detailed analysis. It was also needed to arrange the data format and consult models for recurrent event analysis. Furthermore, the statistical model and covariates need to be considered in detail.
In this paper, we tried to statistically model patient falls based on multivariate analysis by using a logistic model, the Cox model, and models for recurrent events. We first discussed the statistical model as well as the covariates to be included in it. We then developed a multiple scoring system based on the results of multivariate analysis by using data from Iizuka Hospital from 2009 to 2011. Finally, we evaluated each scoring system by calculating the correlation between scores and probability of events.