Mapping techniques for document processing

An information retrieval system should provide references to the set of documents the user must evaluate in order to satisfy his/her information requirements. A major concern in this evaluation process is whether or not a document meets the user's needs. In many document retrieval systems there is no relevant information regarding the content of the documents. This makes it very difficult to evaluate if a document is relevant to the user's initial query. This suggests the need for a method to compare the documents on a word by word basis. Fully automated methods are too complex and difficult to generalize upon. A semiautomated user driven method for document mapping is described in this paper. It should decrease the amount of time required to validate the information content of a query.     

基于双层相似度的协同过滤推荐算法

针对由于用户评价矩阵的数据稀疏性而导致推荐精度和准确率不高的问题,提出了一种基于双层相似度的协同过滤算法。经典算法通过改进某一种相似度或者混合相似度来提高推荐精度和准确度,本文对此进行了改进,将最近邻相似度和最近评分相似度两个概念进行区分,采用双层相似度来寻找这两个概念层次的邻居。第1层用来寻找与用户行为偏好的最近邻居,基于用户共同评价行为和差异行为的对数似然比及用户物品属性偏好相似性来实现。第2层用来寻找在评分意义上的最近评分邻居,通过改进的皮尔森相似度衡量用户评分上的相似性,给用户未知的物品进行评分预测。在Movielens数据集上的实验结果表明,本文算法能够快速排除干扰找到用户邻居,极大地提高了推荐系统的精确度、准确率。     

The design and structure of clinical research information systems

Data management software designed to support clinical data bases typically provides the user with the ability to “enter” and “retrieve” information according to simple user-specified criteria. In the medical research environment, such data base management systems can be self-limiting unless the user has carefully structured the data base schema to be consistent with subsequent statistical procedures used for analysis. For statistical purposes, the data base schema must be configured such that the dependent and independent variables are structurally situated to facilitate the use of statistical application programs. Furthermore, the analysis of time-oriented, prospective studies often requires the data base to be “relational.” This may be inconsistent with data collection procedures that result in “hierarchical” schemata. Methodology for ensuring compatibility between the data base schema and subsequent statistical analyses is presented using examples derived from a multicenter clinical trial of diabetes and an observational data bank approach to disease surveillance in rheumatology.     

用户期望质量驱动的Web服务优化选取

提出了一种基于用户期望的服务质量评价方法。该评价方法仅考虑具有相似期望的用户,允许期望相似的评价影响服务的信誉度评价,以利于得到客观、准确的服务质量评估。在此基础上,提出一种基于用户期望的QoS驱动的服务选取算法。该算法实现了在满足用户偏好和期望的前提下Web服务的最优选取。电子购物的实例展示了该方法的可行性。     

A Gesture-based Tool for Sterile Browsing of Radiology Images

The use of doctor-computer interaction devices in the operation room (OR) requires new modalities that support medical imaging manipulation while allowing doctors'' hands to remain sterile, supporting their focus of attention, and providing fast response times. This paper presents “Gestix,” a vision-based hand gesture capture and recognition system that interprets in real-time the user''s gestures for navigation and manipulation of images in an electronic medical record (EMR) database. Navigation and other gestures are translated to commands based on their temporal trajectories, through video capture. “Gestix” was tested during a brain biopsy procedure. In the in vivo experiment, this interface prevented the surgeon''s focus shift and change of location while achieving a rapid intuitive reaction and easy interaction. Data from two usability tests provide insights and implications regarding human-computer interaction based on nonverbal conversational modalities.     

An ultrasonic head position interface for wheelchair control

To give quadriplegics independent mobility, a “smart” microprocessor-based electric wheelchair has been developed by the Palo Alto Veterans Administration Medical Center and Stanford University. Ultrasound distance-ranging technology is employed to track the user's head position in two-dimensional space. These data are then used to determine the chair's direction and speed. A working prototype vehicle using this type of motion control has been successfully demonstrated. Obstacle detection, wall-following, and cruise control modes are other implemented features of the current design.     

Medical informatics: An emerging medical discipline

The use of computer technology in medicine is no longer the domain of only a few “gadget” happy high-tech aficionados. The rapid pace of medical progress and the increasing demands on physicians' time mandate that mechanisms be developed to deliver the tools of contemporary information management directly into the hands ofall practicing physicians. It is with this intent that the Council on Long-range Planning and Development and the Council on Scientific Affairs of the American Medical Association have developed an informational report on Medical Informatics. The technology for producing information about medicine and patients is well into the information age. However, the technology for managing this information has not kept up, at least to the extent of being available in medical facilities where it is needed. Most users of medical information, physicians included, have not crossed the threshold into the electronic/computer era of information acquisition, distribution, and assimilation. The continuing development of the physician as computer user will create a more efficient work environment for the physician while at the same time improving patient care.     

Considering human factors in the initial analysis and design of a medical computer system

The primary objective of a medical computer system is (should be?) to support patients and the people who care for them. Successful human factors design in these systems depends primarily on successful identification and resolution of management-level issues during the systems' concept development stage. Traditional human factors issues (user, dialogue, terminal characteristics) that affect the man-machine interface are resolved based upon decisions made during concept development phase; inappropriate decisions “early on” result in poor human factors designs.     

A Review of Analytics and Clinical Informatics in Health Care

This study was conducted to evaluate the usability of widely used laboratory and radiology information systems. Three usability experts independently evaluated the user interfaces of Laboratory and Radiology Information Systems using heuristic evaluation method. They applied Nielsen’s heuristics to identify and classify usability problems and Nielsen’s severity rating to judge their severity. Overall, 116 unique heuristic violations were identified as usability problems. In terms of severity, 67 % of problems were rated as major and catastrophic. Among 10 heuristics, “consistency and standards” was violated most frequently. Moreover, mean severity of problems concerning “error prevention” and “help and documentation” heuristics was higher than of the others. Despite widespread use of specific healthcare information systems, they suffer from usability problems. Improving the usability of systems by following existing design standards and principles from the early phased of system development life cycle is recommended. Especially, it is recommended that the designers design systems that inhibit the initiation of erroneous actions and provide sufficient guidance to users.     

Introducing a Module for Laboratory Test Order Entry and Reporting of Results at a Hospital Ward: An Evaluation Study Using a Multi-Method Approach

The medical record system DocuLive EPR was installed at a “typical” ward at the Central Hospital of Akershus. Modules for laboratory order entry and reporting of results were evaluated prospectively using several information sources (hospital information systems, telephone records, user survey, semi-structured interviews with key informants). The main findings are discussed, and the lessons learned from the evaluation project are presented.     

Effects of pruning of a decision-tree for the ear,nose, and throat realm in primary health care based on case-notes

In the primary health care center of Mjölby a sample of case notes in the ear-nose-and-throat realm (N=425) was computer processed using an inductive rule-based decision-tree generating program. As a result of incomplete information in the case-files, the decision trees were “noisy,” e.g., had branches and leaves without meaning. This led to a need for “pruning.” Various methods were tried. The effects of different methods of decision-tree generating and pruning are discussed. The choice of root argument and branching of the decision-trees suggested by the software was the most clinically applicable. The “statistic” approach to pruning gave the most compact and still most clinically relevant decision-tree. The pruned and edited decision trees are compared with a previously published preliminary essential data set for the ear-nose-and-throat realm in primary health care and then discussed as a possible decision support system for various primary health care groups in a practice setting.     

The Iowa Medical Information Network: A concept

Iowa Methodist Medical Center (IMMC) was one of the nation's early developers of a “hospital/physician” system, entering the arena during October 1985, under the direction of Ginny Wagner, Their “MOLI-Link” system now serves over 150 physicians in 50 locations, and is currently undergoing significant enhancement. MOLI-Link was originally developed using Annson Systems (IBAX) products, and has recently migrated to Wallace Computer Services (Wal-Link) software. Over the past 4 years, IMMC has investigated wide-crea medical information networking, and is now actively investigating development of the Iowa Medical Information Network. It is envisioned that IMIN would provide clinical, administrative, and educational information services throughout the IMMC 37 county referral area.     

The Limitations of Decision Trees and Automatic Learning in Real World Medical Decision Making

The decision tree approach is one of the most common approaches in automatic learning and decision making. The automatic learning of decision trees and their use usually show very good results in various “ theoretical” environments. But in real life it is often impossible to find the desired number of representative training objects for various reasons. The lack of possibilities to measure attribute values, high cost and complexity of such measurements, and unavailability of all attributes at the same time are the typical representatives. For this reason we decided to use the decision trees not for their primary task—the decision making—but for outlining the most important attributes. This was possible by using a well-known property of the decision trees—their knowledge representation, which can be easily understood by humans. In a delicate field of medical decision making, we cannot allow ourselves to make any inaccurate decisions and the “tips,” provided by the decision trees, can be of a great assistance. Our main interest was to discover a predisposition to two forms of acidosis: themetabolic acidosis and respiratory acidosis, which can both have serious effects on child's health. We decided to construct different decision trees from a set of training objects. Instead of using a test set for evaluation of a decision tree, we asked medical experts to take a closer look at the generated trees. They examined and evaluated the decision trees branch by branch. Their comments show that trees generated from the available training set mainly have surprisingly good branches, but on the other hand, for some, no medical explanation could be found.     

Use of personal computing technology by deaf-blind individuals

This paper describes a system that enables deaf-blind people to work with microcomputers. The system utilizes the International Morse Code as a general communication medium. The deaf-blind person “hears” Morse code via a vibrotactile device to “see” the computer's screen. This technique enables deaf-blind individuals to receive immediate feedback from their typing and to scan the screen. This makes it possible for them to use the keyboard and screen in the same way as do seeing persons. A side benefit is that it provides a means for deaf-blind people to communicate with the sighted through a common medium: The sighted person can see the screen while the deaf-blind person feels it. Hardware cost to equip a standard personal computer with this interface is negligible. Vibrotactile Morse code is particularly viable because it can be adapted for the individual's particular tactile sensitivities. Morse-encoded tactile communication fits well in a social facilitation context for learning. It is technologically simple and standard. This work can significantly improve the quality of life for deaf-blind individuals because it provides new opportunities for communication and vocation.     

开放系统中基于信任度和上下文的访问控制模型

开放系统中,访问控制机制不仅要能处理数量庞大且身份无法预先确定的用户的访问请求,而且能充分反映用户访问请求时上下文环境信息。本文提出了一种基于信任度和上下文的访问控制模型TC-RBAC,并给出了用户信任度计算方法。通过信任度为未知身份用户分配合适角色,上下文约束实现了对不同的访问请求上下文信息做出不同授权决策,从而满足开放环境下访问控制的设计要求。     

Can Cognitive Biases during Consumer Health Information Searches Be Reduced to Improve Decision Making?

Objective

To test whether the anchoring and order cognitive biases experienced during search by consumers using information retrieval systems can be corrected to improve the accuracy of, and confidence in, answers to health-related questions.

Design

A prospective study was conducted on 227 undergraduate students who used an online search engine developed by the authors to find health information and then answer six randomly assigned consumer health questions. The search engine was fitted with a baseline user interface and two modified interfaces specifically designed to debias anchoring or order effect. Each subject used all three user interfaces, answering two questions with each.

Measurements

Frequencies of correct answers pre- and post- search and confidence in answers were collected. Time taken to search and then answer a question, the number of searches conducted and the number of links accessed in a search session were also recorded. User preferences for each interface were measured. Chi-square analyses tested for the presence of biases with each user interface. The Kolmogorov-Smirnov test checked for equality of distribution of the evidence analyzed for each user interface. The test for difference between proportions and the Wilcoxon signed ranks test were used when comparing interfaces.

Results

Anchoring and order effects were present amongst subjects using the baseline search interface (anchoring: p < 0.001; order: p = 0.026). With use of the order debiasing interface, the initial order effect was no longer present (p = 0.34) but there was no significant improvement in decision accuracy (p = 0.23). While the anchoring effect persisted when using the anchor debiasing interface (p < 0.001), its use was associated with a 10.3% increase in subjects who had answered incorrectly pre-search, answering correctly post-search (p = 0.10). Subjects using either debiasing user interface conducted fewer searches and accessed more documents compared to baseline (p < 0.001). In addition, the majority of subjects preferred using a debiasing interface over baseline.

Conclusion

This study provides evidence that (i) debiasing strategies can be integrated into the user interface of a search engine; (ii) information interpretation behaviors can be to some extent debiased; and that (iii) attempts to debias information searching by consumers can influence their ability to answer health-related questions accurately, their confidence in these answers, as well as the strategies used to conduct searches and retrieve information.     

Implementation of a Patient Charting System: Challenges Encountered and Tactics Adopted in a Burn Center

The rapid movement of information technologies into health care organizations has raised managerial concern regarding the capability of today's institutions to satisfactorily manage their introduction. Indeed, several health care institutions have consumed huge amounts of money and frustrated countless people in wasted information systems implementation efforts. Unfortunately, there are no easy answers as to why so many health informatics projects are not more successful. In this light, the aim of this study is to provide a deeper understanding of how clinical information systems are being implemented by emphasizing research efforts on the dynamic nature of the process, that is, the “how” and “why” of what happened. Using a case study methodology, we examined the implementation of a patient charting system in the Burn Center of a large, not-for-profit, teaching hospital. Based on an in-depth examination of this implementation, several insights are offered to those who have responsibility for managing complex and risky clinical information system implementation projects.     

“Compu-void II”: The computerized voiding diary

Objective: We have previously described an electronic voiding diary, “Compu-Void” (Copyright, 1990) developed to automate recording of bladder symptoms (Rabinet al., 1993). Our objectives in this, the second phase of this study, were to examine a group of subject and control patients' preference and compliance with regard to the “Compu-Void” (CV) compared to the standard written voiding diary (WD), to compare the two methods with respect to the amount and type of information obtained and to determine whether or not the order of use of each recording method influenced results in the subject group.Methods: Thirty-six women between the ages of 20 and 84 with bladder symptomatology were compared to a group of 36 age-matched women.Results: In 100% of subjects and 95% of control patients, CV entries exceeded the number made with the WD in voiding events and in subjects, in incontinent episodes recorded (p<0.0005 andp<0.005, respectively). Over 98% of subjects and over 80% of control patients preferred CV over the WD (p<0.0005). The order of use of each recording method in subjects made no significant difference with regard to the volume of information obtained (p<0.407), number of urinary leakage events recorded (p<0.494), and fluid intake patterns (p<0.410). Patient impressions of, and compliance with each method were not affected by order of use. The only difference regarding order of use was that most subjects who used the CV first also found the WD to be tedious (61% vs 14%).Conclusions: Our results suggest increased volume of data and of patient compliance in reporting bladder symptoms and events using CV, and that order of use is not an important factor in determining patient impressions of the two methods. The majority of subject and control patients preferred CV over traditional methods. An updated version of the software and hardware is also included.