Michael G. Kahn

Episodic skeletal-plan refinement based on temporal data

ONCOCIN is a medical expert system that extends the skeletal-planning technique to an applciation area where the history of past events and the duration of actions are important. The systems knowledge base is designed to reflect a hierarchical model of the domain, and its control and inference mechanisms encourage a mixed-initiative style of interaction between the computer and the user.

Genetic Analysis of Bacteriophage P4 Using P4-Plasmid ColE1 Hybrids

SummaryA set of plasmids that contain fragments of the bacteriophage P4 genome has been constructed by deleting portions of a P4-ColE1 hybrid. A P4 genetic map has been established and related to the physical map by examining the ability of these plasmids to rescue various P4 mutations. The P4 vir1 mutation and P4 genes involved in DNA replication (α), activation of P2 helper genes (δ and ε), polarity suppression (psu) and head size determination (sid) have been mapped, as has the region responsible for synthesis of a nonessential P4 protein.One of the deleted plasmids contains only 5900 base pairs (52%) of P4 but will form plaques if additional DNA is added to increase its total size to near that of P4. This plasmid is also unique in that it will not form stable associations with P2 lysogens of E. coli which are recA+. P4 α mutants can be suppressed as a result of replication under control of the ColE1 part of the hybrid.

Statistical Process Control Methods for Expert System Performance Monitoring

The literature on the performance evaluation of medical expert system is extensive, yet most of the techniques used in the early stages of system development are inappropriate for deployed expert systems. Because extensive clinical and informatics expertise and resources are required to perform evaluations, efficient yet effective methods of monitoring performance during the long-term maintenance phase of the expert system life cycle must be devised. Statistical process control techniques provide a well-established methodology that can be used to define policies and procedures for continuous, concurrent performance evaluation. Although the field of statistical process control has been developed for monitoring industrial processes, its tools, techniques, and theory are easily transferred to the evaluation of expert systems. Statistical process tools provide convenient visual methods and heuristic guidelines for detecting meaningful changes in expert system performance. The underlying statistical theory provides estimates of the detection capabilities of alternative evaluation strategies. This paper describes a set of statistical process control tools that can be used to monitor the performance of a number of deployed medical expert systems. It describes how p-charts are used in practice to monitor the GermWatcher expert system. The case volume and error rate of GermWatcher are then used to demonstrate how different inspection strategies would perform.

Model-Based Interpretation of Time-Varying Medical Data

Abstract nTemporal concepts are critical in medical therapy-planning. If given early enough, specific therapeutic choices may abort or suppress evolving undesired changes in a patients clinical status. Effective medical decision making demands recognition and interpretation of complex temporal changes that permeate the medical record. n nThis paper presents a methodology for representing and using medical knowledge about temporal relationships to infer the presence of clinically relevant events, and describes a program, called TOPAZ, that uses this methodology to generate a narrative summary of such events. A unique feature of TOPAZ is the use of numeric and symbolic modeling techniques to perform temporal reasoning tasks that would be difficult to encode and perform using only one modeling methodology.

Restriction endonuclease cleavage map of bacteriophage P4 DNA.

Abstract A restriction endonuclease cleavage map of satellite phage P4 has been constructed using eight enzymes. A number of genetic variants of P4 were examined and their patterns of digestion were compared.

The Display and Manipulation of Temporal Information

Abstract nBecause medical data have complex temporal features, special techniques are required for storing, retrieving, and displaying clinical data from electronic databases. One significant problem caused by the temporal nature of medical data has been called the temporal granularity problem. The temporal granularity problem is said to occur when the set of facts relevant to a specific problem changes as the time scale changes. We argue that what is needed to deal with changes in the relevant time scale are temporal granularity heuristics. One heuristic that we have explored is that, for any level of problem abstraction, and for each type of data item in the record, there exists an optimal level of temporal abstraction. We describe an implemented database kernel and a graphical user interface that have features designed specifically to support this temporal granularity heuristic. The basis for our solution is the use of temporal abstraction and temporal decomposition to support changes in temporal granularity. This heuristic encodes the relevant behvior of each type of event at different levels of temporal granularity. In doing so, we can define a specific behavior for each type of data as the level of abstraction changes.

Clinical Decision-Support Systems in Radiation Therapy

Computers have been used in radiation therapy since the early 1960s to perform dose calculations. In the last decade, researchers have developed computer-based clinical decisionsupport systems for assisting in different decision-making tasks in radiation therapy. This paper reviews eleven prototype systems developed for target volume delineation, treatment planning, treatment plan evaluation, and treatment machine diagnosis. The advent of three-dimensional (3D) conformal radiation therapy (CRT) provides radiation oncologists with the opportunity to consider innovative beam arrangements which were not possible in two-dimensional class solutions. The difficulty of manually generating the thousands of clinically plausible 3D treatment plans calls for the... Read complete abstract on page 2.

The Expanding Informatics Community: Blessing or Curse?

In their introductory comments to the 2001 ACMI Symposium published in this issue, Friedman, Ozbolt, and Masys 1 note that the current fast-moving and turbulent times seem to be both a blessing and curse for biomedical informatics. Never before have so many modifiers appeared next to the term “informatics,” as collaborations spread out into an ever-widening array of professional and consumer medical/clinical/health fields. Their example of “public health informatics” is only one of dozens of examples that they could have chosen, in which an additional level of informatics specialization has occurred in the health sciences. Adding to the sense of expanding roles and opportunities, informatics teams play an essential role in strategic market needs analysis and in product design, development, and deployment within the clinical and biomedical commercial sectors. None of these features were prevalent in the informatics landscape less than 5 years ago.nnFrom the published report, it appears that the initial concern of the conference organizers was how to prevent the field of informatics from fractionating into such small subsegments that nothing remains as a core shared culture that binds and unifies all informatics practitioners and investigators. From there, the conference seems to have both embraced the widening scope of informatics and created an overall four-part superstructure in which to place the rapidly expanding disparate pieces together. Thus, although the primary data look scattered, the ACMI conference attendees seemed to find four “clusters” in which to organize the overarching themes for widely disparate biomedical informatics activities.nnBefore commenting on some of the organizing themes that form the major contribution from the conference, I first would like to add a personal perspective on the underlying uneasy sense of “culture lost” or perhaps more appropriate “culture diluted” that motivated the conference initially.nnThe strength of any interdisciplinary activity is also …

Brief communication: Developing a data infrastructure for a learning health system: the PORTAL network

The Kaiser Permanente & Strategic Partners Patient Outcomes Research To Advance Learning (PORTAL) network engages four healthcare delivery systems (Kaiser Permanente, Group Health Cooperative, HealthPartners, and Denver Health) and their affiliated research centers to create a new national network infrastructure that builds on existing relationships among these institutions. PORTAL is enhancing its current capabilities by expanding the scope of the common data model, paying particular attention to incorporating patient-reported data more systematically, implementing new multi-site data governance procedures, and integrating the PCORnet PopMedNet platform across our research centers. PORTAL is partnering with clinical research and patient experts to create cohorts of patients with a common diagnosis (colorectal cancer), a rare diagnosis (adolescents and adults with severe congenital heart disease), and adults who are overweight or obese, including those with pre-diabetes or diabetes, to conduct large-scale observational comparative effectiveness research and pragmatic clinical trials across diverse clinical care settings.

Objective evaluation of radiation treatment plans.

The evaluation of radiation treatment plans involves making trade-offs among doses delivered to the tumor volumes and nearby normal tissues. Evaluating state-of-the-art three-dimensional (3D) plans is a difficult task because of the huge amount of planning data that needs to be deciphered. Multiattribute utility theory provides a methodology for specifying trade-offs and selecting the optimal plan from many competing plans. Using multiattribute utility theory, we are developing a clinically meaningful objective plan-evaluation model for 3D radiation treatment plans. Our model incorporates three of the factors involved in radiation treatment evaluation--treatment preferences of the radiation oncologist, clinical condition of the patient, and complexity of the treatment plan.