Can a patient data base help build a stroke diagnostic expert system?

Hier, Daniel B.; Atkinson, Gary D.; Perline, R.; Hill, Howard; Evans, Martha; Desai, Bhupat; McCormick, W. C.; Caplan, Louis R.

doi:10.3109/14639238608994976

Cited by 9 publications

(3 citation statements)

References 4 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…97 Although studies of stroke outcome are abundant, our understanding of the predictors of stroke outcome is still sketchy and incomplete. Only a few predictors, such as level of consciousness, stroke size, and weakness, have been studied in detail (Table 1).…”

Section: Discussionmentioning

confidence: 99%

Deriving clinical prediction rules from stroke outcome research.

Hier

Edelstein

1991

Stroke

View full text Add to dashboard Cite

Background and Purpose. Our purpose was to determine whether clinical prediction rules could be derived from current stroke outcome research.Summary of Report. We reviewed 92 articles on stroke outcome research to determine their suitability for implementation as a clinical prediction rule. Methodological problems in many of these studies made implementation of their results as a clinical prediction rule difficult.Conclusions. Implementation of stroke outcome research as clinical prediction rules would be facilitated by description of patient population demographics; precise definitions of predictor and outcome measures; stratification of patients by stroke mechanism; use of adequate patient sample sizes; and description of the mathematical methods used, including coding schemes, cutpoints, beta coefficients, constant terms, and a priori probabilities. (Stroke 1991;22:1431-1436)

show abstract

Section: Discussionmentioning

confidence: 99%

Deriving clinical prediction rules from stroke outcome research.

Hier

Edelstein

1991

Stroke

View full text Add to dashboard Cite

show abstract

“…For example, MOS is a module that deduces stroke type by using clinical and historical data from the Michael Reese Stroke Registry. 21 Like MOS, many expert systems developed in the medical field are connected to clinical data banks. 22 Furthermore, MICROSTROKE exhibits self-learning characteristics, making use of its stroke registry module, so that with each new patient, the amount of stored information increases.…”

mentioning

confidence: 99%

The MICROSTROKE expert system for stroke type diagnosis.

Spitzer

Thie

Caplan

et al. 1989

Stroke

View full text Add to dashboard Cite

MICROSTROKE is a prototype expert system designed to categorize and diagnose stroke types based on clinical information. The knowledge base of MICROSTROKE includes information from large stroke registries. The system first queries the physician-user for details of the patient's history, information about the onset of stroke, accompanying symptoms, and pertinent neurologic findings and then sums the individual data items, factors in the a priori odds, and arrives at the probabilities of different stroke types for a given patient. Specific diagnosis of stroke type includes thrombosis, embolus, lacune, intracerebral hemorrhage, and subarachnoid hemorrhage. Stroke type diagnoses by MICROSTROKE were correct in 72.8% of 250 cases in the Hamburg Stroke Data Bank, MICROSTROKE runs on any MS-DOS microcomputer and is intended as a practical aid for physicians not fully familiar with the diagnosis of stroke types. (Stroke

show abstract

“…Disappointments aside, with federal funding the project’s scope expanded in different directions for more reliably measured variables, and included population-based studies [13], risk factors for first and recurrent stroke [14], use of a database for computer diagnosis expert systems [15], issues of race and gender [16], later to be pursued in a clinical trial, identification of ‘silent stroke’ [17], circadian rhythms affecting stroke onset [18], eventually setting the stage for their use in large clinical trials [19]. Through it all, efforts continued to refine the elements for ischemic stroke subtype [20,21].…”

Section: Introductionmentioning

confidence: 99%

A Glimpse of Canaan, 40 Years On

Jp¹

2009

Cerebrovasc Dis

View full text Add to dashboard Cite

During the last few decades an explosion in definitions has occurred covering brief to permanent focal syndromes, diagnostic categories for stroke and subtypes, scoring systems characterizing clinical syndromes as well as imaging, and fostered the ascendancy of biostatistics and meta-analyses. These advances have led to the clinical trials which have changed the management, hyperacute therapy and prevention of recurrent stroke. Stroke trial design is now so well codified that its form is expected by the funding agencies, especially companies supporting trials. Despite criticism, transient ischemic attacks remain >24 h, uncommon diagnoses now fit into ‘stroke of other determined mechanism’, hyperacute treatment within 3, maybe 6 h is standard, as are outcomes at 30 days and 3 months. Unsettling to some, the randomized clinical trial may have reached a plateau in development. Clinical trials have also passed the point where outcomes can be measured in easily described events. The current problems find their focus in smaller cohorts, requiring multicenter efforts, nowadays spanning continents. They have also crossed into areas formerly considered the exclusive purview of sibling specialties, some members not predictably as concerned with the same research questions. Threats to the randomized clinical trial are also emerging in outcomes research. This approach is popular with agencies hoping to apply the widely accepted definitions to readily available clinical databases and will see only more use in times of limited budgets. One effect has been the unintentional restriction into the algorithms of new subtypes of ischemic and hemorrhagic stroke. Similarly, there has been insufficient focus on the effect of functional reorganization on poststroke clinical changes. It was long neglected when the clinical effects of lesions were inferred more or less permanent and explained as inferred ambidexterity, reversible tissue deactivation from edema and diaschisis. It was even explained that embolism was a transient process, leaving little brain injury in its wake. Long awaited, modern technologies are at last providing a means to study functional reorganization and compensatory mechanisms. Current results predict a radical change in our understanding of the course of syndromes from focal lesions, hopefully opening a new era for clinical neurology, maybe even a resurrection of semiology. Studies can be pursued in advance of lesions, during the poststroke course of living patients and for those planned for brain interventions, which could perturbate pretreatment functions and pathways. Those long dead would have envied us our current opportunity. Uncertain to be among those who reap the eventual harvest, this author is grateful for a glimpse of Canaan.

show abstract

Can a patient data base help build a stroke diagnostic expert system?

Abstract: The availability of a large database of patient information has been of benefit in the construction of an expert system for stroke care.

Cited by 9 publications

References 4 publications

Deriving clinical prediction rules from stroke outcome research.

Deriving clinical prediction rules from stroke outcome research.

The MICROSTROKE expert system for stroke type diagnosis.

A Glimpse of Canaan, 40 Years On

Contact Info

Product

Resources

About