The Use of Slopes in Trend Data for Preclinical Detection of Pneumothorax(PT). † 1013

Giuffrè, Mario; Lyon, Andrew; Badger, Peter; McIntosh, Neil

doi:10.1203/00006450-199804001-01034

Cited by 2 publications

(3 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…2 Patterns need to be described with artificial intelligence techniques 10 . 3 These descriptions need to be tested on large databases of such time series data 3 .…”

Section: Discussionmentioning

confidence: 99%

See 1 more Smart Citation

Intensive care monitoring: past, present and future

McIntosh

2002

Clinical Medicine

Self Cite

View full text Add to dashboard Cite

-Monitoring is the serial evaluation of time-stamped data, and the volume of such data in an intensive care unit is huge. Clinical and biochemical data may be available at hourly or more frequent intervals but physiological data are 'continuous' . Although sophisticated monitors display the physiological data in multiple and varied combinations, staff are challenged by the frequency of the false alarms and a lack of knowledge of the patterns from which they could predict problems. All these data, together with large amounts of clinical data, lead to information overload. In this paper, the case is made for the development of automatic decision-support systems based on statistical and probabilistic analysis of data patterns appropriate for the level of cognition of the user (nurses and juniors at the bedside rather than consultants). Such decision support could both reduce the false-positive alarms that frustrate clinical staff, and improve the early detection of pathophysiological events. We have used the development of a pneumothorax as our paradigm. Our data indicate that the clinical diagnosis of pneumothorax takes a median of 127 minutes, but using short decision algorithms based on routinely available monitoring data, most can be detected within 10-15 minutes of occurrence.

show abstract

“…2 Patterns need to be described with artificial intelligence techniques 10 . 3 These descriptions need to be tested on large databases of such time series data 3 .…”

Section: Discussionmentioning

confidence: 99%

“…The sensitivity was excellent but the specificity was poor and related to the time spent monitoring 10 .…”

Section: Trend Patterns In Physiological Datamentioning

confidence: 96%

Intensive care monitoring: past, present and future

McIntosh

2002

Clinical Medicine

Self Cite

View full text Add to dashboard Cite

show abstract

“…On the other hand, the low expressive power of threshold alarms prevents healthcare staff from using them to monitor all situations of clinical interest that may appear in a patient. The ability to reason over the temporal evolution of a patient's physiological variables (Giuffre et al, 1998;Mcintosh et al, 2000) and to integrate information originating from various parameters into one single alarm (Tsien et al, 2000;Chambrin, 2001) would make it possible to automatically watch for the occurrence of situations that must be supervised currently by the healthcare staff.…”

Section: Patient Monitoring: What Is Not Working Properly?mentioning

confidence: 99%

Current State of Critical Patient Monitoring and Outstanding Challenges

Otero

Félix

Barro

Handbook of Research on Developments in E-Health and Telemedicine

View full text Add to dashboard Cite

Technological advances in the fields of electronics and computer science have given rise to a considerable increase in the number of physiological parameters available to clinical staff for interpreting a patient’s state. However, owing to the limitations and flaws in current commercial monitoring devices, this has not resulted in a corresponding increase in healthcare quality. This chapter analyses the reasons why clinical staff are not making full use of information from the monitoring devices currently in use in critical care units; a review is made of the most salient proposals from the scientific literature in order to address the imbalance existing between the amount of data available and the improvement in healthcare; and those problems for which suitable solutions have yet to be found and which have, up until now, hindered the applications of said proposals to clinical routine are analysed.

show abstract

The Use of Slopes in Trend Data for Preclinical Detection of Pneumothorax(PT). † 1013

Cited by 2 publications

References 0 publications

Intensive care monitoring: past, present and future

Intensive care monitoring: past, present and future

Current State of Critical Patient Monitoring and Outstanding Challenges

Contact Info

Product

Resources

About