| 1. |
|
|
| 2. |
- Donald, Rob, et al.
(author)
-
Forewarning of hypotensive events using a Bayesian artificial neural network in neurocritical care
- 2019
-
In: Journal of clinical monitoring and computing. - : Springer Science and Business Media LLC. - 1387-1307 .- 1573-2614. ; 33:1, s. 39-51
-
Journal article (peer-reviewed)abstract
- Traumatically brain injured (TBI) patients are at risk from secondary insults. Arterial hypotension, critically low blood pressure, is one of the most dangerous secondary insults and is related to poor outcome in patients. The overall aim of this study was to get proof of the concept that advanced statistical techniques (machine learning) are methods that are able to provide early warning of impending hypotensive events before they occur during neuro-critical care. A Bayesian artificial neural network (BANN) model predicting episodes of hypotension was developed using data from 104 patients selected from the BrainIT multi-center database. Arterial hypotension events were recorded and defined using the Edinburgh University Secondary Insult Grades (EUSIG) physiological adverse event scoring system. The BANN was trained on a random selection of 50% of the available patients (n = 52) and validated on the remaining cohort. A multi-center prospective pilot study (Phase 1, n = 30) was then conducted with the system running live in the clinical environment, followed by a second validation pilot study (Phase 2, n = 49). From these prospectively collected data, a final evaluation study was done on 69 of these patients with 10 patients excluded from the Phase 2 study because of insufficient or invalid data. Each data collection phase was a prospective non-interventional observational study conducted in a live clinical setting to test the data collection systems and the model performance. No prediction information was available to the clinical teams during a patient's stay in the ICU. The final cohort (n = 69), using a decision threshold of 0.4, and including false positive checks, gave a sensitivity of 39.3% (95% CI 32.9-46.1) and a specificity of 91.5% (95% CI 89.0-93.7). Using a decision threshold of 0.3, and false positive correction, gave a sensitivity of 46.6% (95% CI 40.1-53.2) and specificity of 85.6% (95% CI 82.3-88.8). With a decision threshold of 0.3, > 15min warning of patient instability can be achieved. We have shown, using advanced machine learning techniques running in a live neuro-critical care environment, that it would be possible to give neurointensive teams early warning of potential hypotensive events before they emerge, allowing closer monitoring and earlier clinical assessment in an attempt to prevent the onset of hypotension. The multi-centre clinical infrastructure developed to support the clinical studies provides a solid base for further collaborative research on data quality, false positive correction and the display of early warning data in a clinical setting.
|
|
| 3. |
|
|
| 4. |
- Neumann, JO, et al.
(author)
-
The use of hyperventilation theraphy after traumatic brain injury in Europe : an analysis of the BrainIT database
- 2008
-
In: Intensive Care Medicine. - : Springer Science and Business Media LLC. - 0342-4642 .- 1432-1238. ; 34:9, s. 1676-1682
-
Journal article (peer-reviewed)abstract
- Objective To assess the use of hyperventilation and the adherence to Brain Trauma Foundation-Guidelines (BTF-G) after traumatic brain injury (TBI). Setting Twenty-two European centers are participating in the BrainIT initiative. Design Retrospective analysis of monitoring data. Patients and participants One hundred and fifty-one patients with a known time of trauma and at least one recorded arterial blood–gas (ABG) analysis. Measurements and results A total number of 7,703 ABGs, representing 2,269 ventilation episodes(VE) were included in the analysis. Related minute-by-minute ICP data were taken from a 30 min time window around each ABG collection. Data are given as mean with standard deviation. (1) Patients without elevated intracranial pressure (ICP) (\20 mmHg) manifested a statistically significant higher PaCO2(36 ± 5.7 mmHg) in comparison to patients with elevated ICP(C20 mmHg; PaCO2:34 ± 5.4 mmHg, P\0.001). (2) Intensified forced hyperventilation(PaCO2 B 25 mmHg) in the absence of elevated ICP was found in only 49VE (2%). (3) Early prophylactic hyperventilation (\24 h after TBI;PaCO2 B 35 mmHg,ICP\20 mmHg) was used in 1,224VE (54%). (4) During forced hyperventilation(PaCO2 B 30 mmHg), simultaneous monitoring of brain tissue pO2 or SjvO2 was used in only 204 VE (9%). Conclusion While overall adherence to current BTF-Gseems to be the rule, its recommendations on early prophylactic hyperventilation as well as the use of additional cerebral oxygenation monitoring during forced hyperventilation are not followed in this sample of European TBI centers. Descriptor Neurotrauma
|
|
| 5. |
|
|
| 6. |
|
|
| 7. |
- Piper, I, et al.
(author)
-
The BrainIT group: concept and core dataset definition
- 2003
-
In: Acta Neurochirurgica. - : Springer Science and Business Media LLC. - 0001-6268 .- 0942-0940. ; 145:8, s. 615-629
-
Journal article (peer-reviewed)abstract
- Introduction. An open collaborative international network has been established which aims to improve inter-centre standards for collection of high-resolution, neurointensive care data on patients with traumatic brain injury. The group is also working towards the creation of an open access, detailed and validated database that will be useful for post-hoc hypothesis testing. In Part A, the underlying concept, the group coordination structure, membership guidelines and database access and publication criteria are described. Secondly, in part B, we describe a set of meetings funded by the EEC that allowed us to define a "Core Dataset" and we present the results of a feasibility exercise for collection of this core dataset. Methods. Four group meetings funded by the EEC have enabled definition of a "Core Dataset" to be collected from all centres regardless of specific project aim. A paper based pilot collection of data was conducted to determine the feasibility for collection of the core dataset. Specially designed forms to collect the core dataset demographic and clinical information as well as sample the time-series data elements were distributed by both email and standard mail to 22 BrainIT centres. A deadline of two months was set to receive completed forms back from centres. A pilot data collection of minute by minute physiological monitoring data was also performed. Findings. A core-dataset was defined and can be downloaded from the BrainIT web-site (go to "Core dataset" link at: www.brainit.org). Eighteen centres (82%) returned completed forms by the set deadline. Overall the feasibility for collection of the core data elements was high with only 10 of the 64 questions (16%) showing missing data. Of those 10 fields with missing data, the average number of centres not responding was 12% and the median 6%. An SQL database to hold the data has been designed and is being tested. Software tools for collection of the core dataset have been developed. Ethics approval has been granted for collection of multi-centre data as part of a pilot data collection study. Interpretation. The BrainIT network provides a more standardised and higher resolution data collection mechanism for research groups, organisations and the device industry to conduct multi-centre trials of new health care technology in patients with traumatic brain injury.
|
|
| 8. |
|
|
| 9. |
|
|
| 10. |
- Shaw, M, et al.
(author)
-
The brain monitoring with information technology (BrainIT) collaborative network : data validation results
- 2009
-
In: Acta Neurochirurgica Supplements. - Vienna : Springer Vienna. - 9783211855775 - 9783211855782 ; , s. 217-221
-
Book chapter (other academic/artistic)abstract
- Background The BrainIT group works collaboratively on developing standards for collection and analyses of data from brain injured patients towards providing a more efficient infrastructure for assessing new health technology. Materials and methods Over a 2 year period, core dataset data (grouped by nine categories) were collected from 200 head-injured patients by local nursing staff. Data were uploaded by the BrainIT web and random samples of received data were selected automatically by computer for validation by data validation (DV) research nurse staff against gold standard sources held in the local centre. Validated data was compared with original data sent and percentage error rates calculated by data category. Findings Comparisons, 19,461, were made in proportion to the size of the data received with the largest number checked in laboratory data (5,667) and the least in the surgery data (567). Error rates were generally less than or equal to 6%, the exception being the surgery data class where an unacceptably high error rate of 34% was found. Conclusions The BrainIT core dataset (with the exception of the surgery classification) is feasible and accurate to collect. The surgery classification needs to be revised.
|
|
