Computer vision's potential to improve health care

Analysis of data collected via video cameras in operating rooms found a median of 20 errors (IQR 14–36) and eight events (IQR 4–12) per case in the dissection and reconstruction phases of surgery. Broad video capture of all operating room staff actions was supplemented with miniature video cameras m...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:The Lancet (British edition) 2020-05, Vol.395 (10236), p.1537-1537
Hauptverfasser: Milstein, Arnold, Topol, Eric J
Format: Artikel
Sprache:eng
Schlagworte:
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:Analysis of data collected via video cameras in operating rooms found a median of 20 errors (IQR 14–36) and eight events (IQR 4–12) per case in the dissection and reconstruction phases of surgery. Broad video capture of all operating room staff actions was supplemented with miniature video cameras mounted on surgeons' foreheads to capture nuanced physical actions such as economy and speed of a surgeon's hand motion. Tailwinds include growing familiarity with driver assistance technology in personal vehicles, edge computing on sensor hardware that eliminates the need to store or transmit personally sensitive video and audio data, declining cost of sensor hardware, and growing evidence that checklists and other forms of clinician guidelines are not keeping up with increases in complexity of intended clinical actions imposed by advances in clinical knowledge.
ISSN:0140-6736
1474-547X
DOI:10.1016/S0140-6736(20)31090-4