Can we predict your future? Using scores to predict length of stay and discharge destination
Notice bibliographique
Résumé
Background: This audit was completed within a large teaching hospital in Dublin, St Vincents University Hospital. The cohort of patients are those admitted with an acute stroke under the care of the Stroke Multidisciplinary Team, with confirmed stroke on CTBrain/MRI.Problem: It has always been assumed that poor cognitive scores were associated with longer lengths of stays and increased likelihood of discharge to a location other than the patient’s home. Stroke patients can often wait months to access appropriate care packages, further rehab settings or long term care beds resulting in significant costs as well as causing frustration for patients and their families alike. Achieving safe, timely and person centred discharge from hospital to home is an important indicator of quality and a measure of effective and integrated care (Joint Improvement Team, HSE 2014)Improvement related question: We set out to confirm if early cognitive screening of acute stroke patients in a large Dublin teaching hospital could predict their discharge destination and length of stay. This has never been examined previously within an Irish/UK stroke population using a standardised cognitive assessment (MoCA).Methods: We completed a retrospective audit using paper count method on the charts of 120 newly diagnosed stroke patients admitted to St Vincent's University Hospital over a six month period. The proforma gathered information on patient sex, age, date of admission, length of stay, CT/MRI results, admission Barthel, MOCA score on initial assessment, discharge Barthel score and discharge destination.Intervention/Results: 120 patients were included in the audit with a confirmed stroke on CTB/MRI. The average age was 73. There were 52 males and 68 females and the average length of stay was 44 days.Of the 49 patients that scored within mild-no cognitive impairment, 90% (n=44) went home from SVUH, 2% to further rehab, 6% to LTC and 2% died . The average length of stay for this cohort is 17 days.Of those that scored within the mild- moderate cognitive impairment (n=37) 30% went home, 40% went for further rehab, 27% went to LTC and 3% died. The average length of stay for this group was 49 days (more than twice the first group).Of those that scored within moderate – severe cognitive impairment, 12% went for further rehab, 63% to long term care and 25% died and 0% went home.Their average length of stay was 90days, nearly five times longer than the first cohort.Not every patient was able to complete a standardised cognitive assessment.42% of these patients went to long-term care and 35% died. This cohorts average length of stay was 82 days, with a the number of deaths shortly after admissionLessons Learnt: The results of this audit confirm that early cognitive screening can help predict discharge destination and length of stay. Early cognitive screening (as recommended in the Royal College Of Physicians Stroke guidelines) are completed within 24 hours of admission to SVUH. Therefore the multidisciplinary has a strong indicator of discharge destination and length of stay early in the course of the patient’s hospital stay. With an increasing emphasis on the delivery of appropriate allocation of resources and constant pressures on delivering cost effective care it is estimated this knowledge will have significant cost saving benefits. This information is also imperative in early planning to reduce the number of delayed discharges.Effects of changes: As a multidisciplinary team we now use these early cognitive scores prospectively, to inform discharge arrangements and the timeliness of interventions for newly diagnosed stroke patients. Family meetings are now arranged within two weeks of admissions as standard, meaning families/NOK are also informed and involved in effective early discharge planning, allowing for a more seamless discharge.We anticipate that this focus on early scores might assist in the better distribution of healthcare resources in the hospital setting.
Récupéré en direct depuis OpenAlex et désinversé. Les résumés ne sont pas conservés dans cette base de données : les index inversés représentent 8,6 Go des 9,3 Go de texte de la base, et le serveur dispose de 13 Go libres.
Comment cette classification a été obtenuedéplier
Prédiction machine sur la base complète
Imitation des enseignantsNi prévalence calibrée, ni vérité terrain. Validation humaine à venir. Le volet Gemma est une étiquette directe du modèle pour chaque travail de la base, lue sur la notice réduite au titre. Le volet Codex est un classifieur appris des 10 348 étiquettes directes de Codex et calibré sur les taux pondérés de l'échantillon; les champs sans appui suffisant ne portent aucun appel Codex. Le mode candidate est l'union des deux volets; le consensus est leur intersection. Ces sorties portent le statut machine_predicted_unvalidated et ne sont pas des étiquettes humaines.
Scores du classifieur distillé par catégorie (deux têtes)
| Catégorie | Codex | Gemma |
|---|---|---|
| Métarecherche | 0,002 | 0,007 |
| Méta-épidémiologie (sens strict) | 0,000 | 0,000 |
| Méta-épidémiologie (sens large) | 0,000 | 0,000 |
| Bibliométrie | 0,002 | 0,002 |
| Études des sciences et des technologies | 0,000 | 0,000 |
| Communication savante | 0,001 | 0,001 |
| Science ouverte | 0,000 | 0,001 |
| Intégrité de la recherche | 0,000 | 0,001 |
| Charge utile insuffisante (le modèle a refusé de juger) | 0,002 | 0,001 |
Scores machine (provisoires)
Les deux têtes enseignantes du modèle étudiant, lues sur ce travail. Un score ordonne la base pour la relecture; il n'affirme jamais une catégorie, et le statut de validation accompagne chaque rangée tel quel.
Scores de référence d'un modèle non mature (critères de maturité non atteints, 7 itérations). Un score ordonne; il n'affirme jamais une catégorie.
score_only:v0-immature-baseline · tel quel depuis la passe de notation : score_only signifie que le nombre peut ordonner les travaux, et qu'aucune étiquette de catégorie n'en découleClassification
machine, non validéePrédiction automatique; un appel candidat d’une seule source (Gemma direct ou Codex distillé), pas un consensus.
Le détail, modèle par modèle et score par score, se trouve en fin de page sous « Comment cette classification a été obtenue ».