CCMDB Wiki

Overstay2 scoring model for Grace Hospital: Difference between revisions

← Older edit
JMojica (talk | contribs)
CCMDB_legit, admin, approved, Administrators
2,815 edits
 
(3 intermediate revisions by the same user not shown)
Line 10: Line 10:
  !Parameter !! Estimate !! Prob > ChiSq
  !Parameter !! Estimate !! Prob > ChiSq
|-
|-
| Intercept  || -10.1922 || <.0001  
| Intercept  || -10.192235 || <.0001  
|-
|-
| {{OSDD|Age}}  || 0.0309 || <.0001  
| {{OSDD|Age}}  || 0.030877 || <.0001  
|-
|-
| {{OSDD|Homeless}} || 0.8355 || 0.093  
| {{OSDD|Homeless}} || 0.835548 || 0.093  
|-
|-
| {{OSDD|PCH/Chronic Care}}  || -3.6008 || <.0001  
| {{OSDD|PCH/Chronic Care}}  || -3.600816 || <.0001  
|-
|-
| {{OSDD|FromNonWpgFacility}}  || 1.7445 || 0.0612  
| {{OSDD|FromNonWpgFacility}}  || 1.744535 || 0.0612  
|-
|-
| {{OSDD|InterImplantDevice}} || 0.9099 || 0.0004  
| {{OSDD|InterImplantDevice}} || 0.909939 || 0.0004  
|-
|-
| {{OSDD|Dementia}} || 1.1677 || <.0001  
| {{OSDD|Dementia}} || 1.167700 || <.0001  
|-
|-
| {{OSDD|CHF}} || 0.2739 || 0.0263  
| {{OSDD|CHF}} || 0.273869 || 0.0263  
|-
|-
| {{OSDD|Plegia}}  || 0.2615 || 0.0547  
| {{OSDD|Plegia}}  || 0.261490 || 0.0547  
|-
|-
| {{OSDD|GCS_Motor}} || 0.4489 || 0.0131  
| {{OSDD|GCS_Motor}} || 0.448897 || 0.0131  
|-
|-
| {{OSDD|ADL_bath}} || 0.3868 || <.0001  
| {{OSDD|ADL_bath}} || 0.386783 || <.0001  
|-
|-
| {{OSDD|ADL_toilet}}  || 0.1596   || 0.0029  
| {{OSDD|ADL_toilet}}  || 0.159622   || 0.0029  
|-
|-
| {{OSDD|ADL_continence}}  || 0.1565 || <.0001  
| {{OSDD|ADL_continence}}  || 0.156504 || <.0001  
|-
|-
| {{OSDD|ADL_Adlmean_age}}  || -0.00065 || 0.0087  
| {{OSDD|ADL_Adlmean_age}}  || -0.000647 || 0.0087  
|}
|}


Line 45: Line 45:
* OS = exp(Y) / (1 + exp(Y)
* OS = exp(Y) / (1 + exp(Y)


* Homeless, PCH, FromNonWpgFacility, InterImplantDevice, Opioids, Dementia, are binary categorical variables (present/yes=1, absent/no =0) .
*The model gave a 0.076 optimum cut-off probability for OS GE 10 Days with sensitivity = 74.2%, the rate of identifying OS GE 10d out of the patients who actually have OS GE 10d  and with specificity = 74.3%, the rate of identifying OS LT 10d out of the patients who actually have OS LT 10d. This  cut-off point of 0.076 will result to 25.7% rate of identifying '''OS GE 10d''' out of the patients  who actually have '''OS LT 10d'''.  Increasing the cut off predicted probability of (Overstay >= 10 days) to 0.094  resulted to sensitivity = 67.2%, thus reducing the rate of identifying '''OS GE 10d''' out of the patients  who actually have '''OS LT 10d''' to 21.0%.  Thus  '''a predicted probability of (Overstay >= 10 days) of 0.094'''  is going to be used to classify patients into two groups; Overstay >= 10 days and Overstay < 10 days. See more discussion on [[Overstay2 colour]].
* CHF, Plegia, GCS_Motor, ADL_bath, ADL_toilet, ADL_continence are points or scores.  
{{DJ|
* can we just leave the two bullets above on [[Data definition for factor candidates for the Overstay2 project]] to avoid duplicating definitions? [[User:Ttenbergen|Ttenbergen]] 00:21, 30 June 2025 (CDT)
}}


*The model gave a 0.076 optimum cut-off probability for OS GE 10 Days with sensitivity = 74.2%, the rate of identifying OS GE 10d out of the patients who actually have OS GE 10d  and with specificity = 74.3%, the rate of identifying OS LT 10d out of the patients who actually have OS LT 10d. This  cut-off point of 0.076 will result to 24.1% rate of identifying '''OS GE 10d''' out of the patients  who actually have '''OS LT 10d'''.  Increasing the cut off predicted probability of (Overstay >= 10 days) to 0.094  resulted to sensitivity = 67.2%, thus reducing the rate of identifying '''OS GE 10d''' out of the patients  who actually have '''OS LT 10d''' to 19.7%.  Thus  '''a predicted probability of (Overstay >= 10 days) of 0.094'''  is going to be used to classify patients into two groups; Overstay >= 10 days and Overstay < 10 days. See more discussion on [[Overstay2 colour]].
*The model has been validated using the data from the validation set of same period. The AUC C-index = 0.815, the Hosmer and Lemeshow Goodness of fit test Chi-Square value = 8.4318 (prob=0.4002)  and the optimum cut-off probability for OS = 0.079 with sensitivity = 74.4% and specificity = 74.5%.
 
*The model has been validated using the data from the validation set of same period. The AUC C-index = 0.815, the Hosmer and Lemeshow Goodness of fit test Chi-Square value = 8.4318 (prob=0.4002)  and the optimum cut-off probability for OS = 0.079 with sensitivity = 74.4% and specificity = 74.5%.


*The model was again validated using the data from Jan to June 17, 2025. The AUC C-index = 0.784, the Hosmer and Lemeshow Goodness of fit test Chi-Square value = 13.7139 (prob=0.0918)  and the cut-off probability for OS = 0.088 with sensitivity = 73.6% and specificity = 74.3%.
*The model was again validated using the data from Jan to June 17, 2025. The AUC C-index = 0.784, the Hosmer and Lemeshow Goodness of fit test Chi-Square value = 13.7139 (prob=0.0918)  and the cut-off probability for OS = 0.088 with sensitivity = 73.6% and specificity = 74.3%.
Retrieved from "https://ccmdb.kuality.ca/index.php?title=Overstay2_scoring_model_for_Grace_Hospital"