Overstay2 scoring model for St. Boniface: Difference between revisions

Line 3:

== Data elements and assigned coefficients ==

{{~~Discuss~~|z

The binary logistic regression Y (Overstay GE 10 Days) which gave the AUC C-index =0.771 implying better predicted model and Hosmer and Lemeshow Goodness of fit test Chi-Square value of 11.1321 (prob=0.133) is :

* ~~once we have~~ a ~~model~~, ~~add~~ the ~~content for~~ the ~~chosen model here~~, ~~with~~ [[~~template:OSDD~~]] ~~links }}~~

LN(OS/1-OS) = Y

Y = Intercept Estimate + sum of all the rest of (the Parameter values multiplied by the Estimate) listed below:

{| class="wikitable notsortable"

!Parameter !! Estimate !! Prob > ChiSq

|-

| Intercept || -7.308524846 || <.0001

|-

| {{OSDD|Homeless}} || 1.012402498 || 0.0087

|-

| {{OSDD|Dementia}} ||0.570758477 || 0.0081

|-

| {{OSDD|MI}} || 0.456135105 || 0.0067

|-

| {{OSDD|Diabetes}} || -0.527659475 || 0.0068

|-

| {{OSDD|GCS_Motor}} || 0.416028616 || 0.0323

|-

| {{OSDD|ADL_bath}} || 0.412497217 || <.0001

|-

| {{OSDD|ADL_dress}} || -0.19051492 || 0.0034

|-

| {{OSDD|ADL_continence}} || 0.181464804 || <.0001

|-

| {{OSDD|ADL_Adlmean_nh}} || -0.059389318 || 0.0013

|}

Where OS is the likelihood to overstay 10 days and beyond.

How to calculate OS:

* OS = exp(Y) / (1 + exp(Y)

*The model gave a 0.028 optimum cut-off probability for OS GE 10 Days with sensitivity = 69.0%, the rate of identifying OS GE 10d out of the patients who actually have OS GE 10d and with specificity = 70.4 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 29.6% 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 0.039 resulted to sensitivity = 66.9%, thus reducing the rate of identifying '''OS GE 10d''' out of the patients who actually have '''OS LT 10d''' to 26.3%. Thus '''a predicted probability of (Overstay >= 10 days) of 0.039''' 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 = 0.742, the Hosmer and Lemeshow Goodness of fit test Chi-Square value = 13.4047 (prob=0.099) and the optimum cut-off probability for OS = 0.028 with sensitivity = 67.1% and specificity = 71.6%.

== Log ==

@@ Line 3: / Line 3: @@
 == Data elements and assigned coefficients ==
-{{Discuss|z
+The binary logistic regression  Y  (Overstay GE 10 Days)  which gave the AUC C-index =0.771 implying better predicted model and Hosmer and Lemeshow Goodness of fit test Chi-Square value of 11.1321 (prob=0.133) is :
-* once we have a model, add the content for the chosen model here, with [[template:OSDD]] links }}
+LN(OS/1-OS) = Y
+Y = Intercept Estimate + sum of all the rest of (the Parameter values multiplied by the Estimate)   listed below:
+{| class="wikitable notsortable"
+ !Parameter !! Estimate !! Prob > ChiSq
+|-
+| Intercept  || -7.308524846 || <.0001
+|-
+| {{OSDD|Homeless}} || 1.012402498 || 0.0087
+|-
+| {{OSDD|Dementia}}  ||0.570758477  || 0.0081
+|-
+| {{OSDD|MI}}  || 0.456135105 || 0.0067
+|-
+| {{OSDD|Diabetes}} || -0.527659475 || 0.0068
+|-
+| {{OSDD|GCS_Motor}} || 0.416028616 || 0.0323
+|-
+| {{OSDD|ADL_bath}} || 0.412497217 || <.0001
+|-
+| {{OSDD|ADL_dress}}  || -0.19051492  || 0.0034
+|-
+| {{OSDD|ADL_continence}}  || 0.181464804 || <.0001
+|-
+| {{OSDD|ADL_Adlmean_nh}}  || -0.059389318 || 0.0013
+|}
+Where OS is the likelihood to overstay 10 days and beyond.
+How to calculate OS:
+* OS = exp(Y) / (1 + exp(Y)
+*The model gave a 0.028 optimum cut-off probability for OS GE 10 Days with sensitivity = 69.0%, the rate of identifying OS GE 10d out of the patients who actually have OS GE 10d  and with specificity = 70.4  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 29.6% 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 0.039  resulted to sensitivity = 66.9%, thus reducing the rate of identifying '''OS GE 10d''' out of the patients  who actually have '''OS LT 10d''' to 26.3%.  Thus  '''a predicted probability of (Overstay >= 10 days) of 0.039'''  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 = 0.742, the Hosmer and Lemeshow Goodness of fit test Chi-Square value = 13.4047 (prob=0.099)  and the optimum cut-off probability for OS = 0.028 with sensitivity = 67.1% and specificity = 71.6%.
 == Log ==