Overstay2 scoring model for HSC: Difference between revisions

(4 intermediate revisions by the same user not shown)

Line 43:

*The model has been validated using the data from the validation set of same period. The AUC C-index = 0.0.787, the Hosmer and Lemeshow Goodness of fit test Chi-Square value = 10.4037 (prob=0.2346) and the optimum cut-off probability for OS = 0.043 with sensitivity = 71.6% and specificity = 71.5%.

== Model files ==

* files describing the model and records of discussion about it are at S:\MED\MED_CCMED\Julie\MedProjects\Overstay_Project_2025\3_HSCSTB_15Oct2025\HSC\FinalModel

== Log ==

* 2025-06-~~09 no work yet~~

* 2025-10-15 - model 6 selected as final model with AUC=0.789 and HL goodness of fit =10.5443(prob=0.2289)

* 2025-08-11 - found good fit model in the training data set (Nov2020 to Dec2024) as well as in the validation data set1 (Nov2020 to Dec2024) but not in the validation dataset2 (2025 data). When discussed with Dr Roberts and Tina, it was agreed to redefine the period to include Nov 2020 to July 2025 and divide into training set and one validation set and from these data sets find the good fit model. The results presented in Oct 15, 2025.

*2025-07-18 - found good fit model but was agreed to re-do to include more parameters like Chronic Addiction, Acute OD Toxicity, geographic locations, etc as well as clarify the definitions of some parameters.

== Related articles ==

@@ Line 43: / Line 43: @@
 *The model has been validated using the data from the validation set of same period. The AUC C-index = 0.0.787, the Hosmer and Lemeshow Goodness of fit test Chi-Square value = 10.4037 (prob=0.2346)  and the optimum cut-off probability for OS = 0.043 with sensitivity = 71.6% and specificity = 71.5%.
+== Model files ==
+* files describing the model and records of discussion about it are at S:\MED\MED_CCMED\Julie\MedProjects\Overstay_Project_2025\3_HSCSTB_15Oct2025\HSC\FinalModel
 == Log ==
-* 2025-06-09 no work yet
+* 2025-10-15 - model 6 selected as final model with AUC=0.789 and HL goodness of fit =10.5443(prob=0.2289)
+* 2025-08-11 - found good fit model in the training data set (Nov2020 to Dec2024)  as well as in the validation data set1 (Nov2020 to Dec2024) but not in the validation dataset2 (2025 data). When discussed with Dr Roberts and Tina, it was agreed to redefine the period to include Nov 2020 to July 2025 and divide into training set and one validation set and from these data sets find the good fit model.  The results presented in Oct 15, 2025.
+*2025-07-18 - found good fit model but was agreed to re-do to include more parameters like Chronic Addiction, Acute OD Toxicity, geographic locations, etc as well as clarify the definitions of some parameters.
 == Related articles ==