matthieukomorowski / AI_Clinician

Reinforcement learning for medical decisions
99 stars 46 forks source link

AIClinician_sepsis3_def_160219.m cause this error #6

Open paulrich1234 opened 5 years ago

paulrich1234 commented 5 years ago

hello ,moberst,i run AIClinician_sepsis3_def_160219.m this file in ubuntu ,matlab2016b version,but some error happened ,

Undefined function or variable 'SAH'.

Error in AIClinician_sepsis3_def_160219 (line 476) reformatsah=SAH(reformat,sample_and_hold); % do SAH first to handle this task

thank you for your reply .

moberst commented 5 years ago

This should be resolved since the SAH function got uploaded today

paulrich1234 commented 5 years ago

hello @matthieukomorowski @moberst ,i have the SAH file now ,but i found there is another problem .

Warning: MATLAB has disabled some advanced graphics rendering features by switching to software OpenGL. For more information, click here. Requested 2000000x225699 (3363.2GB) array exceeds maximum array size preference. Creation of arrays greater than this limit may take a long time and cause MATLAB to become unresponsive. See <a href="matlab: helpview([docroot '/matlab/helptargets.map'], 'matlab_env_workspace_prefs')">array size limit or preference panel for more information.

Error in AIClinician_sepsis3_def_160219 (line 305) reformat(irow,31+col)=value; %store available values

i dont know why reformat (2000000,68) transfer to 2000000,225699 it may be problem be the itemid has not been replaced by the reference_matrices.mat index . i donot know why it wonot be replaced .

paulrich1234 commented 5 years ago

This should be resolved since the SAH function got uploaded today

hello,moberst ,thank you for your reply and i have encounter another problem in the follow response.

moberst commented 5 years ago

Please look at the pull request #7 which should resolve the reformat issue, that's related to issue #2

paulrich1234 commented 5 years ago

Please look at the pull request #7 which should resolve the reformat issue, that's related to issue #2

@moberst thank you for your excellent work .and i will try it and i am uncertainty about line 305 reformat(irow,31+col)=value; %store available values why it is 31+itemid not 3+itemid @matthieukomorowski does it a hand bug or because the ce010 ..... has 28itemid out of labU ?

paulrich1234 commented 5 years ago

Please look at the pull request #7 which should resolve the reformat issue, that's related to issue #2

hello ,moberst,thank you for your help about the fixed in AIClinician_sepsis3_def_160219.m file .and i got a four columns" icustayid,morta_90d,max_sofa,max_sirs,sepsis_time" after i run it and then i run another file AIClinician_mimic3_dataset_160219.m and i got another data file with columns

bloc | icustayid | charttime | gender | age | elixhauser | re_admission | died_in_hosp | died_within_48h_of_out_time | mortality_90d | delay_end_of_record_and_discharge_or_death | Weight_kg | GCS | HR | SysBP | MeanBP | DiaBP | RR | SpO2 | Temp_C | FiO2_1 | Potassium | Sodium | Chloride | Glucose | BUN | Creatinine | Magnesium | Calcium | Ionised_Ca | CO2_mEqL | SGOT | SGPT | Total_bili | Albumin | Hb | WBC_count | Platelets_count | PTT | PT | INR | Arterial_pH | paO2 | paCO2 | Arterial_BE | Arterial_lactate | HCO3 | mechvent | Shock_Index | PaO2_FiO2 | median_dose_vaso | max_dose_vaso | input_total | input_4hourly | output_total | output_4hourly | cumulated_balance | SOFA | SIRS

but i saw author's dataset description's columns are

'bloc'|'icustayid', 'charttime' ,'gender', 'age', 'elixhauser' ,'re_admission' , 'died_in_hosp' 'died_within_48h_of_out_time','mortality_90d' 'delay_end_of_record_and_discharge_or_death','Weight_kg','GCS','HR','SysBP' 'MeanBP' ,'DiaBP', 'RR' ,'SpO2', 'Temp_C' ,'FiO2_1', 'Potassium' 'Sodium', 'Chloride' , 'Glucose' ,'BUN' , 'Creatinine', 'Magnesium' ,'Calcium' ,'Ionised_Ca' 'CO2_mEqL', 'SGOT' ,'SGPT' ,'Total_bili' ,'Albumin' ,'Hb' ,'WBC_count' 'Platelets_count' ,'PTT' , 'PT' ,'INR' ,'Arterial_pH' ,'paO2', 'paCO2' ,'Arterial_BE' 'Arterial_lactate' ,'HCO3', 'mechvent' ,'Shock_Index','PaO2_FiO2' 'median_dose_vaso' 'max_dose_vaso' 'input_total' 'input_4hourly' 'input_total_tev' 'input_4hourly_tev' 'output_total' 'output_4hourly' 'cumulated_balance' 'cumulated_balance_tev' 'SOFA' 'SIRS'

there are some differences about the two columns such as 'input_total_tev' \ 'input_4hourly_tev' \'cumulated_balance_tev' are not in my data columns and am i missed some steps ? i saw another file--AIClinician_core_160219.m this file do have input_total_tev' \ 'input_4hourly_tev' columns about eicu data?