PREDICTION OF SURVIVAL OF HEART FAILURE PATIENTS USING RANDOM FOREST

Human survival, one of 

the roles that is 

controlled by the heart, makes the heart need to be 

guarded 

and

be

aware 

of

its

damage

.

Cardiovascular  breakdown  is  the  last  phase  of  all 

coronary  illness

.

The  problem  of  the  number  of 

deaths  caused  by  heart  failure  requires  a  survival 

predictor   tool.    

The   patient   electronic   clinical 

record 

apparatus 

is

accessible 

to

gauge 

manifestations, 

body 

highlights 

and

clinical 

research center test esteems that can be u

tilized to 

perform    biostatistical    dissects    pointed    toward 

featuring  examples  and  connections  that  are  not 

recognized  by  clinical  specialists.  AI  is  an  answer 

for  have  the  option  to  foresee  tolerant  endurance 

from   the   information   created   and   to   have   the 

opt

ion

to

recognize 

the

most 

significant 

components  among  those  remembered  for  their 

clinical  records.

With  data  mining  techniques  used 

in   the   available   history   data,   namely   the   Heart 

Failure Clinical Records dataset of 299 instances on 

13  features  using  the 

Random  Forest  algorithm, 

Decision    Tree,    KNN,    Support    Vector    Machine

(SVM)

,  Artificial  Neural  Network  and  Naïve  Bayes 

with 

resample 

and

Synthetic 

Minority 

Oversampling 

Technique

(

SMOTE

)

sampling 

techniques.     The     highest     accuracy     with     the 

resample  sampling  te

chnique  in  the  random  forest 

is  94.31%  and  the  SMOTE  technique  used  in  the 

random  forest  produces  an  accuracy  of  85.82% 

higher  than  other  algorithms

.

The  example  framed 

can   anticipate   the   endurance   of   cardiovascular 

breakdown patients

Human survival, one of 

the roles that is 

controlled by the heart, makes the heart need to be 

guarded 

and

be

aware 

of

its

damage

.

Cardiovascular  breakdown  is  the  last  phase  of  all 

coronary  illness

.

The  problem  of  the  number  of 

deaths  caused  by  heart  failure  requires  a  survival 

predictor   tool.    

The   patient   electronic   clinical 

record 

apparatus 

is

accessible 

to

gauge 

manifestations, 

body 

highlights 

and

clinical 

research center test esteems that can be u

tilized to 

perform    biostatistical    dissects    pointed    toward 

featuring  examples  and  connections  that  are  not 

recognized  by  clinical  specialists.  AI  is  an  answer 

for  have  the  option  to  foresee  tolerant  endurance 

from   the   information   created   and   to   have   the 

opt

ion

to

recognize 

the

most 

significant 

components  among  those  remembered  for  their 

clinical  records.

With  data  mining  techniques  used 

in   the   available   history   data,   namely   the   Heart 

Failure Clinical Records dataset of 299 instances on 

13  features  using  the 

Random  Forest  algorithm, 

Decision    Tree,    KNN,    Support    Vector    Machine

(SVM)

,  Artificial  Neural  Network  and  Naïve  Bayes 

with 

resample 

and

Synthetic 

Minority 

Oversampling 

Technique

(

SMOTE

)

sampling 

techniques.     The     highest     accuracy     with     the 

resample  sampling  te

chnique  in  the  random  forest 

is  94.31%  and  the  SMOTE  technique  used  in  the 

random  forest  produces  an  accuracy  of  85.82% 

higher  than  other  algorithms

.

The  example  framed 

can   anticipate   the   endurance   of   cardiovascular 

breakdown patients

Human survival, one of 

the roles that is 

controlled by the heart, makes the heart need to be 

guarded 

and

be

aware 

of

its

damage

.

Cardiovascular  breakdown  is  the  last  phase  of  all 

coronary  illness

.

The  problem  of  the  number  of 

deaths  caused  by  heart  failure  requires  a  survival 

predictor   tool.    

The   patient   electronic   clinical 

record 

apparatus 

is

accessible 

to

gauge 

manifestations, 

body 

highlights 

and

clinical 

research center test esteems that can be u

tilized to 

perform    biostatistical    dissects    pointed    toward 

featuring  examples  and  connections  that  are  not 

recognized  by  clinical  specialists.  AI  is  an  answer 

for  have  the  option  to  foresee  tolerant  endurance 

from   the   information   created   and   to   have   the 

opt

ion

to

recognize 

the

most 

significant 

components  among  those  remembered  for  their 

clinical  records.

With  data  mining  techniques  used 

in   the   available   history   data,   namely   the   Heart 

Failure Clinical Records dataset of 299 instances on 

13  features  using  the 

Random  Forest  algorithm, 

Decision    Tree,    KNN,    Support    Vector    Machine

(SVM)

,  Artificial  Neural  Network  and  Naïve  Bayes 

with 

resample 

and

Synthetic 

Minority 

Oversampling 

Technique

(

SMOTE

)

sampling 

techniques.     The     highest     accuracy     with     the 

resample  sampling  te

chnique  in  the  random  forest 

is  94.31%  and  the  SMOTE  technique  used  in  the 

random  forest  produces  an  accuracy  of  85.82% 

higher  than  other  algorithms

.

The  example  framed 

can   anticipate   the   endurance   of   cardiovascular 

breakdown patients

Unduhan