265
h p://am esea ch e iew.com/index.php/Jou nal/abou
Volume 3, Issue 10 (2025)
Online ISSN P in ISSN
. .
h p://am esea ch e iew.com/index.php/Jou nal/abou
An E icien A i icial In elligence-Based Ea ly P edic ion o Hea A ack
Using Deep Lea ning CNN and SVM Models
Syed Talal Musha a
Bah ia Uni e si y Laho e Campus, Laho e Pakis an/I2C Inc
Email: syed ala[email p o ec ed]
Mian Muhammad Masab (Co esponding Au ho )
AI Enginee , Solu yics, Faisal Town, Laho e, 54000, Pakis an
Email: [email p o ec ed]
Nasi Ayub
Depu y Head o Enginee ing Cal om Limi ed, M16EG, Uni ed Kingdom
Email: nasi .ayy[email p o ec ed]
Shamoon Mu aza
Business De elope , CubicSol.inc, Canal Bu g, Laho e, 54000, Pakis an
Email: [email p o ec ed]
Habib Ullah
Depa men o Compu e Science, Facul y o Compu e Science & IT Supe io Uni e si y
Laho e, 54000, Pakis an
Email: [email p o ec ed]
Amma Ahmad
Depa men o In o ma ion Technology, Facul y o Compu e Science & IT, Supe io Uni e si y
Laho e, 54000, Pakis an
Email: [email p o ec ed]
Muhammad Zunnu ain Hussain
Bah ia Uni e si y Laho e Campus
Email: [email p o ec ed]du.pk
Hamayun Khan
Depa men o Compu e Science, Facul y o Compu e Science & IT, Supe io Uni e si y
Laho e, 54000, Pakis an
Email: hamayun.khan@supe io .edu.pk
A i icial In elligence (AI) has become an in eg al componen o mode n Ca dio ascula
disease diagnosis, ea men planning, and isk s a i ica ion. I s ans o ma i e po en ial is
pa icula ly c ucial in de eloping egions. Ca dio ascula issues cause mos dea hs
wo ldwide. The Wo ld Heal h O ganiza ion s a es ha abou 17.9 million people die
annually. Medical specialis s spend conside able ime diagnosing o iden i y he eason
behind symp oms. Mo eo e , doc o s canno always keep up wi h hei pa ien s. Machine
lea ning can assis doc o s in p edic ing hea diseases by u ilizing global heal h sec o da a,
hus s eng hening he base o his echnology. The p oposed sys em emphasizes empo al
266
h p://am esea ch e iew.com/index.php/Jou nal/abou
Volume 3, Issue 10 (2025)
Online ISSN P in ISSN
. .
h p://am esea ch e iew.com/index.php/Jou nal/abou
da a modeling h ough he in eg a ion o Pa allel CNN (P-CNN) and Suppo Vec o
Machine (SVM) classi ie s o enable he ea ly de ec ion o Hea Failu e (HF). This hyb id
a chi ec u e acili a es he de elopmen o an e ec i e decision-suppo sys em o he
accu a e diagnosis o Conges i e Hea Failu e (CHF). The model was ained and e alua ed
using he UCI Machine Lea ning Hea Disease da ase , and i s pe o mance was
benchma ked agains s a e-o - he-a algo i hms such as A i icial Neu al Ne wo ks (ANNs)
and Recu en Ne wo ks (RNs). Empi ical e alua ions e eal ha Ca dioHelp achie es
ou s anding p edic i e pe o mance, wi h an accu acy o 97%, an F1-sco e o 93.4%, and a
p ecision imp o emen o 0.8% compa ed o exis ing baseline models. Fu he mo e, when
compa ed wi h ad anced hyb id a chi ec u es—including CNN-RNN, CNN-LSTM, and
CNN-BLSTM— he p oposed amewo k exhibi s accu acy enhancemen s o 2.35%, 1.34%,
and 1.95%, P edic ing hea disease accu a ely and quickly is impo an bu di icul .
Machine lea ning becomes highly e ec i e in iden i ying and ca ego izing pa ien s.
Ad anced machine lea ning and deep lea ning models, like SVMs and CNNs, can o ecas
pa ien s' medical his o ies and gene al well-being. Hea disease p edic ions lowe global
dea h a es. While educing he cos o medical ca e. Minimizing expensi e hospi al s ays,
long- e m ca e, and u gen medical help can sa e li es and educe amily and socie al s ess.
Using machine lea ning in heal hca e can help ind hea disease ea ly, make su e pa ien s
ge ea men on ime, and help hem li e be e li es. Mo eo e , using hese echnologies
can help doc o s make be e decisions, inc ease he accu acy o diagnoses, and o e pa ien s
cus om ea men plans
Hea disease is ecognized as one o he complex and deadly illnesses a ec ing humans
globally. In he Uni ed S a es, 11.2% o adul s a e a lic ed by hea disease. The p e alence
is e en highe among indi iduals aged 75 and olde , eaching 37.3%. Resea ch indica es ha
nea ly 80% o hea disease cases migh ha e been a oided h ough ea ly de ec ion and
li es yle changes [1]. Sadly, hea disease emains he leading cause o dea h, ye i is also
one o he mos p e en able condi ions. Taking imely p ecau ions can signi ican ly lowe he
isk o hea disease. Un o una ely, a lack o adequa e knowledge wi hin he gene al
popula ion esul s in unnecessa y a ali ies. The economic impac is subs an ial, wi h hea
disease cos ing app oxima ely $417.9 billion be ween 2020 and 2021 [2]. This igu e
encompasses heal hca e se ices, medica ions, and p oduc i i y losses om p ema u e
dea hs. I is c ucial o ecognize ha he e is a conside able a ia ion in isk le els among
indi iduals wi h hea disease. The mo ali y a es om hea disease di e based on sex, ace,
and e hnici y. Below a e he pe cen ages o all dea hs a ibu ed o hea disease in 2021,
ca ego ized by ace and sex [3, 4]. Se e al ac o s con ibu e o he ongoing challenge o
hea disease, including li es yle- ela ed isks such as poo die , lack o physical ac i i y,
obesi y, high blood p essu e, smoking, and diabe es. Impo an ly, hese ac o s a e
con ollable. Addi ionally, a ia ions in social and economic s a us, es ic ed access o
p e en i e heal hca e, and an aging popula ion exace ba e he issue. Despi e ad ancemen s
in medical ea men and inc eased public awa eness, he ise in hea disease a es indica es
ha hese e o s a e s ill inadequa e [5, 6]. Deep-lea ning models ha a e based on a single
deep-lea ning a chi ec u e a e solo deep-lea ning models. Models ha a e p oduced by
connec ing wo o mo e deep-lea ning a chi ec u es a e hyb id deep-lea ning (HDL) models.
267
h p://am esea ch e iew.com/index.php/Jou nal/abou
Volume 3, Issue 10 (2025)
Online ISSN P in ISSN
. .
h p://am esea ch e iew.com/index.php/Jou nal/abou
Role o Machine Lea ning in Heal hca e
Machine lea ning (ML) and deep lea ning (DL) came o he escue medical diagnos ics has
shown emendous po en ial, pa icula ly in p edic ing c i ical condi ions like hea a acks.
By p ocessing and analyzing he la ge amoun o da a, Machine lea ning (ML) and mul i-
laye ed neu al ne wo k models a e use ul in p edic ing hea disease [7, 8]. The abili y o
examine he ea ly isk o ca dio ascula disease (CVD) can help imp o e he pa ien ’s heal h
and educe he associa ed isks. O e he las decade, ca dio ascula esea ch has
inc easingly in eg a ed ad anced compu a ional me hods, including a i icial in elligence
(AI), machine lea ning (ML), and deep lea ning (DL) [9, 10]. In ecen yea s, mos
ca dio ascula p edic ion s udies ha e implemen ed machine lea ning echniques (ML) like
suppo ec o machines (SVM), decision ees (DT), and nai e Bayes (NB) [11, 12].
S ill, i is ac ually challenging o ha ness he as amoun o clinical da a and use i o model
aining. Implan ing in clinical se ings emains challenging, usually esul ing in less accu a e
esul s [13, 14]. Deep Lea ning (DL), a specialized b anch o machine lea ning (ML) ha
enables he p ocessing o la ge amoun s o da a a a e y high speed wi hou any accu acy
issues. In ecen yea s, esea che s and scien is s ha e been con inuously explo ing he
applica ion o deep lea ning in he medical ield, as hey ha e achie ed good esul s in o he
ields. Fo example, esea che s ha e success ully used deep lea ning (DL) models,
including, con olu ional neu al ne wo k (CNN), a Long Sho -Te m Memo y (LSTM), and a
CNN-LSTM o p edic hea diseases using mul iple da a se s [15].
In addi ion, many da ase s ha e been de eloped by esea che s o p edic hea disease.
Rema kable da ase s such as he UCI Hea Disease Da ase , he F amingham Hea S udy,
he Hea Failu e Clinical Reco ds, and ca dio ascula da ase s play a pi o al ole in hea
disease S udies claim ha he p oposed ea u e selec ion me hod needs o be able o
op imally balance he mos ele an ea u es in he da ase o imp o e he p edic ions. The
au ho s sugges ed ha a new ea u e selec ion me hod is needed o choose he bes mix o
impo an ea u es in a da ase so ha p edic ion pe o mance can be imp o ed. Many hea
disease p edic ion models a e no sui able o eal-wo ld clinical use because hei inne
wo kings a e di icul o in e p e . Open-sou ce models can help make hese ools mo e
268
h p://am esea ch e iew.com/index.php/Jou nal/abou
Volume 3, Issue 10 (2025)
Online ISSN P in ISSN
. .
h p://am esea ch e iew.com/index.php/Jou nal/abou
accessible, bu some a e s ill no a ailable o he public. Wi hou open-sou ce so wa e, i is
ha de o medical p o essionals o build p edic i e hea disease p edic ion sys ems [16].
De eloping new echniques also equi es collabo a ion among expe s om di e en ields.
I is impo an o igu e ou how hese sys ems can wo k on eal- ime da a wi hou always
needing a physician o supe ise hem. A p esen , many la ge medical ins i u ions do no
ha e s ong p edic i e o ea ly diagnosis sys ems in place [17].
Hea ea u e ex ac ion
The in es iga ion in ol es he ex ac ion o di e se a ibu es om he medical da a ob ained
ia heal hca e de ices. The imp o emen o p edic ion accu acy is one s ep owa ds
ex ending classical DL app oaches wi h speci ic and in e p e able unc ions [16]. In addi ion,
DL can also be e ec i ely used along wi h o he echnologies o enhance accu acy, ea u e
selec ion, and da a classi ica ion. Addi ionally, s ochas ic me hods migh be conside ed o
enhance he pe o mance o hea disease p edic ion. Ne e heless, such hyb id models could
dec ease he p edic i e pe o mance. Fu he mo e, he e is a dea h o s anda d c i e ia o
selec ing pe o mance e alua ion p ocedu es and me ics ha can be employed in assessing
he e ec i eness o new echnologies.
Eq (4)
Eq (5)
Acco dingly, he es ablishmen o new es e alua ion indica o s and igo ous e i ica ion is
bene icial o imp o e s e iliza ion p edic ion models [18].
These da ase s con ain a as numbe o a ibu es ha help in he accu a e p edic ion o hea
diseases. Bo h changeable and non-changeable ac o s con ibu e o he p edic ion o hea
disease. Non- changeable ac o s include gende , e hnic backg ound, and amily his o y. On
he o he hand, changeable isk ac o s such as choles e ol le el, blood p essu e, unheal hy
li es yle habi s, and smoking can be al e ed and con olled h ough speci ic measu es and
medical ea men [19, 20]. These cha ac e is ics in luenced he c ea ion o la ge da ase s,
and esea che s ha e made conside able e o s o e ine and enhance hese da ase s.
Table 1 unde sco es he echniques o enhanced p e en i e ca e, ea ly diagnosis, and
li es yle changes o mi iga e bo h he heal h and inancial impac s o hea a acks ac oss he
na ion.
Table 1. Summa y o exis ing echniques on hea disease p edic ion
Me hod
Key
Con ibu ions
P ecision%
Recall
%
F1
Sco e%
Re
T adi ional
Su ey o
92
90.3
91.9
[21]
269
h p://am esea ch e iew.com/index.php/Jou nal/abou
Volume 3, Issue 10 (2025)
Online ISSN P in ISSN
. .
h p://am esea ch e iew.com/index.php/Jou nal/abou
ML
echniques
exis ing
app oaches o
hea disease
p edic ion
Supe ised
lea ning
models
Hea disease
p edic ion
using
supe ised
lea ning
algo i hms
82
91.2
91.1
[22,
23]
ML
classi ica ion
me hods
Summa ized
classi ica ion
echniques o
hea disease
p edic ion
88.2
94.5
91.3
[24,
25]
ML & so
compu ing
O e iew o
ML and so
compu ing
app oaches o
hea disease
p edic ion
92.6
94.8
91.9
[26,
27]
ML wi h
mul iple da a
modali ies
Summa ized
hea disease
p edic ion wi h
ML using
mul iple da a
sou ces
90.5
90.3
92.6
[28,
29]
AI in
ca dio ascula
CT
Re iewed AI-
based
app oaches in
ca dio ascula
CT and u u e
implica ions
92.5
89.2
87.5
[30,
31]
So
compu ing o
hea disease
S udied use o
so compu ing
in hea disease
p edic ion and
diagnosis
88.1
83.4
91.9
[32]
ML and DL
algo i hms
Analyzed
di e en hea
diseases using
bo h ML and
DL me hods
86.4
90.3
85.6
[33]
270
h p://am esea ch e iew.com/index.php/Jou nal/abou
Volume 3, Issue 10 (2025)
Online ISSN P in ISSN
. .
h p://am esea ch e iew.com/index.php/Jou nal/abou
AI o
inhe i ed hea
diseases
Re iewed
applica ions o
AI models in
inhe i ed HD
93.2
92.8
96.1
[34]
ML on ECG
signals
Focused on
ML echniques
o hea
disease
diagnosis om
ECG da a
94.2
84.3
86.3
[35,
36]
Figu e 1. Gene alize Hea disease p edic ion App oaches [37]
As shown in Table 1, p edic ing hea disease has a long his o y; howe e , mos exis ing
s udies employ adi ional machine lea ning (ML) models. Howe e , some use bo h machine
lea ning (ML) and deep lea ning models (DL). Each me hod has i s own limi a ions,
271
h p://am esea ch e iew.com/index.php/Jou nal/abou
Volume 3, Issue 10 (2025)
Online ISSN P in ISSN
. .
h p://am esea ch e iew.com/index.php/Jou nal/abou
ad an ages, and disad an ages. To be e unde s and he esea ch landscape, p io s udies on
hea disease p edic ion Me hods we e e iewed. Table 2 p o ides a comp ehensi e e iew
o hese s udies [38, 40].
Table 2. Rele an Machine Lea ning Models on hea disease p edic ion
Disc ip ion
Key Con ibu ions
Model
Accu acy
Re
So compu ing o
hea disease
S udied use o so
compu ing in hea
disease p edic ion
and diagnosis
NB, DT,
DF, and K-
NN
classi ie s
KNN:90.7,
DT: 80.2,
RF: 84.2,
NB: 88.15
[41]
ML and DL
algo i hms
Analyzed di e en
hea diseases using
bo h ML and DL
me hods
SVM, NB
LR, DNN,
DT, RF,
and K-NN.
SVM:97.41,
NB: 91.38,
LR: 96.29,
DNN: 98.15,
DT: 96.42,
RF: 90.46,
KNN: 96.42
[42,
43]
AI o inhe i ed
hea diseases
Re iewed
applica ions o AI
models in inhe i ed
HD
KACGAN-
based
model
98.15, DT:
[44,
45]
ML on ECG
signals
Focused on ML
echniques o hea
disease diagnosis
om
ECG da a
RF
96.42, RF:
[46,
47]
ML wi h mul iple
da a modali ies
Summa ized hea
disease p edic ion
wi h ML using
mul iple da a
sou ces
KNN
90.46, KNN:
[48,
49]
AI in
ca dio ascula CT
Re iewed AI-based
app oaches in
ca dio ascula CT
and u u e
implica ions
CNN
classi ie s
89.2
[50]
Analyze ele an esea ch on p edic ing hea disease using machine lea ning (ML) and deep
lea ning (DL) models o execu e his esea ch. S udies ha applied machine lea ning (ML) o
deep lea ning (DL) we e excluded om he analysis. F om he selec ed pape s, we ex ac ed
de ails such as he yea o publica ion, p edic ion echniques (ML, DL, o hyb id
272
h p://am esea ch e iew.com/index.php/Jou nal/abou
Volume 3, Issue 10 (2025)
Online ISSN P in ISSN
. .
h p://am esea ch e iew.com/index.php/Jou nal/abou
app oaches), da ase s used (public o sel -c ea ed), and epo ed con ibu ions. S udies we e
ca ego ized in o h ee g oups: (i) classical machine lea ning (ML), (ii) deep lea ning (DL),
and (iii) in eg a ed app oaches. E en ually, we ecapi ula ed ou indings in Tables, which
p o ide a de ailed o e iew o he su eyed and analyzed me hods.
This able ensu es ha he e iew is wide, o ganized, and equi able. We applied nume ous
sea ch me hods o collec all app op ia e li e a u e in his e iew. We concen a ed on
keywo ds and subjec headings ela ed o hea disease p edic ion models and deep lea ning,
using he me hod om ea lie s udies and sea ching only English sou ces. To be ho ough
and a oid o e lap, we included bo h o wa d and backwa d sea ches. We also elied on a
keywo d-based s a egy o keep he sea ch bo h b oad and a ge ed.
Li e a u e Re iew
This subsec ion summa izes he esea ch on exis ing wo k on using deep lea ning (DL)
echnology o hea disease. Table 6 comp ehensi ely in oduces he exis ing wo k o
au ho s on deep lea ning o hea disease. In he ield o hea disease p edic ion, esea che s
ha e deployed a huge a ay o me hods wi h g ea achie emen s [51, 52]. This s a ed he
p ocess o con olu ional neu al ne wo ks (CNNs) in ca ego izing indi iduals as i o un i
wi hin a Cle eland da ase [53, 54].
Eq (6)
Thei model a ained he imp essi e es accu acy o 96% and aining accu acy o 97%.
Especially, hey in eg a ed he clinical pa ame e s o iden i y he pa ien s' isk ac o s,
enabling ea ly isk p edic ion. In addi ion, hey expanded on he bene i s o a balanced
da ase o o e come he limi a ions posed by adi ional machine lea ning (ML) [55, 56].
U ilized he powe o a con olu ional neu al ne wo k (CNN) o deal wi h ea ly-s age hea
disease. Thei s udy clea ly de ined he dominance o a con olu ional neu al ne wo k (CNN)
o e classical me hods using he Cle eland da ase and achie ed he admi able accu acy o
94.78% [57, 58]. Thei model passes he p e-p ocessing and ea u e ex ac ion, and also in
p edic ion, highligh ing i s commendable capabili ies [59, 60].
√ Eq (7)
Eq (8)
273
h p://am esea ch e iew.com/index.php/Jou nal/abou
Volume 3, Issue 10 (2025)
Online ISSN P in ISSN
. .
h p://am esea ch e iew.com/index.php/Jou nal/abou
Table 3 p o ides he de ailed in o ma ion abou an o e iew o deep lea ning (DL)
app oaches o hea disease p edic ion.
Table 3. Compa a i e O e iew o deep lea ning (DL) Techniques o Hea Disease
P edic ion
Model
Da ase
Model
P ecission
Accu acy
Re
Ensemble
DL +
Fea u e
Fusion
Clinical +
senso da a
98.5%
Combining wea able
senso and clinical da a
imp o ed p edic ion
[60,
61]
Deep
Neu al
Ne wo k
(DNN)
Hea disease
da ase s
93.33%
Deepe ne wo k
ou pe o med ANN and
simple models
[62,
63]
Mul i- ask
Deep &
Wide NN
Hea ailu e
da a
Supe io
o ecas ing
(no %
gi en)
Mul i- asking cap u ed
sha ed ea u es
E ec i ely
[64,
65]
CNN
Cle eland
da ase
94.78%
CNN achie ed s ong
p edic i e pe o mance
s. adi ional ML
Models
[66,
67]
CNN
Cle eland
da ase
96%
Classi ied ― i ‖ s
―un i ‖ pa ien s wi h
high accu acy
[68,
69]
LSTM-
DBN
Fou ECG
da ase s
88.42%
Used ime- equency
ECG signals; b oade
da ase co e age
[70,
71]
CNN
Cle eland
da ase
94.78%
CNN achie ed s ong
p edic i e pe o mance
s. adi ional ML
Models
[72,
73]
CNN
Cle eland
da ase
96%
Classi ied ― i ‖ s
―un i ‖ pa ien s wi h
high accu acy
[74]
LSTM-
DBN
Fou ECG
da ase s
88.42%
Used ime- equency
ECG signals; b oade
da ase co e age
[75,
76]
280
h p://am esea ch e iew.com/index.php/Jou nal/abou
Volume 3, Issue 10 (2025)
Online ISSN P in ISSN
. .
h p://am esea ch e iew.com/index.php/Jou nal/abou
(ANNs). Employed open-access da ase s, which we e pa i ioned in o aining and es ing
se s. Thei analysis e ealed ha he Cle eland da ase is one o he mos commonly
employed da ase s in hea disease esea ch. such as hose by Suja ha and Mahalakshmi.
Random Fo es (RF) wo ked bes wi h 95.60% accu acy [130]. A deep neu al ne wo k
(DNN) model using Talos ine- uning and ained i on eal pa ien eco ds. Talos pe o med
be e han o he op imize s and achie ed 90.78% accu acy, p o ing i can help make hea
disease p edic ions mo e dependable. The s udies used a ious da ase s and we e ca e ully
done o imp o e p edic ion models o u u e esea ch [131]. Chicco and his eam buil a
comple e sys em ha joined dis inc me hods, like Fuzzy Logic (FL) wi h models like
Decision T ees (DT), Suppo Vec o Machines (SVM), and A i icial Neu al Ne wo ks
(ANN), being es ed, and Adaboos . The Accomplishmen o his sys em came om using
ea u e educ ion and ea u e selec ion me hods, like LASSO and MRMR [40]. A e ha ,
Zeleznik and his eam c ea ed a model known as he Hyb id Random Fo es wi h Linea
Model (HRFLM) app oach. This me hod used a ea u e selec ion echnique along wi h a
Random Fo es (RF) model o enhance he model's abili y o p edic ou comes. The model
wo ked well a inding he mos impo an ea u es o p edic ing hea disease and had an
accu acy o 88.7% [132]. Neu al Ne wo ks wi h Decision T ees (DT) o de elop a special
hyb id sys em. This sys em pe o med be e han olde me hods and showed highe
accu acy in classi ying hea disease. All hese s udies ep esen majo p og ess in hea
disease p edic ion and help in building sys ems ha a e bo h accu a e and e icien .
Acco ding o S aw and Wu, common supe ised lea ning echniques—including Random
Fo es (RF), Decision T ee (DT), and ensemble app oaches—a e essen ial in p edic i e
modelling and a e e y use ul in analyzing medical da a. These algo i hms play an impo an
ole in diagnosing di e en ypes o hea diseases [133]. In oduced a new me hod ha
combined mul i-laye neu al ne wo ks employing a hie a chical, componen -based lea ning
amewo k. This enhanced hea disease p edic ion because i unde s ood he complex
ela ionships be ween di e en isk ac o s mo e e ec i ely. I also ga e be e esul s han
adi ional me hods. Fu he mo e, Das and his colleagues used impo an isk- ela ed ea u es
ha we e de i ed using ime-se ies analysis o pa ien da a. Then hey applied a ough se
echnique o s udy he ela ionships be ween hose ea u es. Thei esea ch showed ha his
me hod can p edic hea disease e ec i ely and plays an impo an ole in heal hca e
analy ics [134]. The analysis ound ha he mos commonly used da ase is he Cle eland
da ase , which comes om he UCI Reposi o y. E en hough his da ase has 76 ea u es,
mos o he models used only 14 o hem, such as age, gende , ches pain ype, blood
p essu e, ECG esul s, maximum hea a e, blood suga , and he numbe o majo blood
essels. In e ms o popula i y, he S a log (Hea ) da ase came in second, and he Hunga ian
da ase was hi d [135]. The de elope s o hea disease p edic ion ha e used a ious
languages. Py hon is one o he p e e ed p og amming languages, wi h 75% o he
esea che s desc ibing i as a a o i e p og amming language, as desc ibed in igu e 8. A
numbe o hem a e p obably MATLAB, 9%, R, 8%, Ja a, 7%, and Knowledge
ep esen a ion language SWRL (Seman ic Web Rule Language), 1%. each is also signi ican
in he case o de ice +DL and IoT +DL. All o he s a egies a e less equen ly u ilized: 6%,
6%, 4%. The pape p o ides a succinc o e iew o he Deep Lea ning (DL), Enhanced
281
h p://am esea ch e iew.com/index.php/Jou nal/abou
Volume 3, Issue 10 (2025)
Online ISSN P in ISSN
. .
h p://am esea ch e iew.com/index.php/Jou nal/abou
T ans e Deep Lea ning (ETDL), and In eg a ed DL app oaches. To imp o e p edic ion
esul s, bigge and mo e a ied da ase s a e needed. Algo i hms need o be alida ed by
in eg a ing mul iple isk elemen s wi hin e y la ge coho s [136, 137]. API o cloud-based
da ase s can be hos ed o esea ch pu poses, since cloud compu ing e icien ly handles la ge
olumes o pa ien eco ds IoT de ices enable he eal- ime eco ding o key clinical
indica o s. Collabo a ion wi h physicians is equally impo an o collec meaning ul da a o
model imp o emen s. Enhancing p edic i e accu acy by subjec ing models o mul i- acili y
da ase s is mos likely o be mo e e ec i e [42]. Ne e heless, alida ion emains a p oblem,
hough lab es esul s a e some o he mos aluable o e alua ing p edic ion accu acy
[138,139]. Mo e gene al medical eco ds may enhance he accu acy o some p edic ion
models, o ins ance, o ca diac CT scans. Finally, esea che s sugges using eal-wo ld
da ase s ins ead o jus heo e ical ones o simula ions.
Models mo e e icien when wo king wi h da ase s ha ha e a lo o missing in o ma ion,
hei ea u e selec ion me hods should be changed, his will enhance he esul s o he model
as a whole. Pai wise classi ica ion wi h ex a ea u es has also been p oposed o inc eased
accu acy. In o de o imp o e he e iciency o models ha ake da ase s wi h subs an ial
missing alues, hei ea u e selec ion s a egies should be al e ed. I has been p oposed in
s udies [140, 141]. Implemen ing ensemble classi ie s wi h ex a ea u es p o ides be e
models o p edic ing he s aging and se e i y o a gi en condi ion, hus enhancing he
esul s o he model as a whole. Pai wise classi ica ion wi h ex a ea u es has also been
p oposed o inc eased accu acy. Managing a big numbe o ea u es in combina ion wi h
medical da a eco ds is a ask ha is known o be di icul , and hus, a dedica ed echnique
o ea u e educ ion is needed. I is also c ucial o de elop a be e echnique ha ea u es
ea u e elimina ion, missing da a impu a ion, noise handling, and mo e, o boos he accu acy
o a model’s p edic ions [142, 143].
Me hod and Ma e ials
The p ima y objec i e o his s udy is o de elop a compu e ized amewo k o p edic ing
he p obabili y o hea disease, he eby p o iding aluable decision-suppo ools o
heal hca e p o essionals and imp o ing pa ien ou comes. To achie e his goal, a ange o
machine lea ning algo i hms was applied o a s uc u ed da ase , and he co esponding
esul s a e comp ehensi ely analyzed in his epo . The p oposed me hodology is u he
enhanced h ough igo ous da a p ep ocessing, encompassing da a cleaning, elimina ion o
non-con ibu o y a iables, and inco po a ion o addi ional clinical pa ame e s such as Mean
A e ial P essu e (MAP) and Body Mass Index (BMI). Following p ep ocessing, he da ase
is pa i ioned based on gende o enable mo e nuanced analysis, and k-modes clus e ing is
employed o unco e la en pa e ns wi hin subpopula ions. The e ined da ase is hen
u ilized o ain p edic i e models capable o p oducing obus and eliable diagnos ic
ou comes. This imp o ed me hodological amewo k is expec ed o subs an ially enhance
p edic i e p ecision and o e all model e icacy, as demons a ed in he subsequen sec ions
o his s udy.
282
h p://am esea ch e iew.com/index.php/Jou nal/abou
Volume 3, Issue 10 (2025)
Online ISSN P in ISSN
. .
h p://am esea ch e iew.com/index.php/Jou nal/abou
P oposed Enhanced Hea disease p edic ion Model
This s udy seeks o de elop a obus and comp ehensi e amewo k o p ecise hea disease
p edic ion h ough he in eg a ion o ad anced machine lea ning pa adigms, ea u e selec ion
mechanisms, and dimensionali y educ ion echniques. By le e aging sophis ica ed
algo i hms, he p oposed model e ec i ely unco e s and in e p e s complex, nonlinea
ela ionships embedded wi hin clinical da a. The inco po a ion o ensemble deep lea ning
a chi ec u es and inno a i e ea u e usion s a egies enables he sys em o deli e accu a e
and imely diagnos ic p edic ions, p o iding heal hca e p o essionals wi h an in elligen
decision-suppo ool o imp o e diagnos ic accu acy and pa ien ou comes.
The hyb id p edic i e amewo k is s uc u ed in o h ee p incipal phases: da a acquisi ion,
p ep ocessing, and classi ica ion—each se ing a c ucial unc ion in op imizing model
pe o mance. Du ing he p ep ocessing phase, me iculous p ocedu es a e implemen ed o
ensu e da a in eg i y and enhance compu a ional e iciency. These include he impu a ion o
missing alues, accomplished h ough he ML-HDPM app oach, which accu a ely es ima es
incomple e da a en ies. In addi ion, an ex ensi e ea u e selec ion p ocess is employed o
iden i y he mos disc imina i e a ibu es ele an o hea disease p edic ion. This p ocess
le e ages a hyb id op imiza ion s a egy ha syne gis ically combines he Gene ic Algo i hm
(GA) and Recu si e Fea u e Elimina ion Me hod (RFEM), he eby enabling he ex ac ion o
salien ea u es ha signi ican ly con ibu e o p edic i e p ecision and model obus ness.
Figu e 4. P oposed F amewo k o Hea Disease P edic ion App oaches
283
h p://am esea ch e iew.com/index.php/Jou nal/abou
Volume 3, Issue 10 (2025)
Online ISSN P in ISSN
. .
h p://am esea ch e iew.com/index.php/Jou nal/abou
The expe imen al amewo k o his s udy was sys ema ically designed o e alua e model
pe o mance unde a ying condi ions h ough h ee dis inc es ing scena ios: (1) u ilizing
he comple e da ase wi hou applying any da a educ ion echniques, (2) employing a
educed da ase de i ed om a ep esen a i e subse o he o iginal da a, and (3)
implemen ing a modi ied bee algo i hm on he educed da ase .
E alua ion o he Enhanced Hea Disease P edic ion Model
The modi ied bee algo i hm, an enhanced adap a ion o he con en ional bee op imiza ion
me hod, was speci ically enginee ed o imp o e pe o mance by i e a i ely explo ing and
ine- uning model pa ame e s. All expe imen s we e conduc ed on a compu a ional se up
equipped wi h an In el i5 p ocesso and 3 GB o RAM, using MATLAB e sion 9.2 as he
p ima y de elopmen en i onmen . In each scena io, he da ase was sys ema ically
pa i ioned o aining and es ing in acco dance wi h he expe imen al design. To ensu e
me hodological igo and mi iga e o e i ing, k- old c oss- alida ion was employed,
whe ein he da ase was di ided in o k mu ually exclusi e subse s. Each subse was
sequen ially used as a alida ion se while he emaining subse s we e u ilized o aining.
This p ocess was epea ed k imes, and he mean pe o mance me ics we e compu ed o
p o ide a obus and unbiased e alua ion o he model’s p edic i e capabili y ac oss di e se
condi ions.
∑
∑
∑
∑
∑
∑
∑
∑
284
h p://am esea ch e iew.com/index.php/Jou nal/abou
Volume 3, Issue 10 (2025)
Online ISSN P in ISSN
. .
h p://am esea ch e iew.com/index.php/Jou nal/abou
Figu e 5. Accu acy analysis o p edic ing hea disease
Figu e 6. P ecision analysis o p edic ing hea disease.
285
h p://am esea ch e iew.com/index.php/Jou nal/abou
Volume 3, Issue 10 (2025)
Online ISSN P in ISSN
. .
h p://am esea ch e iew.com/index.php/Jou nal/abou
Figu e 7. False posi i e a e analysis o p edic ing hea disease
Figu e 8. T ue posi i e a e analysis o p edic ing hea disease
The ML-HDPM app oach exhibi s supe io pe o mance in e ms o F-sco e, achie ing
91.5% du ing aining and 89.6% du ing es ing, su passing all compa a i e algo i hms as
shown in Figu e 10. This ou s anding pe o mance is a ibu ed o he comp ehensi e design
o he model, which e ec i ely in eg a es ea u e selec ion, da a balancing, and deep
lea ning op imiza ion echniques. By cap u ing signi ican pa e ns wi hin hea disease
da ase s, ML-HDPM a ains an op imal balance be ween p ecision and ecall, esul ing in
consis en ly highe F-sco es. These esul s emphasize he model’s s ong p edic i e
286
h p://am esea ch e iew.com/index.php/Jou nal/abou
Volume 3, Issue 10 (2025)
Online ISSN P in ISSN
. .
h p://am esea ch e iew.com/index.php/Jou nal/abou
capabili y and i s po en ial o enhance diagnos ic accu acy and imp o e o e all pa ien ca e
ou comes.
Figu e 9. F sco e analysis o p edic ing hea disease.
The simula ion esul s unde sco e he obus ness and p edic i e e icacy o he p oposed
Machine Lea ning Hyb id Deep P edic i e Model (ML-HDPM) in o ecas ing hea disease
ou comes. Achie ing aining and es ing accu acies o 95.5% and 89.1%, espec i ely, he
ML-HDPM demons a es supe io pe o mance ela i e o compe ing algo i hms. This
enhanced capabili y is u he alida ed by consis en accu acy measu es o 94.8% ( aining)
and 88.3% ( es ing), as illus a ed in Figu e 11, con i ming he model’s gene alizabili y
ac oss di e se da ase s. Fu he mo e, he ML-HDPM achie es a ma ked educ ion in alse
posi i e a es (FPR)—8.2% du ing aining and 14.7% du ing es ing—indica ing i s
p o iciency in minimizing misclassi ica ion e o s and enhancing o e all p edic i e
p ecision. In pa allel, he model a ains no ably highe ue posi i e a es (TPR) o 96.2%
( aining) and 90.8% ( es ing), e lec ing i s capaci y o co ec ly iden i y hea disease cases
wi h high eliabili y. Collec i ely, hese esul s a i m ML-HDPM’s subs an ial po en ial as a
obus p edic i e ool o accu a e and eliable hea disease diagnosis.
287
h p://am esea ch e iew.com/index.php/Jou nal/abou
Volume 3, Issue 10 (2025)
Online ISSN P in ISSN
. .
h p://am esea ch e iew.com/index.php/Jou nal/abou
Figu e 10. ROC–a ea unde cu e o (a) MLP, p oposed Machine Lea ning Hyb id Deep
P edic i e Model (b) RF, (c) DT, and (d) XGB
TABLE 5: Compa a i e Analysis P oposed Model Using Mul iple Classi ie s based on UCI
ML Da ase
Clas
si ie
Model
Compu
a ion
Time
JC
Dice
Sco e
Sensi i
i y
Acc
u ac
y
Speci
ici y
P eci
sion
F-
Sco
e
NBB
3-Laye
CNN
K = 30
0.7
44
2
0.7442
0.6486
0.64
15
0.64
37
0.74
42
0.64
83
E-
CNN
U-Ne
K = 30
0.6
43
3
0.6433
0.6486
0.52
45
0.64
85
0.64
33
0.64
85
SV
M
VGG19
K = 30
0.1
43
0.8444
0.6485
0.74
42
0.74
42
0.74
42
0.64
86
288
h p://am esea ch e iew.com/index.php/Jou nal/abou
Volume 3, Issue 10 (2025)
Online ISSN P in ISSN
. .
h p://am esea ch e iew.com/index.php/Jou nal/abou
2
RNN
Incep io
nV3
K = 30
0.2
12
0.5245
0.6485
0.64
33
0.14
32
0.64
33
0.14
32
P op
osed
Mod
el
E icien
Ne B4
K = 30
0.6
22
2
0.7627
0.6486
0.74
84
0.21
2
0.64
33
0.21
2
Figu e 10. Sensi i i y s speci ici y
289
h p://am esea ch e iew.com/index.php/Jou nal/abou
Volume 3, Issue 10 (2025)
Online ISSN P in ISSN
. .
h p://am esea ch e iew.com/index.php/Jou nal/abou
Figu e 11. Sensi i i y s speci ici y o HHD and ARVC
Conclusion
This a icle e alua es a Deep Lea ning (DL), Enhanced T ans e Deep Lea ning (ETDL), and
hyb id Deep Lea ning app oaches o o ecas ing hea disease p edic ion. The me iculous
analysis shows ha CNN is he leading DL-based s a egy, Hyb id deep lea ning (DL)-based
Enhanced T ans e Deep Lea ning Enhanced T ans e Deep Lea ning is he mos in luen ial
Enhanced T ans e Deep Lea ning -based echnique and he mos u ilized in eg a ed
pa adigm in he con ex o DL. In ecen yea s, he e has been a g owing in e es in esea ch
ha combines DL and o he coope a i e echniques. The model was ained and e alua ed
using he UCI Machine Lea ning Hea Disease da ase , and i s pe o mance was
benchma ked agains s a e-o - he-a algo i hms such as A i icial Neu al Ne wo ks (ANNs)
and Recu en Ne wo ks (RNs). Empi ical e alua ions e eal ha Ca dioHelp achie es
ou s anding p edic i e pe o mance, wi h an accu acy o 97%, an F1-sco e o 93.4%, and a
p ecision imp o emen o 0.8% compa ed o exis ing baseline models. Fu he mo e, when
compa ed wi h ad anced hyb id a chi ec u es—including CNN-RNN, CNN-LSTM, and
CNN-BLSTM— he p oposed amewo k exhibi s accu acy enhancemen s o 2.35%, 1.34%,
and 1.95%, P edic ing hea disease accu a ely and quickly is impo an bu di icul .
Machine lea ning becomes highly e ec i e in iden i ying and ca ego izing pa ien s.
Ad anced machine lea ning and deep lea ning models, like SVMs and CNNs, can o ecas
pa ien s' medical his o ies and gene al well-being. I has also been ound ha he Py hon
language is he mos p e e ed one among all languages o implemen ing hese echnologies
because i p o ides ex ensi e lib a ies as well as communi y suppo . Also, he ac ha mos
o he in luen ial s udies come om jou nals p o es how academic his ield is; mos ly om
gian publishe s like IEEE, Sp inge , and Else ie . Though he domain has mo ed a long
way, eno mous challenges s ill exis ; impo an ly, big and di e se da ase s a e nowhe e o be
ound. This inadequacy pu s a e y high limi a ion on how much DL- based app oaches can
assis in imp o ing accu acy, obus ness, and o e all eliabili y when i comes o hea
disease p edic ions.
FUNDING STATEMENT: The au ho s ecei ed no speci ic unding o his s udy.
CONFLICTS OF INTEREST: The au ho s decla e ha hey ha e no con lic s o in e es o
epo ega ding he p esen s udy.
REFERENCES
Na ional Hea , Lung, and Blood Ins i u e, Medical Expendi u e Panel Su ey
(MEPS), unpublished abula ion (2019–2020) in AHA S a is ical Summa y 2025,
Tables 28-1 and 28-2.
Cen e s o Disease Con ol and P e en ion, ―Hea Disease Fac s,‖ U.S. Depa men o
Heal h & Human Se ices, Oc . 24, 2024. [Online]. A ailable:
h ps://www.cdc.go /hea -disease/da a- esea ch/ ac s-s a s/index.h ml
The Global S a is ics, ―Uni ed S a es Hea Disease S a is ics 2025 | Mo ali y S a s,‖ 2025.
[Online]. A ailable: h ps://www. heglobals a is ics.com/uni ed-s a es-hea -
296
h p://am esea ch e iew.com/index.php/Jou nal/abou
Volume 3, Issue 10 (2025)
Online ISSN P in ISSN
. .
h p://am esea ch e iew.com/index.php/Jou nal/abou
MACHINE LEARNING. Vol.-20, No.-3, Ma ch (2025) pp 54 - 72
Yousa , M., Khalid, F., Saleem, M. U., Din, M. U., Shahid, A. K., & Khan, H. (2025). A
Deep Lea ning-Based Enhanced Sen imen Classi ica ion and Consis ency Analysis
o Que ies and Resul s in Sea ch Using O acle Hyb id Fea u e Ex ac ion. Spec um
o Enginee ing Sciences, 3(3), 99-121.
Khan, H., Usman, R., Ahmed, B., Hashimi, U., Najam, Z., & Ahmad, S. (2019). The mal-
awa e eal- ime ask schedulabil y es o ene gy and powe sys em op imiza ion
using homogeneous cache hie a chy o mul i-co e sys ems. Jou nal o Mechanics o
Con inua and Ma hema ical Sciences, 14(4), 442-452.
Ali, M., Cheema, S. M., Ayub, N., Naz, A., & Aslam, Z. (2022, Decembe ). Impac o
adop ing obo s as eache s: a e iew s udy. In 2022 In e na ional Con e ence on
Eme ging Technologies in Elec onics, Compu ing and Communica ion
(ICETECC) (pp. 1-9). IEEE.
Na eed, A., Khan, H., Im iaz, Z., Hassan, W., & Fa eed, U. (2024). Applica ion and E hical
Aspec s o Machine Lea ning Techniques in Ne wo king: A Re iew. Spec um o
enginee ing sciences, 2(3), 455-501.
Ayub, N., Bakhe , S., A shad, M. J., Saleem, M. U., Anam, R., & Fuzail, M. Z. (2025). AN
ENHANCED MACHINE LEARNING AND BLOCKCHAIN-BASED
FRAMEWORK FOR SECURE AND DECENTRALIZED ARTIFICIAL
INTELLIGENCE APPLICATIONS IN 6G NETWORKS USING ARTIFICIAL
NEURAL NETWORKS (ANNS). Spec um o Enginee ing Sciences, 3(4), 348-
364.
Gha oo , U., Ayub, N., Yaseen, A., Anas, M., Fa ooq, I., Khan, S., & Naghman, N. F.
(2025). AI Assis ed Hea Disease P edic ion and Classi ica ion and Segmen a ion
based on PIMA and UCI Machine Lea ning Da ase s. Annual Me hodological
A chi e Resea ch Re iew, 3(7), 248-276.
Sa wa , H. Khan, I. Uddin, R. Waleed, S. Ta iq, "An E icien E-Comme ce Web Pla o m
Based on Deep In eg a ion o MEAN S ack Technologies", Bulle in o Business and
Economics (BBE)., ol. 12, no. 4, pp. 447-453, Jun. 2023
Ali, M., Cheema, S. M., Ayub, N., Naz, A., & Aslam, Z. (2022, Decembe ). Blockchain-
based P i acy P ese a ion F amewo k o IoT-Based In o ma ion Sys ems. In 2022
3 d In e na ional Con e ence on Inno a ions in Compu e Science & So wa e
Enginee ing (ICONICS) (pp. 1-7). IEEE, 2022
Asgha , M. A., Aslam, A., Bakhe , S., Saleem, M. U., Ahmad, M., Goha , A., & Khan, H.
(2025). An E icien In eg a ion o A i icial In elligence-based Mobile Robo s in
C i ical F ames o he In e ne o Medical Things (IoMTs) Using (ADP2S) and
Con olu ional Neu al Ne wo ks (CNNs). Annual Me hodological A chi e Resea ch
Re iew, 3(4), 160-183.
Ali, M., Cheema, S. M., Aslam, Z., Naz, A., & Ayub, N. (2023, Ma ch). CBAI: Cloud-Based
Agile In as uc u e o Enhancing Dis ibu ed Agile De elopmen . In 2023 4 h
In e na ional Con e ence on Compu ing, Ma hema ics and Enginee ing
Technologies (iCoMET) (pp. 1-6). IEEE.
Ayub, N., Yaseen, A., Amin, M. N., Rizwan, S. M., Fa ooq, I., & Hussain, M. Z. (2025).
297
h p://am esea ch e iew.com/index.php/Jou nal/abou
Volume 3, Issue 10 (2025)
Online ISSN P in ISSN
. .
h p://am esea ch e iew.com/index.php/Jou nal/abou
Reliable Fede a ed Lea ning (Rdl) Assis ed In usion De ec ion And Classi ica ions
App oach Using (Ssl/Tls) Fo Ne wo k Secu i y. Annual Me hodological A chi e
Resea ch Re iew, 3(7), 376-400.
Jabeen, T., Mehmood, Y., Khan, H., Nasim, M. F., & Naq i, S. A. A. (2025). Iden i y The
and Da a B eaches How S olen Da a Ci cula es on he Da k Web: A Sys ema ic
App oach. Spec um o enginee ing sciences, 3(1), 143-161.
Khan, A. K., Bakhe , S., Ja ed, A., Rizwan, S. M., & Khan, H. (2025). F amewo k o
P edic ing Cus ome Sen imen Awa e Que ies and Resul s in Sea ch Using O acle
and Machine Lea ning. Spec um o Enginee ing Sciences, 3(2), 588-617.
Abdullah, M. M., Khan, H., Fa han, M., & Khadim, F. (2024). An Ad ance Machine
Lea ning (ML) App oaches o Anomaly De ec ion based on Ne wo k
T a ic. Spec um o enginee ing sciences, 2(3), 502-527.
Hashmi, U., & ZeeshanNajam, S. A. (2023). The mal-Awa e Real-Time Task Schedulabil y
es o Ene gy and Powe Sys em Op imiza ion using Homogeneous Cache
Hie a chy o Mul i-co e Sys ems. Jou nal o Mechanics o Con inua and
Ma hema ical Sciences, 14(4), 442-452.
Sul an, H., Rahman, S. U., Muni , F., Ali, A., Younas, S., & Khan, H. (2025). Ins i u ional
dynamics, inno a ion, and en i onmen al ou comes: a panel NARDL analysis o
BRICS na ions. En i onmen , De elopmen and Sus ainabili y, 1-43.
Hussain, M., Ahmed, H. A., Baba , M. Z., Ali, A., Shahzad, H. M., Rehman, S. U., ... &
Alshah ani, A. M. (2025). An Enhanced Con olu ional Neu al Ne wo k (CNN)
based P-EDR Mechanism o Diagnosis o Diabe ic Re inopa hy (DR) using
Machine Lea ning. Enginee ing, Technology and Applied Science Resea ch, 15(1),
19062-19067.
Ramzan, M. S., Nasim, F., Ahmed, H. N., Fa ooq, U., Nawaz, M. S., Bukha i, S. K. H., &
Khan, H. (2025). An Inno a i e Machine Lea ning based end- o-end Da a Secu i y
F amewo k in Eme ging Cloud Compu ing Da abases and In eg a ed Pa adigms:
Analysis on Taxonomy, challenges, and Oppo uni ies. Spec um o enginee ing
sciences, 3(2), 90-125.
Muj aba, A., Zul iqa , M., Azha , M. U., Ali, S., Ali, A., & Khan, H. (2025). ML-based
Fileless Malwa e Th ea s Analysis o he De ec ion o Cybe secu i y A ack based
on Memo y Fo ensics: A Su ey. The Asian Bulle in o Big Da a
Managemen , 5(1), 1-14.
Hussain, S., Sa wa , N., Ali, A., Khan, H., Din, I., Alqah ani, A. M., ... & Ali, A. (2025). An
Enhanced Random Fo es (ERF)-based Machine Lea ning F amewo k o
Resampling, P edic ion, and Classi ica ion o Mobile Applica ions using Tex ual
Fea u es. Enginee ing, Technology & Applied Science Resea ch, 15(1), 19776-
19781.
Ahmad, I., Nasim, F., Khawaja, M. F., Naq i, S. A. A., & Khan, H. (2025). Enhancing IoT
Secu i y and Se ices based on Gene a i e A i icial In elligence Techniques: A
Sys ema ic Analysis based on Eme ging Th ea s, Challenges and u u e
Di ec ions. Spec um o enginee ing sciences, 3(2), 1-25.
Khan, H., Im iaz, M. A., Siddique, H., Rana, M. T. A., Ali, A., Baig, M. Z., ... & Alsaawy,
298
h p://am esea ch e iew.com/index.php/Jou nal/abou
Volume 3, Issue 10 (2025)
Online ISSN P in ISSN
. .
h p://am esea ch e iew.com/index.php/Jou nal/abou
Y. (2025). An Enhanced Task Mig a ion Technique Based on Con olu ional Neu al
Ne wo k in Machine Lea ning F amewo k.
Ahmed, A., Ja ed, M. A., Qu eshi, J. N., Khan, H., & Yousa , H. F. (2024). An insigh ul
Machine Lea ning based P i acy-P ese ing Technique o Fede a ed Lea ning. The
Asian Bulle in o Big Da a Managemen , 4(4), 332-343.
Fa ooq, I., Ahmed, S. A., Ali, A., Wa aich, M. A., Aqeel, M., & Khan, H. (2024). Enhanced
Classi ica ion o Ne wo ks Enc yp ed T a ic: A Concep ual Analysis o Secu i y
Assessmen s, Implemen a ion, T ends and Fu u e Di ec ions. The Asian Bulle in o
Big Da a Managemen , 4(4), 500-522.
Fawy, K. F., Rod iguez-O iz, G., Ali, A., Jadeja, Y., Khan, H., Pa hak, P. K., ... & Rahman,
J. U. (2025). Ca aly ic explo a ion me allic and nonme allic nano-ca alys s,
p ope ies, ole in pho oelec ochemis y o sus ainable applica ions. Re iews in
Ino ganic Chemis y, (0).
Liaqa , M. S., Sha i , N., Ali, A., Khan, H., Ahmed, H. N., & Khan, H. (2024). An Op imal
Analysis o Cloud-based Secu e Web Applica ions: A Sys ema ic Explo a ion based
on Eme ging Th ea s, Pi alls and Coun e measu es. Spec um o enginee ing
sciences, 2(5), 427-457.
Adil, M. U., Ali, S., Haide , A., Ja ed, M. A., & Khan, H. (2024). An Enhanced Analysis o
Social Enginee ing in Cybe Secu i y Resea ch Challenges, Coun e measu es: A
Su ey. The Asian Bulle in o Big Da a Managemen , 4(4), 321-331.
Maqsood, M., Da , M. M., Ja ed, M. A., & Khan, H. (2024). A Su ey on he In e ne o
Medical Things (IOMT) P i acy and Secu i y: Challenges Solu ions and Fu u e
om a New Pe spec i e. The Asian Bulle in o Big Da a Managemen , 4(4), 355-
368.
Khawa , M. W., Salman, W., Shaheen, S., Shakil, A., I ikha , F., & Faisal, K. M. I. (2024).
In es iga ing he mos e ec i e AI/ML-based s a egies o p edic i e ne wo k
main enance o minimize down ime and enhance se ice eliabili y. Spec um o
Enginee ing Sciences, 2(4), 115-132.
Ahmad, J., Salman, W., Amin, M., Ali, Z., & Shoka , S. (2024). A Su ey on Enhanced
App oaches o Cybe Secu i y Challenges Based on Deep Fake Technology in
Compu ing Ne wo ks. Spec um o Enginee ing Sciences, 2(4), 133-149.
Ayub, N., Ejaz, A., Hassan, B., Hussain, M. Z., Nadeem, M., Sabi , L., & Fa ima, S. (2025).
An E icien Machine Lea ning And Deep Lea ning Based Deep Packe Secu i y
F amewo k Fo De ec ion O Compu ing Ne wo k Faul s In The Io s. Spec um o
Enginee ing Sciences, 3(5), 659-674.
Ayub, N., Im iaz, M. A., Ali, E., Alqah ani, A. M., Ali, A., Ashu o , M., ... & Law, F. L.
(2025). A Decision F amewo k o In a Task Fixed P io i y INTEL PXA270
Dis ibu ed A chi ec u e o So RT-Applica ions Based on Deep
Lea ning. Enginee ing, Technology & Applied Science Resea ch, 15(3), 23553-
23558.
Ayub, N., Waheed, A., Ahmad, S., Akba , M. H. A., Fuzail, M. Z., & Hashmi, A. H. (2025).
S eng hening Ne wo k Secu i y: An E icien DL Enabled Da a P o ec ion and
P i acy F amewo k o Th ea Mi iga ion and Vulne abili ies De ec ion in IoT
299
h p://am esea ch e iew.com/index.php/Jou nal/abou
Volume 3, Issue 10 (2025)
Online ISSN P in ISSN
. .
h p://am esea ch e iew.com/index.php/Jou nal/abou
Ne wo k. Annual Me hodological A chi e Resea ch Re iew, 3(6), 1-25.
Fa ooq, M., Younas, R. M. F., Qu eshi, J. N., Haide , A., & Nasim, F. (2025). Cybe secu i y
isks in DBMS: S a egies o mi iga e da a secu i y h ea s: A sys ema ic
e iew. Spec um o enginee ing sciences, 3(1), 268-290.
Ayub, N., Habib, Z., Bakhe , S., Riaz, S., Rizwan, S. M., Abid, M., ... & Khan, H. (2025).
An Op imal Ai & Deep Lea ning Mechanism Fo Mi iga ing Hacking Th ea
Iden i ica ion Using Secu e Ne wo k In as uc u e Based On Linux And So wa e-
De ined Ne wo k (Sdn). Spec um o Enginee ing Sciences, 3(5), 675-687.
Aslam, I., Ta iq, W., Nasim, F., Khan, H., Khawaja, M. F., Ahmad, A., & Nawaz, M. S.
(2025). A Robus Hyb id Machine Lea ning based Implica ions and P e en ions o
Social Media Blackmailing and Cybe bullying: A Sys ema ic App oach.
Ayub, N., Anwe , M. A., Iqbal, A., Rizwan, S. M., Shahbaz, A., Abid, M. H., & Ra i, S.
(2025). Enhanced ML F amewo k based on A i icial Neu al Ne wo k o
coun e measu es o Da a P o ec ion and Ne wo k Vulne abili ies De ec ion in
Indus ial In e ne o Things. Annual Me hodological A chi e Resea ch
Re iew, 3(5), 410-431.
Akh a , M. H., Ali, A., Ali, S., Nasim, F., Aziz, M. H., Khan, H., & Naq i, S. A. A. (2025).
A No el Machine Lea ning App oach o Da abase Exploi a ion o Enhance
Da abase Secu i y: A Su ey. Spec um o Enginee ing Sciences, 3(2), 26-57.
Jabeen, T., Mehmood, Y., Khan, H., Nasim, M.F. and Naq i, S.A.A., 2025. Iden i y The
and Da a B eaches How S olen Da a Ci cula es on he Da k Web: A Sys ema ic
App oach. Spec um o enginee ing sciences, 3(1), pp.143-161.
A. S. Oli e , K. Ganesan, S. A. Yu a aj, T. Jayasanka , M. Y. Sikkanda , and N. B. P akash,
―Accu a e p edic ion o hea disease based on biosys em using eg essi e lea ning-
based neu al ne wo k classi ie ,‖ Jou nal o Ambien In elligence and Humanized
Compu ing, ol. 13, no. S1, pp. 1–9, 2021.
S. Dami and M. Yahaghizadeh, ―P edic ing ca dio ascula e en s wi h deep lea ning
app oach in he con ex o he In e ne o Things,‖ Neu al Compu ing and
Applica ions, ol. 33, no. 13, pp. 7979–7996, 2021.
F. Ali, S. El-Sappagh, I. S. Riazul, D. Kwak, A. Ali, M. Im an, and K. S. Kwak, ―A sma
heal hca e moni o ing sys em o hea disease p edic ion based on ensemble deep
lea ning and ea u e usion,‖ In o ma ion Fusion, ol. 63, pp. 208–222, 2020.
S. S. Sa mah, ―An e icien IoT-based pa ien moni o ing and hea disease p edic ion sys em
using deep lea ning modi ied neu al ne wo k,‖ IEEE Access, ol. 8, pp. 135784–
135797, 2020.
B. Wang, Y. Bai, Z. Yao, J. Li, W. Dong, Y. Tu, W. Xue, Y. Tian, Y. Wang, and K. He, ―A
mul i- ask neu al ne wo k a chi ec u e o enal dys unc ion p edic ion in hea
ailu e pa ien s wi h elec onic heal h eco ds,‖ IEEE Access, ol. 7, pp. 178392–
178400, 2019.
M. Khan, ―An IoT amewo k o hea disease p edic ion based on MDCNN classi ie ,‖
IEEE Access, ol. 8, pp. 34717–34727, 2020.
J. Sha i, M. S. Obaida , P. V. K ishna, B. Sadou, M. Punambal, and J. Gi anjali, ―P edic ion
o hea abno mali ies using deep lea ning model and wea able de ices in sma
300
h p://am esea ch e iew.com/index.php/Jou nal/abou
Volume 3, Issue 10 (2025)
Online ISSN P in ISSN
. .
h p://am esea ch e iew.com/index.php/Jou nal/abou
heal h homes,‖ Mul imedia Tools and Applica ions, ol. 81, pp. 543–557, 2022.
S. Sha ma and M. Pa ma , ―Hea diseases p edic ion using deep lea ning neu al ne wo k
model,‖ In e na ional Jou nal o Inno a i e Technology and Explo ing Enginee ing,
ol. 9, no. 3, pp. 2244–2248, 2020.
S. Nandy, M. Adhika i, V. Balasub amanian, V. Menon, X. Li, and M. Zaka ya, ―An
in elligen hea disease p edic ion sys em based on swa m-a i icial neu al ne wo k,‖
Neu al Compu ing and Applica ions, ol. 35, pp. 14723–14737, 2023.
P. Dhaka and B. Nagpal, ―WoM-based deep BiLSTM: Sma disease p edic ion model using
WoM-based deep BiLSTM classi ie ,‖ Mul imedia Tools and Applica ions, ol. 82,
pp. 25061–25082, 2023.
N. Sha ma, L. Mal iya, A. Jadha , and P. Lalwani, ―A hyb id deep neu al ne lea ning
model o p edic ing co ona y hea disease using andomized sea ch c oss-
alida ion op imiza ion,‖ Decision Analy ics Jou nal, ol. 9, p. 100331, 2023.
C. Zhou, A. Hou, P. Dai, A. Li, Z. Zhang, Y. Mu, and L. Liu, ―Risk ac o e inemen and
ensemble deep lea ning me hods on p edic ion o hea ailu e using eal heal hca e
eco ds,‖ In o ma ion Sciences, ol. 637, p. 118932, 2023.
A. A. Almaz oi, ―Su i al p edic ion among hea pa ien s using machine lea ning
echniques,‖ Ma hema ical Biosciences and Enginee ing, ol. 19, no. 1, pp. 134–145, 2022.
G. Gup a, U. Ada sh, R. N. Subba, and A. B. Rao, ―Compa ison o a ious machine
lea ning app oaches used in hea ailmen s p edic ion,‖ Jou nal o Physics: Con e ence
Se ies, ol. 2161, no. 1, p. 012010, 2022.
R. Bha i, A. Khampa ia, M. Shabaz, G. Dhiman, S. Pande, and P. Singh, ―P edic ion o
hea disease using a combina ion o machine lea ning and deep lea ning,‖
Compu a ional In elligence and Neu oscience, ol. 2021, p. 8387680, 2021.
P. Li, Y. Hu, and Z. P. Liu, ―P edic ion o ca dio ascula diseases by in eg a ing mul i-
modal ea u es wi h machine lea ning me hods,‖ Biomedical Signal P ocessing and
Con ol, ol. 66, p. 102474, 2021.
R. Biswas, A. R. Bee a olu, A. Ka im, S. Azam, M. T. Hasan, M. S. Alam, and P. Ghosh,
―A obus deep lea ning-based p edic ion sys em o hea disease using a
combina ion o i e da ase s,‖ in P oc. 31s In . Con . Compu e Theo y and
Applica ions (ICCTA), 2021, pp. 223–228.
D. Chicco and G. Ju man, ―Machine lea ning can p edic su i al o pa ien s wi h hea
ailu e om se um c ea inine and ejec ion ac ion alone,‖ BMC Medical
In o ma ics and Decision Making, ol. 20, no. 16, pp. 108–121, 2020.
R. B. Zeleznik, P. Eslami, e al., ―Deep con olu ional neu al ne wo k o p edic
ca dio ascula isk om compu ed omog aphy,‖ Na u e Communica ions, ol. 12,
no. 1,
p. 715, 2021.
M. A. Hassani, R. Tao, M. Kamyab, and M. H. Mohammadi, ―An app oach o p edic ing
hea disease using a hyb id neu al ne wo k and decision ee,‖ in P oc. 5 h In .
Con . Big Da a and Compu ing, Chengdu, China, 2020, pp. 84–89.
h p://am esea ch e iew.com/index.php/Jou nal/abou
Volume 3, Issue 10 (2025)
Online ISSN P in ISSN
. .
h p://am esea ch e iew.com/index.php/Jou nal/abou
Page 301
I. S aw and H. Wu, ―In es iga ing bias in heal hca e algo i hms: A sex-s a i ied analysis
o supe ised machine lea ning models in li e disease p edic ion,‖ BMJ Heal h
& Ca e In o ma ics, ol. 29, no. 1, pp. 142–156, 2022.
O. W. Samuel, B. Yang, Y. Geng, M. G. Asogbon, S. Pi bhulal, D. Mzu ikwao, O. P.
Idowu, T. J. Ogundele, X. Li, S. Chen, e al., ―A new echnique o he p edic ion
o hea ailu e isk d i en by hie a chical neighbo hood componen -based
lea ning and adap i e mul i-laye ne wo ks,‖ Fu u e Gene a ion Compu e
Sys ems, ol. 110, pp. 781–794, 2020.
S. Das, S. K. P adhan, S. Mish a, S. P adhan, and P. Pa naik, ―P edic ion o hea
diseases using so compu ing echnique,‖ in In elligen Sys ems: P oc. ICMIB,
Sp inge , Be lin, 2022, pp. 155–167.
S. Singhal, H. Kuma , and V. Pass icha, ―P edic ion o hea disease using CNN,‖
Ame ican In e na ional Jou nal o Resea ch in Science, Technology, Enginee ing
& Ma hema ics, ol. 23, no. 1, pp. 257–261, 2018.
P. Rani, R. Kuma , N. M. Ahmed, and A. Jain, ―A decision suppo sys em o hea
disease p edic ion based upon machine lea ning,‖ Jou nal o Reliable In elligen
En i onmen s, ol. 7, no. 3, pp. 263–275, 2021.
G. S. Sajja, ―A comp ehensi e e iew o a ious machine lea ning echniques o hea
disease p edic ion,‖ In e na ional Jou nal o Compu e Applica ions, ol. 183, p.
37, 2021.
B. Vaishali, V. Madhushi, C. P adeep, and S. Gau a , ―E icien hea disease p edic ion
using hyb id deep lea ning classi ica ion models,‖ IRBM, ol. 44, no. 5, p.
100786, 2023.
A. Mehmood, M. Iqbal, Z. Mehmood, A. I aza, M. Nawaz, T. Nazi , M. Masood, and M.
Masood, ―P edic ion o hea disease using deep con olu ional neu al ne wo ks,‖
A abian Jou nal o Science and Enginee ing, ol. 46, no. 4, pp. 3409–3422,
2021.
A. Haup mann, S. A idge, F. Lucka, V. Mu hu angu, and J. A. S eeden, ―Real- ime
ca dio ascula MR wi h spa io- empo al a i ac supp ession using deep lea ning
– p oo o concep in congeni al hea disease,‖ Magne ic Resonance in
Medicine, ol. 81, no. 2,
pp. 1143–1156, 2019.
