DOI: 10.5121/ijcsi .2025.17504 57
HARNESSING ARTIFICIAL INTELLIGENCE FOR
PUBLIC HEALTH AND EPIDEMIOLOGY:
OPPORTUNITIES, BARRIERS, AND PATHWAYS TO
EQUITABLE GLOBAL IMPACT
Shana az Mohammed 1, Nasa Mohammed 2, S u hi Balammaga y 3, Si eesha
Kolla 4, S ujan Kuma Gan a 5, Shuaib Abdul Khade 6
1.3 School o Compu e and In o ma ion Sciences, Uni e si y o he Cumbe lands, KY,
USA
2 Depa men o Heal hCa e Adminis a ion. Valpa aiso Uni e si y, IN, USA
4 Depa men o In o ma ion Technology, Na ional Ins i u es o Heal h, USA
5 Depa men o In o ma ion Technology, JNTU, Telangana, India
6 Depa men o In o ma ion Technology, Conco dia Uni e si y, WI, USA
ABSTRACT
A i icial In elligence (AI) is ans o ming public heal h and epidemiology by enabling ea lie de ec ion,
imp o ed su eillance, p edic i e o ecas ing, and mo e e icien esponses o heal h h ea s. Le e aging
echniques such as machine lea ning, deep lea ning, na u al language p ocessing, and compu e ision, AI
can p ocess as and di e se da a sou ces, including elec onic heal h eco ds, mobile heal h apps,
genomic sequencing, and social media. These ools enhance ou b eak p edic ion accu acy, op imize
accine dis ibu ion, accele a e con ac acing, and map disease ansmission, as demons a ed du ing he
COVID-19 pandemic. Beyond in ec ious disease, AI also suppo s moni o ing o non-communicable
diseases and men al heal h h ough passi e da a collec ion and beha io al end analysis. Despi e i s
p omise, ba ie s hinde widesp ead, equi able adop ion. Key conce ns include da a p i acy, algo i hmic
bias, lack o anspa ency, and he digi al di ide, which isk wo sening heal h dispa i ies i no add essed.
E ec i e in eg a ion o AI in o public heal h equi es obus go e nance amewo ks, c oss-sec o
collabo a ion, and wo k o ce capaci y-building. Looking o wa d, ede a ed lea ning, explainable AI, and
s ong egula o y mechanisms will be essen ial o ensu e e hical, accoun able, and globally inclusi e use.
By c i ically assessing cu en applica ions and cha ing u u e p io i ies, his s udy unde sco es how AI
can s eng hen heal h sys ems o be mo e esponsi e, e idence-d i en, and equi able wo ldwide.
KEYWORDS
A i icial In elligence, Public Heal h, Epidemiology, Disease Su eillance, Machine Lea ning, Ou b eak
P edic ion, Heal h In o ma ics, P edic i e Analy ics, Da a P i acy, Heal h Equi y, Digi al Heal h,
Explainable AI, COVID-19, Non-Communicable Diseases, Popula ion Heal h.
1. INTRODUCTION
The p ima y goals o epidemiology and public heal h a e o p o ec and imp o e popula ion
heal h h ough su eillance, illness p e en ion, policy o mula ion, and heal h p omo ion [1].
His o ically, public heal h app oaches elied ex ensi ely on s a is ical modeling, manual da a
collec ion, and ield epidemiological s udies o assess illness ends, iden i y isk ac o s, and
alloca e heal h esou ces. Howe e , due o he massi e olume o heal h- ela ed da a om
wea able senso s, genomic sequencing, social media, elec onic heal h eco ds (EHRs), and
In e na ional Jou nal o Compu e Science & In o ma ion Technology (IJCSIT) Vol 17, No 5, Oc obe 2025
58
en i onmen al senso s, adi ional me hodologies a e no longe capable o e icien ly analyzing
and comp ehending such as amoun s o dynamic, complex da a [2].
In his si ua ion, a i icial in elligence (AI), wi h i s excep ional pa e n ecogni ion, p edic i e
analy ics, and decision suppo capabili ies, is seen as a game-changing echnology [3]. Using
machine lea ning, deep lea ning, and na u al language p ocessing, AI sys ems can ins an ly si
h ough millions o s uc u ed and uns uc u ed heal h da a poin s o deli e mo e p ecise and
imely da a-d i en insigh s in o public heal h ends, disease ansmission, and new heal h isks
[4]. Enhancing epidemiological models, iden i ying high- isk g oups, and ad ancing e idence-
based policies all depend on his accomplishmen .
AI sys ems we e u ilized o manage accine supply chains, ack con ac s, p edic ou b eaks, and
e en comba misin o ma ion du ing he COVID-19 pandemic, making i one o he mos
success ul uses o AI in his o y [5]. These applica ions a e being esea ched o ch onic illness
p e en ion, men al heal h moni o ing, and o he in ec ious diseases such as in luenza, dengue
e e , and mala ia. In hese applica ions, AI coo dina es esou ce deploymen o a ge ed public
heal h and ea ly in e en ion ini ia i es whe e hey a e mos e ec i e.
The use o AI in public heal h aises conce ns abou da a quali y, algo i hmic bias,
in e ope abili y, p i acy, and a lack o egula o y s anda ds [6]. AI sys ems ha le e age biased
da a sou ces may con inue o p omo e heal h inequi ies, and he lack o openness o some
algo i hms may e ode public us and make people esis an o mo al esponsibili y. The e o e, i
is c i ical o ensu e ha AI sys ems a e open, equi able, and secu e, and ha hey a e also
sensi i e o human igh s and accoun able o public heal h objec i es [7].
This s udy pape also c i ically examines p esen uses, examples, p oblems, e hics, and u u e
po en ial in an e o o explo e he complex ole o AI in epidemiology and public heal h [8].
By c i ically examining bo h he social and echnological aspec s o AI in eg a ion, he p ojec
will gain quali a i e insigh s on how o de elop heal hie , mo e e ec i e, and mo e equi able
heal h sys ems ha can add ess p esen and u u e public heal h issues [9].
2. LITERATURE REVIEW
Ad ancemen s in compu ing powe , big da a analy ics, and machine lea ning (ML) algo i hms
ha e esul ed in a majo inc ease in he con e gence o public heal h and AI [10]. While
s a is ical eg ession models and geog aphical analysis a e use ul, hey a e o en unable o handle
high-dimensional da a, missing alues, eal- ime in e ence, and nonlinea ela ionships, among
o he epidemiologic di icul ies. A a ie y o AI modali ies ex end hose s a egies by u ilizing
decision-suppo sys ems, eal- ime moni o ing, and p edic i e modeling [11].
P e ious esea ch highligh s how machine lea ning is ans o ming disease su eillance,
speci ically in e ms o in ec ious disease epidemic p edic ion and moni o ing. Using deep
lea ning models o o ecas COVID-19 case spikes based on mo emen , a el, and longi udinal
heal h da a is one example [12]. Sys ems such as BlueDo and Heal hMap can now de ec ea ly
epidemics by using synd omic da a ex ac ed om social media, news media, and clinical
epo ing hanks o na u al language p ocessing (NLP) echniques [13].The mos p o ound end
is he use o AI o manage non-communicable diseases (NCDs) [14]. AI suppo ed isk
s a i ica ion and he diabe es, ca dio ascula , and men al heal h ea ly de ec ion models. AI
deployed in mobile heal h (mHeal h) echnologies imp o es emo e heal h moni o ing, especially
in u al se ings [15]. AI suppo s he analysis o he social de e minan s o heal h, which a e
deeply ing ained in complex and uns uc u ed da a.
In e na ional Jou nal o Compu e Science & In o ma ion Technology (IJCSIT) Vol 17, No 5, Oc obe 2025
59
Howe e , he e a e se e al se ious issues aised in he li e a u e. Algo i hmic bias, da a quali y,
anspa ency laws, and e hics a e among he equen ly discussed subjec s. Acco ding o
s udies, desc ibing a i icial in elligence (XAI) is c i ical o winning public and heal hca e
p o essional us [16]. The e ha e also been claims o a lack o a ailable local da a and
in as uc u e cons ain s impeding AI esea ch and applica ion in low- and middle-income
coun ies (LMICs) [17].
The ollowing able is a synop ic ep esen a ion o signi ican s udies ha ha e g ea ly
con ibu ed o he e olu ion o AI in public heal h and epidemiology:
Table 1: Summa y o Key Li e a u e on AI in Public Heal h and Epidemiology
No el AI F amewo k: PH-AIEX (Public Heal h AI wi h Explainabili y and Fede a ed Lea ning)
Desc ip ion:
A modula AI amewo k designed o public heal h and epidemiology, PH-AIEX places a high
alue on equali y, scalabili y, and anspa ency. Explainable AI (XAI) laye s o in e p e abili y,
ede a ed lea ning o p i acy-p ese ing modeling, and hyb id deep lea ning a chi ec u es
(inco po a ing LSTM o empo al da a, GNN o ela ional da a, and a en ion-based modules o
mul i-sou ce in eg a ion) a e all combined in his app oach.
Key ea u es:
• Fede a ed Lea ning Backbone: Facili a es coope a i e modeling among hospi als and
ins i u ions wi hou equi ing aw da a sha ing.
• The Explainable AI (XAI) Laye a ibu es p edic ions using SHAP o LIME o imp o e
clinical in e p e abili y.
• LSTM o ime se ies (ou b eak p edic ion), GNN o ela ional con ac acing, and
a en ion o in eg a ing many da a sou ces (such as social media, mobili y, and EHRs)
a e all combined in a hyb id a chi ec u e.
3. METHODOLOGY
He e, me hodology applied o assess he in eg a ion o AI in epidemiology and public heal h is
explained [18]. I co e s da a sou ces, AI me hods, model aining and alida ion, and
pe o mance me ics. The me hodology was designed o in es iga e some o he nume ous uses
In e na ional Jou nal o Compu e Science & In o ma ion Technology (IJCSIT) Vol 17, No 5, Oc obe 2025
60
o AI, anging om p edic ing ou b eaks o esou ce alloca ion, u ilizing ac ual measu emen s in
da a se s and modelling in as uc u e [19].
Sys ema ic Re iew Me hodology
Da abases sea ched:
• PubMed/MEDLINE.
• The Scopus
• The Web o Science
• IEEE Xplo e
• EMBASE
• Coch ane Lib a y
Sea ch S a egy:
• Keywo ds: "Public Heal h," "Epidemiology," o "Disease Su eillance" in conjunc ion
wi h "A i icial In elligence," "Machine Lea ning," o "Deep Lea ning."
• Range o da es: 2018-2025
• Documen ypes include echnical and medical con e ence pape s, sys ema ic e iews,
and pee - e iewed a icles.
Inclusion C i e ia:
• Resea ch using o e alua ing AI in epidemiological o public heal h si ua ions.
• Obse a ional, modeling, o expe imen al s udy using eal heal hca e da a.
• Resea ch p esen ing pe o mance me ics o ou comes ele an o esou ce alloca ion,
ou b eak o ecas ing, o su eillance
• English language
Exclusion Cei e ia:
• Resea ch wi hou empi ical e alua ion
• Re iews ha a e no conce ned wi h epidemiology o public heal h
• Pee - e iewed p ep in s and abs ac s wi hou ull da a
• AI esea ch limi ed o he apeu ic (non-popula ion) applica ions
3.1. Da a Sou ces
The eliabili y o AI models in public heal h elies s ongly on he quali y and a ie y o inpu
da a. The sou ces conside ed o his s udy include:
• Elec onic Heal h Reco ds (EHRs): Pa ien demog aphic in o ma ion, es esul s,
medica ion his o y [20].
• Mobile and Wea able De ices: Real- ime physiological da a (hea a e, s eps, sleep).
• Social media & Web Da a: Twi e ending, Google T ends, web o ums synd omic
su eillance [21].
• Geog aphic and En i onmen al Da a: Sa elli e images and clima ic a iables o ec o -
bo ne disease modelling.
In e na ional Jou nal o Compu e Science & In o ma ion Technology (IJCSIT) Vol 17, No 5, Oc obe 2025
61
• Public Da ase s: WHO, CDC, Johns Hopkins COVID-19 da ase , heal h minis y
websi es [22].
The da ase s we e anonymized and agg ega ed in o de o mee da a p o ec ion legisla ion such as
GDPR and HIPAA.
Da abases:
• COVID-19 case p edic ions using da a om WHO and Johns Hopkins
• P edic ing ch onic diseases using EHR da a (MIMIC-III, eICU, o simila accessible
da ase s)
• Da a om su eillance o public heal h (CDC in luenza da ase s)
3.2. AI Techniques Employed
Va ious AI models we e employed based on he na u e o he p oblem:
• Supe ised Lea ning: Logis ic Reg ession, Random Fo es , G adien Boos ing o disease
diagnosis and isk o ecas ing [23].
• Unsupe ised Lea ning: K-Means clus e ing o popula ion heal h segmen a ion.
• Deep Lea ning: Long Sho -Te m Memo y (LSTM) ne wo ks o ou b eak o ecas ing in
ime se ies [24].
• Na u al Language P ocessing (NLP): Applied o news, epo , and social media ex
analysis.
• Rein o cemen Lea ning: Applied in accine deli e y logis ics and esou ce op imiza ion
unde changing cons ain s.
3.3. Model T aining and Valida ion
Models we e ained o e his o ical heal h da a (80%) and es ed o e he emaining 20%. 5- old
c oss- alida ion was done o ge s able models [25]. Ea ly s opping and d opou laye s we e
u ilized o e deep lea ning models o p e en o e i ing.
3.4. Model Pe o mance Me ics
Model pe o mance was e alua ed using he ollowing me ics:
• Accu acy: P opo ion o co ec p edic ions ou o all p edic ions made.
Accu acy =
Whe e TPTP: ue posi i es, TNTN: ue nega i es, FPFP: alse posi i es, FNFN: alse nega i es
• P ecision (Posi i e P edic i e Value): P opo ion o posi i e iden i ica ions ha a e
co ec .
P ecision =
• Recall (Sensi i i y): P opo ion o ac ual posi i es de ec ed co ec ly.
Recall =
In e na ional Jou nal o Compu e Science & In o ma ion Technology (IJCSIT) Vol 17, No 5, Oc obe 2025
62
• F1 Sco e: Ha monic mean o p ecision and ecall.
F1 Sco e = 2X
3.5. Visualiza ion and In e p e a ion
While ying o g aphically depic ela i e pe o mance and usage o AI me hods by a ious
applica ions, a ba diag am is displayed.
Ba Diag am Desc ip ion
Table 2: AI Techniques Used in Public Heal h Applica ions
This ba cha illus a es well supe ised lea ning echniques head public heal h applica ions due
o hei explainabili y and simplici y, ollowed by deep lea ning and NLP, speci ically in ou b eak
o ecas ing and analysis o public opinion
Figu e 1: AI Techniques Used in Public Heal h Applica ions
In e na ional Jou nal o Compu e Science & In o ma ion Technology (IJCSIT) Vol 17, No 5, Oc obe 2025
63
4. KEY FINDINGS
AI applica ion in epidemiology and public heal h has been accompanied by some headline-
g abbing indings [26]. The ollowing key indings summa ize i s impac on co e unc ional
a eas:
4.1. Disease Su eillance and Ea ly De ec ion
A i icial in elligence sys ems ha e shown phenomenal pe o mance in eal- ime moni o ing o
diseases [27]. Blue Do and Heal hMap apply machine lea ning and na u al language p ocessing
o ead news a icles, social media, and wo ldwide heal h da abases o iden i y possible ou b eaks
soone han con en ional sys ems [28]. Blue Do iden i ied he ini ial ou b eak days p io o
WHO's o icial announcemen du ing he COVID-19 pandemic [29]. AI's capabili y o p ocess
uns uc u ed da a in geog aphies and languages gi es a p ophylac ic laye o global heal h
secu i y.
4.2. Ou b eak P edic ion and Modelling
LSTM and andom o es eg esso s a e machine lea ning algo i hms ha ha e been applied o
o ecas ing and p edic ing disease ansmission pa e ns [30]. They ha e been applied in using
his o ical case eco ds, mobili y, clima ic ac o s, and heal hca e capaci ies o p edic u u e
coun s o cases and hospi aliza ion. Fo example, SEIR models using AI we e u ilized o
modelling he ansmission o COVID-19 in such a manne ha policymake s could plan
lockdowns and es ic esou ces in ad ance. P edic i e powe ose signi ican ly wi h he use o
he e ogeneous da a inpu s [31].
4.3. Popula ion Heal h Su eillance
A i icial in elligence has signi ican ly con ibu ed o he esea ch on social de e minan s o
heal h and popula ion heal h isk de e mina ion [32]. Unsupe ised machine lea ning algo i hms
g oup indi iduals acco ding o li es yle in o ma ion, beha iou ai s, and en i onmen al
exposu e. The g oupings allow public heal h p o essionals o de elop cus omized in e en ions in
high- isk popula ions [33]. Mo eo e , wea able senso s linked o AI algo i hms allow emo e and
con inuous moni o ing o physiological indica o s and enable ea ly wa ning sys ems o disease
exace ba ions.
4.4. Resou ce Alloca ion and Decision Suppo
AI excels in op imizing he use o heal h esou ces, especially du ing an eme gency.
Rein o cemen lea ning models ha e been applied in he modelling o accine dis ibu ion unde
esou ce-cons ained condi ions o op imize o impac and ai ness [34]. AI assis s eme gency
depa men iaging sys ems h ough he p edic ion o pa ien de e io a ion om EHR and i al
signs o allow p ope p io i iza ion [35]. The models ha e been mos use ul in esou ce-
cons ained en i onmen s and in pandemic p epa edness.
In e na ional Jou nal o Compu e Science & In o ma ion Technology (IJCSIT) Vol 17, No 5, Oc obe 2025
64
Figu e 2: AI A eas o Func ion in Public Heal h
This diag am illus a es he in e connec ion be ween AI-d i en unc ions in public heal h, om
ea ly wa ning sys ems o popula ion heal h isk s a i ica ion and logis ical planning.
5. APPLICATIONS AND CASE STUDIES
A i icial in elligence is ans o ming public heal h bo h heo e ically easible, bu in ac mo e
impo an ly h ough eal-wo ld applied applica ions [36]. This sec ion ocuses on he p ac ical
applica ions and esul s o speci ic applica ions in men al heal h, ch onic disease p e en ion, and
in ec ious disease managemen .
5.1. COVID-19 Pandemic Response
A u ning poin in he use o AI in public heal h was he COVID-19 pandemic. In ec ion,
hospi aliza ion, and in ensi e ca e uni a es a e p edic ed by machine lea ning echniques, which
ha e made ex ensi e use o AI models [37].
• AI-powe ed applica ions, like Aa ogya Se u in India, e alua e exposu e isk ia Blue oo h
and GPS.
• NLP cha bo s aided in symp om iage and sel - epo ing by use s.
• AI-suppo ed esou ce alloca ion o he logis ics o he supply chain o accina ions and
en ila o ins alla ion, using IBM Wa son-like echnology helping heal h depa men s
simula e supply chain beha io [38].
This quick eac ion showed how AI can speed up da a in e p e a ion and help guide eme gency
decision-making.
5.2. Mala ia and Vec o -Bo ne Diseases
AI is inc easingly being used o an icipa e and manage he sp ead o diseases such as dengue,
Zika, and mala ia using [39].
• Remo e Sensing In eg a ion: Machine lea ning algo i hms use en i onmen al da a
( empe a u e and p ecipi a ion) and sa elli e image y o iden i y mosqui o b eeding places
ha o e a signi ican isk.
• P edic i e Ou b eak Modeling: The use o a i icial in elligence (AI) o o ecas empo al-
spa ial disease pa e ns enabled p oac i e p e en a i e in e en ions such as awa eness
campaigns and la icide sp aying [40].
In e na ional Jou nal o Compu e Science & In o ma ion Technology (IJCSIT) Vol 17, No 5, Oc obe 2025
65
Case s udies om B azil and Kenya show ha he use o AI imp o es ho spo iden i ica ion
accu acy and eac ion ime [41].
5.3. Ch onic Disease Managemen
The use o AI in he ea men o noncommunicable diseases (NCDs) is g owing in impo ance.
• Hype ension and Diabe es Risk P edic ion: AI echnologies, using EHRs and biome ic
alues, classi y people in o isk g oups, so in e en ions can be di ec ed app op ia ely
[42].
• Wea able Technology In eg a ion: Fi bi and Apple Wa ch use a i icial in elligence o
de ec anomalies in hea a e, exe cise, and sleep habi s, aiding in he diagnosis o
diso de s such as a hy hmias and hype ension [43].
When clinical s a a ailabili y necessi a es emo e moni o ing, hese me hods a e especially
use ul in low- esou ce se ings.
5.4. Men al Heal h Moni o ing
AI is also showing po en ial in men al heal h diagnosis and ea men :
• SENTIMENT ANALYSIS: Tex con en o social media is analysed by NLP models o
iden i y dep ession o signs o anxie y in g oups [44].
• FACIAL AND VOICE RECOGNITION: AI so wa e in e p e s one and acial
exp ession o ack emo ional s a e, in o ming psychological he apy.
Pilo in es iga ions a uni e si ies in he Uni ed Kingdom and he Uni ed S a es ha e shown ha
AI echnologies imp o e adi ional counselling and boos sc eening accu acy [45].
Line Diag am Desc ip ion
Table 3: T ends in AI Applica ion o Public Heal h (2018–2025)
In e na ional Jou nal o Compu e Science & In o ma ion Technology (IJCSIT) Vol 17, No 5, Oc obe 2025
72
[17] Chen, Z., Azman, A. S., Chen, X., Zou, J., Tian, Y., Sun, R., ... & Yu, H. (2022). Global landscape o
SARS-CoV-2 genomic su eillance and da a sha ing. Na u e gene ics, 54(4), 499-507.
[18] Nguyen-Da, T., Li, Y. M., Peng, C. L., Cho, M. Y., & Nguyen-Thanh, P. (2023). Tou ism demand
p edic ion a e COVID-19 wi h deep lea ning hyb id CNN–LSTM—Case s udy o Vie nam and
p o inces. Sus ainabili y, 15(9), 7179.
[19] Chen, T., D edze, M., Weine , J. P., He nandez, L., Kimu a, J., & Kha azi, H. (2019). Ex ac ion o
ge ia ic synd omes om elec onic heal h eco d clinical no es: assessmen o s a is ical na u al
language p ocessing me hods. JMIR medical in o ma ics, 7(1), e13039.
[20] Sheu, R. K., & Pa deshi, M. S. (2022). A su ey on medical explainable AI (XAI): ecen p og ess,
explainabili y app oach, human in e ac ion and sco ing sys em. Senso s, 22(20), 8068.
[21] Rajkoma , A., O en, E., Chen, K., Dai, A. M., Hajaj, N., Ha d , M., ... & Dean, J. (2018). Scalable
and accu a e deep lea ning wi h elec onic heal h eco ds. NPJ digi al medicine, 1(1), 18.
[22] Bach ige , P., Pe i, C. F., Sco , F. E., Pa k, S. R., Kelshike , M. A., Sahemey, H. K., ... & Pe e s, N.
S. (2022). Poin -o -ca e sc eening o hea ailu e wi h educed ejec ion ac ion using a i icial
in elligence du ing ECG-enabled s e hoscope examina ion in London, UK: a p ospec i e,
obse a ional, mul icen e s udy. The Lance Digi al Heal h, 4(2), e117-e125.
[23] Obonyo, C. O., We e, V. O., Wamae, P., & Muok, E. M. (2023). SCHISTOACT: a p o ocol o an
open-label, i e-a m, non-in e io i y, indi idually andomized con olled ial o he e icacy and
sa e y o p aziquan el plus a emisinin-based combina ions in he ea men o Schis osoma mansoni
in ec ion. T ials, 24(1), 763.
[24] Si, Y., Du, J., Li, Z., Jiang, X., Mille , T., Wang, F., ... & Robe s, K. (2021). Deep ep esen a ion
lea ning o pa ien da a om Elec onic Heal h Reco ds (EHR): A sys ema ic e iew. Jou nal o
biomedical in o ma ics, 115, 103671.
[25] Zuo, X., Chen, Y., Ohno-Machado, L., & Xu, H. (2021). How do we sha e da a in COVID-19
esea ch? A sys ema ic e iew o COVID-19 da ase s in PubMed Cen al A icles. B ie ings in
Bioin o ma ics, 22(2), 800-811.
[26] Sun, D., Xu, J., Wen, H., & Wang, D. (2021). Assessmen o landslide suscep ibili y mapping based
on Bayesian hype pa ame e op imiza ion: A compa ison be ween logis ic eg ession and andom
o es . Enginee ing Geology, 281, 105972.
[27] Mohammed, A. R., Ram, S. S., Ahmed, M. I., & Kam an, S. A. (2024). Remo e Moni o ing o
Cons uc ion Si es Using AI and D ones..
[28] Mohammed, N. U., Mohammed, Z. A., Gunda, S. K. R., Mohammed, A., & Khaja, M. U.
Ne wo king wi h AI: Op imizing Ne wo k Planning, Managemen , and Secu i y h ough he
medium o A i icial In elligence.
[29] Le è e, T., & Delpie e, C. (2021). A i icial in elligence in epidemiology. In A i icial In elligence
in Medicine (pp. 1-12). Cham: Sp inge In e na ional Publishing.
[30] Mansou , R. F., El Am aoui, A., Nouaou i, I., Díaz, V. G., Gup a, D., & Kuma , S. (2021). Demola
A i icial in elligence and in e ne o hings enabled disease diagnosis model o sma heal hca e
sys ems. IEEE Access, 9, 45137-45146.
[31] Adeoye, A., Onah, C. O., O oba o , E. T., Akin ayo, E. A., Inuaeyen, J. U., Umo u, D. O., ... &, M.
B. (2025). AI and Machine Lea ning o Ea ly De ec ion o In ec ious Diseases in he US:
Oppo uni ies and Challenges. Jou nal o Medical Science, Biology, and Chemis y, 2(1), 54-63.
[32] Kuma , R., S i as a a, V., & Nand, K. N. (2023). The wo sides o he co id-19
pandemic. COVID, 3(12), 1746-1760.
[33] Leung, X. Y., Islam, R. M., Adhami, M., Ilic, D., McDonald, L., Palawa h ha, S., ... & Ka im, M. N.
(2023). A sys ema ic e iew o dengue ou b eak p edic ion models: Cu en scena io and u u e
di ec ions. PLoS neglec ed opical diseases, 17(2), e0010631.
[34] Cano, A., & K awczyk, B. (2022). ROSE: obus online sel -adjus ing ensemble o con inual
lea ning on imbalanced d i ing da a s eams. Machine Lea ning, 111(7), 2561-2599.
[35] Benda, N. C., Zaw ha, S., Ande son, K., Sha ma, M. M., Lin, P. B., Zaw ha, B., & Mas e son
C ebe , R. (2022). De eloping popula ion heal h su eillance using mHeal h in low- esou ce
se ings: quali a i e assessmen and pilo e alua ion. JMIR Fo ma i e Resea ch, 6(10), e36260.
[36] O du, M., Demi , E., To allis, C., & Gunal, M. M. (2021). A no el heal hca e esou ce alloca ion
decision suppo ool: A o ecas ing-simula ion-op imiza ion app oach. Jou nal o he ope a ional
esea ch socie y, 72(3), 485-500.
In e na ional Jou nal o Compu e Science & In o ma ion Technology (IJCSIT) Vol 17, No 5, Oc obe 2025
73
[37] Ruiz, V. M., Goldsmi h, M. P., Shi, L., Simpao, A. F., Gál ez, J. A., Naim, M. Y., ... & Tsui, F. R.
(2022). Ea ly p edic ion o clinical de e io a ion using da a-d i en machine-lea ning modeling o
elec onic heal h eco ds. The Jou nal o ho acic and ca dio ascula su ge y, 164(1), 211-222.
[38] Liu, F., & Panagio akos, D. (2022). Real-wo ld da a: a b ie e iew o he me hods, applica ions,
challenges and oppo uni ies. BMC Medical Resea ch Me hodology, 22(1), 287.
[39] San angelo, O. E., Gen ile, V., Pizzo, S., Gio dano, D., & Ced one, F. (2023). Machine lea ning and
p edic ion o in ec ious diseases: a sys ema ic e iew. Machine Lea ning and Knowledge
Ex ac ion, 5(1), 175-198.
[40] Kuma , A., Tejaswini, P., Nayak, O., Kuju , A. D., Gup a, R., Rajanand, A., & Sahu, M. (2022,
May). A su ey on IBM wa son and i s se ices. In Jou nal o Physics: Con e ence Se ies (Vol.
2273, No. 1, p. 012022). IOP Publishing.
[41] Hussain-Alkha eeb, L., Ri e a Rami ez, T., K oege , A., Gozze , E., & Runge-Ranzinge , S. (2021).
Ea ly wa ning sys ems (EWSs) o chikungunya, dengue, mala ia, yellow e e , and Zika ou b eaks:
Wha is he e idence? A scoping e iew. PLoS neglec ed opical diseases, 15(9), e0009686
[42] Yeboah, V., Asibey, M. O., & Abdulai, A. S. J. (2021). Slum upg ading app oaches om a social
di e si y pe spec i e in he global sou h: Lessons om he B azil, Kenya and Thailand
cases. Ci ies, 113, 103164.
[43] Zhao, Y., Han, J., Hu, X., Hu, B., Zhu, H., Wang, Y., & Zhu, X. (2024). Hype ension isk p edic ion
models o pa ien s wi h diabe es based on machine lea ning app oaches. Mul imedia Tools and
Applica ions, 83(20), 59085-59102
[44] To on, N., Lin, J., Julious, S., Chowdhu y, M., & B and, A. (2023). A e iew o sample sizes o
UK pilo and easibili y s udies on he ISRCTN egis y om 2013 o 2020. Pilo and easibili y
s udies, 9(1), 188.
[45] Jungwi h, D., & Haluza, D. (2023). A i icial in elligence and public heal h: an explo a o y
s udy. In e na ional Jou nal o En i onmen al Resea ch and Public Heal h, 20(5), 4541.
[46] We e, M. C., Sa ai, S., Mokaya, B., Mbugua, S., Ribeka, N., Cholli, P., & Yeung, A. (2021).
mUzima mobile elec onic heal h eco d (EHR) sys em: de elopmen and implemen a ion a
scale. Jou nal o medical In e ne esea ch, 23(12), e26381.
[47] Haw, J. S., Shah, M., Tu bow, S., Egeolu, M., & Umpie ez, G. (2021). Diabe es complica ions in
acial and e hnic mino i y popula ions in he USA. Cu en diabe es epo s, 21(1), 2.
[48] Daneshjou, R., Smi h, M. P., Sun, M. D., Ro embe g, V., & Zou, J. (2021). Lack o anspa ency and
po en ial bias in a i icial in elligence da a se s and algo i hms: a scoping e iew. JAMA
de ma ology, 157(11), 1362-1369.
[49] Buh mes e , V., Münch, D., & A ens, M. (2021). Analysis o explaine s o black box deep neu al
ne wo ks o compu e ision: A su ey. Machine Lea ning and Knowledge Ex ac ion, 3(4), 966-
989.
[50] Paccoud, I., Baumann, M., Le Bihan, E., Pé é, B., B einbaue , M., Böhme, P., ... & Leis , A. K.
(2021). Socioeconomic and beha iou al ac o s associa ed wi h access o and use o pe sonal heal h
eco ds. BMC medical in o ma ics and decision making, 21(1), 18.
[51] Radanlie , P., San os, O., B andon-Jones, A., & Joinson, A. (2024). E hics and esponsible AI
deploymen . F on ie s in A i icial In elligence, 7, 1377011.
[52] Ali, S. W., Sadiq, M., Te iche, Y., Naq i, S. A. R., Hoang, L. Q. N., Mu a a , M. U., ... &
Gue e o, J. M. (2021). O sho e wind a m-g id in eg a ion: A e iew on in as uc u e, challenges,
and g id solu ions. Ieee Access, 9, 102811-102827.
[53] Oluwa emi, I. O., Clemen , T., Adanigbo, O. S., Gbenle, T. P., & Adekunle, B. I. (2021). A Re iew
o E hical Conside a ions in AI-D i en Ma ke ing Analy ics: P i acy, T anspa ency, and Consume
T us . In e na ional Jou nal O Mul idisciplina y Resea ch and G ow h E alua ion, 2(2), 428-435.
[54] Camille i, M. A. (2024). A i icial in elligence go e nance: E hical conside a ions and implica ions
o social esponsibili y. Expe sys ems, 41(7), e13406.
[55] Baka e¹, S. S., Adeniyi, A. O., Akpuokwe, C. U., & Eneh⁴, N. E. (2024). Da a p i acy laws and
compliance: a compa a i e e iew o he EU GDPR and USA egula ions.
[56] Xu, J., Xiao, Y., Wang, W. H., Ning, Y., Shenkman, E. A., Bian, J., & Wang, F. (2022). Algo i hmic
ai ness in compu a ional medicine. EBioMedicine, 84.
[57] Wang, Y. (2024). A compa a i e analysis o model agnos ic echniques o explainable a i icial
in elligence. Resea ch Repo s on Compu e Science, 25-33.
[58] Zhang, K., & Aslan, A. B. (2021). AI echnologies o educa ion: Recen esea ch & u u e
di ec ions. Compu e s and educa ion: A i icial in elligence, 2, 100025.
In e na ional Jou nal o Compu e Science & In o ma ion Technology (IJCSIT) Vol 17, No 5, Oc obe 2025
74
[59] Yang, Q. (2021). Towa d esponsible ai: An o e iew o ede a ed lea ning o use -cen e ed
p i acy-p ese ing compu ing. ACM T ansac ions on In e ac i e In elligen Sys ems (TiiS), 11(3-4),
1-22.
[60] No illa, M. L. B., Goa es, M. C., Le le , T., No illa, N. K. B., Wu, C. Y., Dall, A., & Hansen, C.
(2023). In eg a ing social ca e in o heal hca e: a e iew on applying he social de e minan s o
heal h in clinical se ings. In e na ional jou nal o en i onmen al esea ch and public heal h, 20(19),
6873.
[61] Balasub amaniam, N., Kauppinen, M., Rannis o, A., Hiekkanen, K., & Kujala, S. (2023).
T anspa ency and explainabili y o AI sys ems: F om e hical guidelines o
equi emen s. In o ma ion and So wa e Technology, 159, 107197.
[62] Lee, L. K., Ruano, E., Fe nández, P., O ega, S., Lucas, C., & Joachim-Céles in, M. (2021).
Wo k o ce eadiness aining: a comp ehensi e aining model ha equips communi y heal h
wo ke s o wo k a he op o hei p ac ice and p o ession. F on ie s in public heal h, 9, 673208.
