Co esponding au ho : Spy idon Achinas
Copy igh © 2025 Au ho (s) e ain he copy igh o his a icle. This a icle is published unde he e ms o he C ea i e Commons A ibu ion Liscense 4.0.
Ha nessing Bayesian ne wo ks in cance managemen : A pe spec i e
Nikolaos Cha alampogiannis 1, Ma ena Vi ola Quin e o 2, E hymios Poulios 3 and Spy idon Achinas 4, *
1 Depa men o U ology, SLK Kliniken am Gesundb unnen, Heilb onn, Ge many.
2 Facul y o Enginee ing, Ra ael Núñez Uni e si y Co po a ion, Ca agena, Colombia.
3 14 h Depa men o Su ge y, A ikon Uni e si y Hospi al, Medical School, Na ional and Kapodis ian Uni e si y o A hens,
A hens, G eece.
4 D en he, The Ne he lands.
Wo ld Jou nal o Ad anced Resea ch and Re iews, 2025, 26(02), 109-114
Publica ion his o y: Recei ed on 23 Ma ch 2025; e ised on 28 Ap il 2025; accep ed on 01 May 2025
A icle DOI: h ps://doi.o g/10.30574/wja .2025.26.2.1580
Abs ac
Machine lea ning is b eaking in o medicine and heal hca e suppo ing he p ognosis, diagnosis and ea men selec ion
o a wide a ie y o malignancies. Bayesian Ne wo ks, a sub elemen o Machine Lea ning, has po ency o suppo
clinicians and oncologis s in cance managemen . In his a icle, we discussed aspec s and po en ial o Bayesian
Ne wo ks in cance he apeu ics and his pe spec i e is in o ma i e o medical doc o s as well as bio-in o ma icians,
AI enginee s, and da a analys s.
Keywo ds: Bayesian Ne wo ks; Cance he apeu ics; P ognosis; Diagnosis
1. In oduc ion
Al hough cance in one o he mos a al diseases o mankind, he e ha e been signi ican changes in he las decade
including he cance diagnosis, p ognosis and he apy op imiza ion. The e has been a conside able in es iga ion on
cance diagnosis by de eloping compu a ional models o e icien de ec ion o cance ous condi ions [1,2]. Many
bioin o ma icians ha e adop ed A i icial In elligence (AI)-based lea ning app oaches in cance he apeu ics [3].
Bayesian Ne wo ks (BNs) can be applied in h ee di e en ca ego ies o image-based asks in oncology: de ec ion,
cha ac e iza ion and moni o ing o umo s [4].
Some challenges do emain as medical da a canno be used as di ec inpu [5]. I is c ucial o ex ac , quan i y and
e alua e ea u es. Ano he challenge could lie in he ac ha AI will expe ience low exposu e and expe clinicians
which leads o blind spo s o a e condi ions as well as a epe oi e o doc o s expe iences in disease in e p e a ions
[6].
AI-based ools can play a ole in moni o ing he umo . The adi ional way o con on ing he umo consis s o he
esponse e alua ion c i e ia in solid umo s (RESICT) and he wo ld heal h o ganiza ion (WHO) c i e ia o es ima ing
umo bu den and de e mining ea men esponse [7-9]. These me hods a e hea ily c i icized o o e simpli ying
complex umo geome y and being unable o de e mine he e iciency o chemo he apy in he case o nume ous lesions.
[7-9].
A ca dinal numbe o s udies o he nexus BNs and cance managemen delinea e he s a us quo [10-15]; i has been
alluded ha AI can ex ac and quan i y key image in o ma ion by simula ing complex human unc ions. I is
ecommended he elabo a ion o an ex ensi e s udy o e alua e he ex en o he cu en applica ions and seg ega e he
esea ch in o ma ion ha e eals pinnacles and adeo s o AI implemen a ion in cance managemen . This pe spec i e
Wo ld Jou nal o Ad anced Resea ch and Re iews, 2025, 26(02), 109-114
110
discusses aspec s and po en ial o BNs in cance he apeu ics and is in o ma i e o medical doc o s as well as bio-
in o ma icians, AI enginee s, and da a analys s.
2. Realising he alue o Bayesian Ne wo ks
Bayesian Ne wo ks (BNs) use complex modelling app oaches o manage la ge da ase s o aid physicians in cance
managemen [16]. BNs is conside ed a powe ul ool o medical doc o s and speci ically oncologis s in clinical diagnosis
and decision-making [16,17].
In cance esea ch AI-based ools a e commonly used in imaging echniques including: compu ed omog aphy (CT)
scam, magne ic esonance imaging, mammog aphy and ul asound [18,19]. These echniques gene a e as amoun o
da a and AI-based ools allow he ansla ion o he da ase s.
ML-based ools can ecognize in o ma ion ha canno be no iced by he human eye and can be used o educe e o s o
omission in obse a ion o e sigh . I can be used o highligh zones o in e es aiding he expe in de ec ion [20,21].
Using pa ame e s ML-based ools can also be used o cha ac e ize he s age o he umo . Cance diagnos ics is plagued
by in e a e bias and inconsis en ep oducibili y e en among expe s [21]. Using au oma ed segmen a ion AI has he
po en ial o inc ease e iciency, ep oducibili y and quali y o umo assessmen . Bayesian Ne wo ks aids he clinicians
wi h he selec ion o cance ea men echniques wi h high le el o unce ain y. BNs [22].
The ad en o Machine Lea ning has imp o ed malignancy ea men as he BNs can be used as p ognos ic and
diagnos ic ool o se e al ypes o malignancies [23]. The essence o BNs li ecycle in compu a ional medical
he apeu ics is p o ided in Figu e 1. Da a igilance as i is desc ibed in Eu opean Da abase on Cance s aims o ensu e
and imp o e pa ien s’ sa e y.
ML ools manu ac u e s o heal hca e ope a ions a e idea ing BNs as an e icien solu ion o p obabilis ic in e ence
ha can aid decision making in clinical ope a ions. BN is conside ed as a nascen machine lea ning echnique, inasmuch
o ien a ing o o he ML echniques like a i icial neu al ne wo k o suppo ec o machines, ha may esul in a clea
and heal hy heal hca e a ena [23,24].
Figu e 1 The e ol ing scheme in compu a ional medicine concep is embodied by i e pilla s
Applica ion o BNs is allu ing due o he capabili y o assessing in e dependencies o clinical ac o s ha exis in la ge
medical da ase s [25,26]. Ba ie s ha e been iden i ied du ing he adop ion and applicabili y o BNs in cance
managemen . Among hese cons ain s, he lack o uni ied p o ocols o p ocessing he e ogeneous medical da a
ep esen s a signi ican challenge o he la ge-scale implemen a ion o hese echnologies [27,28].
Howe e , ini ia i es, such as he Eu opean "Sma 4Heal h" p ojec , demons a e ha ha monizing clinical da abases
can subs an ially imp o e he pe o mance o BNs, achie ing p edic i e diagnos ic accu acy exceeding 90% [29].
Fu he mo e, he combina ion o BNs wi h explainable AI (XAI) echniques and ede a ed lea ning is opening new
possibili ies in p ecision oncology [30]. Pa icula ly in managing complex cance s, his syne gy no only enhances
diagnos ic accu acy bu also p o ides in e p e able explana ions o clinical decisions [31]. A ecen mul icen e s udy
Wo ld Jou nal o Ad anced Resea ch and Re iews, 2025, 26(02), 109-114
111
showed ha hyb id sys ems combining BNs and deep neu al ne wo ks can educe alse posi i es in ea ly lung cance
de ec ion by 32% compa ed o adi ional me hods [32].
3. Ques ioning he alue o clinical p esen a ion
The yawning gap amids isual examina ion and in asi e ine needle aspi a ion calls in o ques ion whe he he ou ine
decision making can unde pin he d i e o e icien cance managemen . The a emp o ea men solu ions is mo e
han necessa y o a adical ee o a success ul cu e wi h a g oup o ea u es such as size, capsula o local issue
in asion being in insic [33].
The he apeu ics deadlock edounds a c oss-cu ing disquie o e ec i e su gical applica ions [34]. The clus e ing o
su gical in e en ion is he sine qua non o he e icien cance ea men . The appeal o su gical esec ion amps up
he e icacy o ca cinoma cu e [34]. A quin essence su gical aiming o edeem quali y in malignancy managemen .
Maneu e abili y o he ca cinoma he apies ci cum en s con en ional ea men and is a c ucial componen o expedi e
he applica ion o ad anced echnologies in cance ca e [35]. Agains ha backd op, he e is oom o manoeu e and
doc o s a e enamo ed wi h non-in asi e ea men s. Medical conce ns o an ab up cu ailmen o adju an o
pallia i e he apies is an exis en ial isk o he pa ien s [33]. The cu e ea men managemen concep mani es s an
e ol ing scheme ha is embodied by echnological ad ancemen s [35].
The pa hological deadlock edounds a c oss-cu ing disquie o a p oac i e s ance wi h d as ic al e a ions in he clinical
judgmen . Fu u e en u es o p eope a i e biopsy may be aken in o accoun o assess he ecu en disease when
e alua ing a pa ien wi h a known diagnosis o cance . The esec ion wi h nega i e ma gins esusci a ed he cance
ea men and ekindled he ailing cu e managemen .
The ope a i e managemen o ca cinomas hinged on he p eope a i e clinical suspicion o in aope a i e iden i ica ion
o malignancy [34]. En bloc esec ion o all adjacen issues wi hou capsula dis up ion e inces he sh ewdness o he
su gical app oach o embed o achie e g ossly and mic oscopically nega i e ma gins, including esec ion o any adjacen
ib oadipose o muscula so issue.
Figu e 2 T adi ional cance ea men modali ies
The epu a ion o chemo he apeu ic agen s is ebbing away o asmuch as is emo al a enua es he su i al o pa ien s
wi h ca cinomas. Unequi ocal and plausible use o in aope a i e ho mone assay is c ucial and may will all in o he
no mal ange i he e has been adequa e esec ion o ho monally ac i e disease. This may agg a a e me as asis, and
u he explo a ion may ha e mo bid epe cussions in su gical ea men . Gene ic and molecula analysis a e bounden
in o de o pe k up he diagnosis landscape and p o ide a cushion o ca cinoma managemen .
I has been ex ensi ely alluded ha chemo he apy is no su icien ly e ec i e o he ea men o some malignancies
[36]. Lack o clinical da a ega ding he e alua ion o sys emic he apy may he ald he dubiousness amongs case
epo s. Technological b eak h oughs in no el he apeu ic sys emic he apy, e e ed o by some as he c i ical junc u e
o he pha maco he apy in he u u e, ha e led o he pledge ha scien is s will expand he ambi o medicines o mono
he apies o combina ion he apies and may balk he used o non- esponsi e medicines [36,37].The adju an
chemo he apy’s a emp s o keep pace con inue o lounde due o limi ed da a and, dubious applicabili y.
Wo ld Jou nal o Ad anced Resea ch and Re iews, 2025, 26(02), 109-114
112
Resea che s ocus on iden i ying and ialing e icien chemo he apy as a ea men al e na i e as he e adia ion
he apy is no s anda dized o se e al malignancies. Con en ious a gumen s o e he adju an adia ion concomi an ly
jeopa dize he he apy pe o mance.
Con inuing esea ch e o s buoy he adju an he apy o manage he ebbs and lows o bio he apy o immuno he apy.
Immuno he apy ins an ia es an auspicious denouemen o a enua e he e ec s o o he ea men me hods. E a ic
decision making due o limi ed da a is holding back bio he apy om i s po en ial succou o elimina e ca cinoma and
amo ize bio he apy pi alls.
Plausible expe ience is needed o dodge medical isks and decisions wi h syne gy and alac i y amids li o al ea men
eam may be aken on an indi idualized basis. Looking o a la e le y, le e aging new he apies ende s a spa king
change o a su ge y-based he apeu ic scheme wi h medical isk a e seness.
3.1. Le e aging Bayesian Ne wo ks in cance managemen
The pe pe a ion o immedia e p ognosis is ega ded a c ucial impe us o he physicians o ponde ca cinoma diagnosis
and expedi ing he ea men in non-in asi e sound manne . Medical s a egy aiming o inco po a e Machine Lea ning
in suppo decision making is pi o al o he ma u e implemen a ion o he BNs in cance managemen [24]. Ba ie s,
such as alidi y issues, necessi a e he comp ehension o algo i hms and he s anda diza ion o BNs o imp o e he
implemen a ion in he clinical a ena [27,28].
To add ess hese challenges and o e come hese ba ie s, se e al s udies a e p oposing ce i ica ion p o ocols based
on s anda ds such as ISO 13485 o AI-assis ed diagnos ic sys ems, including mul icen e e alua ions ha measu e
sensi i i y (>95%) and speci ici y (>90%) in eal-wo ld scena ios [27]. Addi ionally, he c ea ion o public BN model
eposi o ies, such as Cance ML [28] acili a es b oade implemen a ion.
Fu he mo e, success ul adop ion o BNs equi es hei adap a ion o exis ing hospi al in o ma ion sys ems
(HIS/RIS/PACS) h ough s anda dized in e aces like HL7 FHIR [38]. This app oach is suppo ed by pilo expe iences
conduc ed a leading oncology cen e s, which ha e demons a ed ha such in eg a ion can educe diagnos ic ime by
up o 40% o solid umo s [23]. Howe e , challenges emain in in e ope abili y wi h elec onic heal h eco ds, whe e
na u al language p ocessing (NLP) eme ges as a key solu ion o ex ac ing uns uc u ed clinical a iables o eed BN
models [39].
4. Conclusions
I is ecommended he elabo a ion o an ex ensi e s udy o e alua e he ex en o he cu en applica ions and seg ega e
he esea ch in o ma ion ha e eals pinnacles and adeo s o AI implemen a ion in cance managemen . This
pe spec i e discusses aspec s and po en ial o BNs in cance he apeu ics and is in o ma i e o medical doc o s as well
as bio-in o ma icians, AI enginee s, and da a analys s.
Compliance wi h e hical s anda ds
Disclosu e o con lic o in e es
No con lic o in e es o be disclosed.
Re e ences
[1] Su yan M, Shoka Z, Ash aq UA. A i icial in elligence in cance diagnosis and he apy: Cu en s a us and u u e
pe spec i e. Compu e s in Biology and Medicine. 2023; 165:107356.
h ps://doi.o g/10.1016/j.compbiomed.2023.107356
[2] Hamamo o R, e al. Applica ion o a i icial in elligence echnology in oncology: Towa ds he es ablishmen o
p ecision medicine. Cance s. 2020; 12(12):3532. h ps://doi.o g/10.3390/cance s12123532
[3] Malik P, Pa hania M, Ra hau VK. O e iew o a i icial in elligence in medicine. Jou nal o amily medicine and
p ima y ca e. Jou nal o Family Medicine and P ima y Ca e. 2019; 8(7):2328.
h ps://doi.o g/10.4103/j mpc.j mpc_440_19
Wo ld Jou nal o Ad anced Resea ch and Re iews, 2025, 26(02), 109-114
113
[4] Spiegelhal e DJ, Myles JP, Jones DR, Ab ams KR. An in oduc ion o Bayesian me hods in heal h echnology
assessmen . BMJ. 1999; 319(7208):508-12. h ps://doi.o g/10.1136/bmj.319.7208.508
[5] Kakhi K, Alizadehsani R, Dipu Kabi HM, Abbas Khos a i A, Naha andi S, Acha ya UR. The in e ne o medical
hings and a i icial in elligence: ends, challenges, and oppo uni ies. Biocybe ne ics and Biomedical
Enginee ing. 2022; 42(3):749-71. h ps://doi.o g/10.1016/j.bbe.2022.05.008
[6] Londhe, VY, Bhasin B. A i icial in elligence and i s po en ial in oncology, D ug Disco e y Today 2019; 24(1):228-
232. h ps://doi.o g/10.1016/j.d udis.2018.10.005
[7] Eisenhaue EA, e al. New esponse e alua ion c i e ia in solid umou s: e ised RECIST guideline ( e sion 1.1).
Eu opean Jou nal o Cance . 2009; 45(2):228-247.h ps://doi.o g/10.1016/j.ejca.2008.10.026
[8] Schwa z, L.H., e al. RECIST 1.1 - S anda disa ion and disease-speci ic adap a ions: Pe spec i es om he RECIST
Wo king G oup. Eu opean Jou nal o Cance . 2016; 62:138-145. h ps://doi.o g/10.1016/j.ejca.2016.03.082
[9] Pa k JO, e al. Measu ing esponse in solid umo s: compa ison o RECIST and WHO esponse c i e ia. Japanese
Jou nal o Clinical Oncology. 2003; 33:533-7. h ps://doi.o g/10.1093/jjco/hyg093
[10] Rong G, Mendez A, Assi EB, Zhao B, Sawan M. A i icial in elligence in heal hca e: e iew and p edic ion case
s udies. Enginee ing. 2020; 6(3):291-1. h ps://doi.o g/10.1016/j.eng.2019.08.015
[11] Sche ini F, Ven u ini S, Giuliano M, e al. (2022) Mul iple Bayesian ne wo k me a-analyses o es ablish
he apeu ic algo i hms o me as a ic iple nega i e b eas cance , Cance T ea men Re iews, 111 (102468).
h ps://doi.o g/10.1016/j.c .2022.102468
[12] Huehn M, Gaebel J, Oese A, Die z A, Neumu h T, Wichmann G, S oeh M. Bayesian Ne wo ks o Suppo Decision-
Making o Immune-Checkpoin Blockade in Recu en /Me as a ic (R/M) Head and Neck Squamous Cell
Ca cinoma (HNSCC). Cance s (Basel). 2021; 13(23):5890. h ps://doi.o g/10.3390/cance s13235890
[13] Sesen MB, Nicholson AE, Bana es-Alcan a a R, Kadi T, B ady M. Bayesian ne wo ks o clinical decision suppo
in lung cance ca e. PloS one. 2013; 8(12):e82349. h ps://doi.o g/10.1371/jou nal.pone.0082349
[14] Sieswe da M, Xie S, an Rossum R, e . (2023) Iden i ying Con ounde s Using Bayesian Ne wo ks and Es ima ing
T ea men E ec in P os a e Cance Wi h Obse a ional Da a. JCO Clinical Cance In o ma ics. 7:e2200080.
h ps://doi.o g/10.1200/CCI.22.0008
[15] Hoshi K, Kawakami J, Kumagai M, Kasaha a S, Nishimu a N, Nakamu a H, Sa o K. An analysis o hy oid unc ion
diagnosis using Bayesian- ype and SOM- ype neu al ne wo ks. Chemical and pha maceu ical bulle in. 2005,
53(12):1570-4. h ps://doi.o g/10.1248/cpb.53.1570
[16] McLachlan, S., Dube K, Hi man GA, No man E Fen on NE, Ky imi E. Bayesian ne wo ks in heal hca e: Dis ibu ion
by medical condi ion. A i icial In elligence in Medicine. 2020; 107:101912.
h ps://doi.o g/10.1016/j.a med.2020.101912
[17] A o a P, Boyne D, Sla e JJ, Gup a A, B enne DR, D uzdzel MJ. Bayesian ne wo ks o isk p edic ion using eal-
wo ld da a: a ool o p ecision medicine. Value in Heal h. 2019; 22(4):439-45.
h ps://doi.o g/10.1016/j.j al.2019.01.006
[18] Zhang, B, e al. Machine Lea ning and AI in Cance P ognosis, P edic ion, and T ea men Selec ion: A C i ical
App oach. Jou nal o Mul idisciplina y Heal hca e. 2023; 16:1779-1791.
h ps://doi.o g/10.2147/JMDH.S410301
[19] Gup a S, Kuma Y. Cance p ognosis using a i icial in elligence-based echniques. SN Compu e Science. 2022;
3:1-8. h ps://doi.o g/10.1007/s42979-021-00964-3
[20] Busna u Ș, Niculescu AG, Bolocan A, e al. Clinical applica ions o a i icial in elligence—An upda ed o e iew.
Jou nal o clinical medicine. 2022; 11(8):2265. h ps://doi.o g/10.3390/jcm11082265
[21] Seoni, S., e al. Applica ion o unce ain y quan i ica ion o a i icial in elligence in heal hca e: A e iew o las
decade (2013–2023). Compu e s in Biology and Medicine. 2023; 1:107441.
h ps://doi.o g/10.1016/j.compbiomed.2023.107441
[22] Ky imi, E., McLachlan S, Dube K, e al. Bayesian Ne wo ks in Heal hca e: he chasm be ween esea ch en husiasm
and clinical adop ion. medRxi , 2020; 5:2020-06. h ps://doi.o g/10.1101/2020.06.04.20122911
[23] Abdullah AA, Hassan MM, Mus a a YT. A e iew on Bayesian deep lea ning in heal hca e: Applica ions and
challenges. IEEE Access. 2022; 10:36538-62.
Wo ld Jou nal o Ad anced Resea ch and Re iews, 2025, 26(02), 109-114
114
[24] Alshuh i MS, Al-Musawi SG, Al-Alwany AA e al. A i icial in elligence in cance diagnosis: Oppo uni ies and
challenges, Pa hology - Resea ch and P ac ice. 2024; 253:154996. h ps://doi.o g/10.1016/j.p p.2023.154996
[25] Cypko MA, S oeh M, Oel ze-Ja a S, Die z A, Lemke HU. A Guide o Cons uc ing Bayesian Ne wo k G aphs o
Cance T ea men Decisions. S udies in Heal h Technology and In o ma ics. 2017; 245:1355.
h ps://doi.o g/10.3233/978-1-61499-830-3-1355
[26] an de S ap L, an Haa en MF, an Ma ewijk EF, e al. The easibili y o a Bayesian ne wo k model o assess he
p obabili y o simul aneous symp oms in pa ien s wi h ad anced cance . Scien i ic Repo s. 2022; 12:22295.
h ps://doi.o g/10.1038/s41598-022-26342-4
[27] Zhou Y, Hospedales TM, Fen on N. When and whe e o ans e o Bayesian ne wo k pa ame e lea ning, Expe
Sys ems wi h Applica ions. 2016; 55 (361-373). h ps://doi.o g/10.1016/j.eswa.2016.02.011
[28] Ky imi E, Dube K, Fen on N, e al. Bayesian ne wo ks in heal hca e: Wha is p e en ing hei adop ion? A i icial
In elligence in Medicine 2021; 116:102079. h ps://doi.o g/10.1016/j.a med.2021.102079
[29] Angelopoulos N, Cha zipli A, Nangalia J, Mau a F, Campbell PJ. Bayesian ne wo ks elucida e complex genomic
landscapes in cance . Communica ions Biology. 2022; 5:306. h ps://doi.o g/10.1038/s42003-022-03243-w
[30] Kuipe s J, Su e P, Mo a G. E icien Sampling and S uc u e Lea ning o Bayesian Ne wo ks, Jou nal o
Compu a ional and G aphical S a is ics, 2022; 31(3):639-650.
h ps://doi.o g/10.1080/10618600.2021.2020127
[31] Mao L, Wang H., Hu LS, T an NL, Canoll PD, Swanson K, Li J. Knowledge-In o med Machine Lea ning o Cance
Diagnosis and P ognosis: A Re iew, IEEE T ansac ions on Au oma ion Science and Enginee ing, ol. 22, pp. 1008–
1028, 2025. h ps://ieeexplo e.ieee.o g/s amp/s amp.jsp?a numbe =10806835
[32] Rawa D, Sha ma S, Bhadula S. "Case based Reasoning Technique in Digi al Diagnos ic Sys em o Lung Cance
De ec ion" 2023 8 h In e na ional Con e ence on Communica ion and Elec onics Sys ems (ICCES), Coimba o e,
India, 2023; 1355-1361. 10.1109/ICCES57224.2023.10192863.
h ps://ieeexplo e.ieee.o g/abs ac /documen /10192863
[33] Liu B, Zhou H, Tan L, e al. Explo ing ea men op ions in cance : umo ea men s a egies. Signal
T ansduc ion and Ta ge ed The apy. 2024; 9:175. h ps://doi.o g/10.1038/s41392-024-01856-7
[34] Saunde s AC, Mu ebi M, Rao TS. A Re iew o he Cu en S a e o Global Su gical Oncology and he Role o
Su geons Who T ea Cance : Ou P o ession's Impe a i e o Ac Upon a Wo ldwide C isis in E olu ion. Annals o
Su gical Oncology. 2023; 30(6):3197-3205. h ps://doi.o g/10.1245/s10434-023-13352-3
[35] Debela DT, Muzazu SG, He a o KD, Ndalama MT, Mesele BW, Haile DC, Ki ui SK, Manyazewal T. New app oaches
and p ocedu es o cance ea men : Cu en pe spec i es. SAGE Open Medicone. 2021;
9:20503121211034366. h ps://doi.o g/10.1177/20503121211034366
[36] Le ai A, de The H. Con en ional chemo he apy: millions o cu es, un esol ed he apeu ic index. Na u e Re iews
Cance . 2025; 25:209–218. h ps://doi.o g/10.1038/s41568-024-00778-4
[37] Tilsed CM, Fishe SA, Nowak AK, Lake RA and Les e huis WJ. Cance chemo he apy: insigh s in o cellula and
umo mic oen i onmen al mechanisms o ac ion. F on ie s in Oncology. 2022;12:960317.
h ps://doi.o g/10.3389/ onc.2022.960317
[38] Wong-Pé ez D, Ma -Co nelio O. HL7 In e ope abili y S anda d in Heal h: Sys ema ic Re iew o he Li e a u e.
Re is a Cubana de In o má ica Médica, 2023; 15. h p://scielo.sld.cu/scielo.php?sc ip =sci_a ex &pid=S1684-
18592023000200009&lng=es& lng=es.
[39] Hossain E, Rana R, Higgins N, Soa J, Da a Ba ua P. Na u al Language P ocessing in Elec onic Heal h Reco ds in
ela ion o heal hca e decision-making: A sys ema ic e iew. Compu e s in Biology and Medicine. 2023;
155:106649. h ps://doi.o g/10.1016/j.compbiomed.2023.106649
