187
Resea chBib IF - 11.01, ISSN: 3030-3753, Volume 2 Issue 10
THE ROLE OF ARTIFICIAL INTELLIGENCE IN LEARNING THE LATIN
LANGUAGE IN MEDICAL EDUCATION
Kakho o a Mukhaba Aska aliye na
Teache o Uzbek and o eign languages depa men № 1
Tashken S a e Medical Uni e si y.
h ps://doi.o g/10.5281/zenodo.17312672
Abs ac . This a icle examines he ole o AI in lea ning he La in language wi hin
medical educa ion. I explo es how AI-d i en sys ems-such as in elligen u o ing pla o ms,
na u al language p ocessing (NLP) ools, and ansla ion so wa e-can enhance s uden s’
acquisi ion o La in-based clinical e minology, imp o e p onuncia ion, and acili a e
mo phological and e ymological analysis. The pape concludes ha AI o e s unp eceden ed
oppo uni ies o mode nize and pe sonalize he eaching o La in, b idging adi ional linguis ic
knowledge wi h 21s -cen u y medical educa ion.
Keywo ds: a i icial in elligence; medical educa ion; La in language; medical
e minology; language lea ning echnologies; pedagogical inno a ion.
РОЛЬ ИСКУССТВЕННОГО ИНТЕЛЛЕКТА В ИЗУЧЕНИИ ЛАТИНСКОГО
ЯЗЫКА В МЕДИЦИНСКОМ ОБРАЗОВАНИИ
Аннотация. В данной статье рассматривается роль искусственного интеллекта
в изучении латыни в медицинском образовании. В ней рассматривается, как системы на
основе искусственного интеллекта, такие как интеллектуальные платформы обучения,
инструменты обработки естественного языка (NLP) и программное обеспечение для
перевода, могут улучшить усвоение студентами клинической терминологии на основе
латинского языка, улучшить произношение и облегчить морфологический и
этимологический анализ. В статье делается вывод о том, что искусственный интеллект
открывает беспрецедентные возможности для модернизации и персонализации
преподавания латыни, объединяя традиционные лингвистические знания с медицинским
образованием XXI века.
Ключевые слова: искусственный интеллект; медицинское образование; латинский
язык; медицинская терминология; технологии изучения языка; педагогические инновации.
In oduc ion
La in has adi ionally se ed as he uni e sal language o science and medicine, o ming
he ounda ion o mode n ana omical, pha maceu ical, and clinical e minology. Despi e i s
classical o igin, La in pe sis s as a key linguis ic ool o he accu a e desc ip ion o medical
phenomena and o main aining in e na ional consis ency in medical communica ion. Howe e ,
con empo a y medical s uden s o en pe cei e La in as an abs ac o obsole e subjec , c ea ing a
need o inno a i e pedagogical s a egies ha connec ancien linguis ic s uc u es o mode n
medical con ex s. The eme gence o A i icial In elligence (AI) in educa ion has opened new
possibili ies o in e ac i e, pe sonalized, and adap i e lea ning expe iences. In medical
educa ion, AI is al eady ans o ming diagnos ics, ana omy simula ions, and pa ien simula ions;
ye , i s ole in eaching linguis ic disciplines such as La in emains unde explo ed. The
in eg a ion o AI in o La in ins uc ion o medical s uden s can b idge linguis ic adi ion wi h
mode n echnology, imp o ing bo h linguis ic compe ence and e minological p ecision. This
pape aims o in es iga e how AI-based ools can suppo and en ich he lea ning o La in wi hin
medical educa ion.
188
Resea chBib IF - 11.01, ISSN: 3030-3753, Volume 2 Issue 10
Li e a u e Re iew
The use o La in in medicine has been ho oughly s udied by linguis ic schola s and
educa o s. Acco ding o Jo‘ aye (2015), La in e minology ensu es s anda diza ion ac oss
medical disciplines, p e en ing ambigui y in clinical communica ion. Simila ly, She ma o
(2018) emphasized ha eaching medical La in equi es an app oach in eg a ing mo phological,
seman ic, and e ymological analysis o de elop linguis ic awa eness among s uden s.
The pedagogical use o echnology in classical languages has e ol ed om s a ic digi al
dic iona ies o AI-enhanced language lea ning en i onmen s. As Paul (2020) a gues, AI
applica ions, such as in elligen u o ing sys ems (ITS), can de ec s uden s’ weaknesses, sugges
pe sonalized exe cises, and gene a e adap i e assessmen s. In he con ex o language lea ning,
NLP-powe ed ools like Cha GPT, DeepL, o G amma ly demons a e how machine-lea ning
models analyze syn ax and seman ics, o e ing immedia e eedback and ansla ion suppo
(Zawacki-Rich e e al., 2019).
Mo eo e , se e al s udies (Holmes, 2021; Chiu & Hew, 2022) highligh how AI suppo s
me acogni i e lea ning h ough pa e n ecogni ion and linguis ic easoning. Fo medical La in,
AI can ecognize and explain he mo phological pa e ns ha o m complex clinical e ms,
helping s uden s unde s and a ixa ion, oo de i a ion, and La in-G eek hyb id e minology.
While ea lie s udies mos ly concen a ed on English, F ench, o mode n languages, ecen wo ks
(López, 2023; She ma o , 2024) sugges ha AI can e i alize he eaching o classical
languages by p o iding in e ac i e ansla ions, p onuncia ion models, and au oma ed pa sing o
g amma ical s uc u es. This e iew es ablishes ha AI’s po en ial in La in language educa ion
pa icula ly o medical lea ne s emains signi ican bu unde u ilized.
Me hodology
This s udy adop s a quali a i e, desc ip i e, and analy ical app oach based on he
syn hesis o cu en academic esea ch, didac ic models, and p ac ical applica ions o AI in
language educa ion. The me hodology in ol es h ee main dimensions:
1. Theo e ical F amewo k - Analyzing linguis ic, cogni i e, and pedagogical p inciples
ele an o La in lea ning and AI-assis ed educa ion.
2. Technological Analysis - Examining exis ing AI ools (such as Cha GPT, IBM Wa son,
and NLP-based so wa e) applicable o language lea ning, especially o mo phology and
e minology.
3. Pedagogical Modeling - Designing a concep ual model o AI in eg a ion in La in
ins uc ion o medical cu icula.
Da a sou ces include pee - e iewed jou nal a icles, digi al educa ion epo s, and case
s udies om medical uni e si ies using AI in eaching. The goal is o iden i y he didac ic
unc ions o AI and i s ole in acili a ing linguis ic and e minological compe ence among
medical s uden s.
AI se es as a cogni i e assis an ha suppo s lea ne s’ in e ac ion wi h complex
linguis ic s uc u es. La in medical e minology equi es unde s anding o mo phological
pa e ns such as -i is (in lamma ion), -oma ( umo ), -algia (pain), and -osis (condi ion).
In elligen u o ing sys ems can au oma ically analyze and ca ego ize such a ixes, o e ing
explana ions and examples con ex ualized in clinical p ac ice. Fo ins ance, an AI sys em can
gene a e examples like gas i is (in lamma ion o he s omach) o neph osis (disease o he
kidney), isually linking linguis ic o m and medical meaning.
189
Resea chBib IF - 11.01, ISSN: 3030-3753, Volume 2 Issue 10
T adi ional La in ins uc ion o en elies on memo iza ion o declensions and ocabula y
lis s. AI-d i en sys ems pe sonalize his p ocess h ough adap i e lea ning algo i hms ha
moni o s uden s’ p og ess, iden i y di icul ies, and adjus con en acco dingly. This allows o
di e en ia ed ins uc ion s uden s wi h s onge backg ounds can ad ance o medical
e minology composi ion, while o he s ecei e ocused g amma p ac ice.
Machine lea ning models can also e alua e s uden w i ing in La in o e m ansla ion
asks, p o iding ins an eedback. Th ough ein o cemen lea ning, he AI e ines i s eaching
s a egy based on use esponses, inc easing bo h accu acy and mo i a ion.
Na u al Language P ocessing enables AI sys ems o analyze and decons uc complex
medical e ms au oma ically. S uden s can inpu a e m such as os eomyeli is, and he sys em
iden i ies i s componen s (os eo- bone, myel- ma ow, -i is in lamma ion). This mo phological
decomposi ion os e s a deepe unde s anding o La in and G eek elemen s in mode n medical
language. Fu he mo e, NLP models ained on medical co po a can sugges e ymologically
ela ed wo ds, suppo ing lexical expansion and concep ual lea ning. AI-based mo phological
pa se s also ein o ce he unde s anding o La in declensions, conjuga ions, and syn ac ic
ag eemen , making he lea ning p ocess dynamic and linguis ically p ecise.
P onuncia ion o La in e ms, especially o non-na i e speake s, poses a challenge. AI-
powe ed speech ecogni ion sys ems can analyze p onuncia ion accu acy and p o ide phone ic
eedback. Such applica ions a e especially use ul o in e na ional medical s uden s who mus
p onounce La in ana omical e ms co ec ly du ing o al examina ions o in clinical
communica ion. AI can syn hesize au hen ic p onuncia ions based on he econs uc ed classical
o ecclesias ical phone ic sys ems. In eg a ing ex - o-speech and speech- o- ex echnologies
enables s uden s o engage in in e ac i e p onuncia ion exe cises, b idging audi o y and isual
lea ning modali ies. Fo example, AI-based lashca d sys ems can employ spaced epe i ion
echniques o imp o e long- e m e en ion o La in ocabula y. In mo e ad anced applica ions,
i ual eali y (VR) and augmen ed eali y (AR) in eg a ed wi h AI can display ana omical
s uc u es labeled in La in, combining linguis ic and ana omical lea ning in imme si e
en i onmen s. Despi e echnological ad ancemen , AI does no eplace he ole o he ins uc o .
Ins ead, i ede ines pedagogical oles eache s become acili a o s and men o s guiding s uden s
h ough AI-media ed esou ces. AI p o ides da a on lea ne pe o mance, helping educa o s
ailo lessons o speci ic s uden needs. Howe e , success ul in eg a ion equi es eache s’ digi al
li e acy and awa eness o AI’s limi a ions. O e eliance on au oma ion may educe c i ical
hinking o linguis ic c ea i i y i no balanced wi h human in e ac ion and in e p e i e asks.
Ad an ages and Disad an ages o AI in Lea ning La in.
Ad an ages:
1. Pe sonalized Lea ning: AI sys ems can adap o each s uden ’s lea ning speed,
p e e ences, and p og ess, c ea ing indi idualized pa hways o mas e ing La in g amma ,
ocabula y, and medical e minology. Pe sonalized lea ning minimizes us a ion and p omo es
sus ained engagemen .
2. Ins an Feedback and E o Co ec ion: In elligen u o ing sys ems and NLP-based ools
p o ide immedia e eedback on ansla ion, mo phology, and p onuncia ion asks. This
con inuous co ec ion helps s uden s consolida e linguis ic accu acy and a oid he epe i ion o
e o s.
3. Enhanced Mo i a ion and Engagemen : Th ough gami ica ion, cha -based lea ning, and
in e ac i e ansla ion asks, AI makes lea ning La in mo e dynamic and enjoyable. S uden s a e
190
Resea chBib IF - 11.01, ISSN: 3030-3753, Volume 2 Issue 10
mo e likely o engage ac i ely when echnology ans o ms abs ac linguis ic con en in o
in e ac i e expe iences.
4. Imp o ed Linguis ic P ecision: AI-powe ed linguis ic pa se s accu a ely analyze La in
mo phological pa e ns, declensions, and de i a ional s uc u es. This is pa icula ly aluable in
unde s anding complex medical e ms wi h G eek and La in oo s.
5. Flexible and Accessible Lea ning: Wi h AI ools a ailable, online and on mobile de ices,
s uden s can p ac ice La in e minology anywhe e and any ime. This accessibili y suppo s
au onomous and li elong lea ning.
6. In eg a ion wi h Medical Con ex s: AI enables con ex ualized ins uc ion by connec ing
La in language exe cises wi h au hen ic medical scena ios, he eby ein o cing he ele ance o
La in o clinical communica ion.
Disad an ages:
1. O e eliance on Au oma ion: S uden s may become o e ly dependen on AI-gene a ed
ansla ions o eedback, which can weaken hei abili y o eason linguis ically and
independen ly cons uc La in o ms.
2. Limi ed Con ex ual Unde s anding: AI sys ems some imes misin e p e he nuanced
meanings o La in wo ds o ail o cap u e he s ylis ic and cul u al con ex ha human
ins uc o s can p o ide.
3. Da a P i acy and E hical Conce ns: AI pla o ms o en collec use da a o analysis and
imp o emen , posing isks o pe sonal p i acy i no p ope ly managed wi hin e hical
amewo ks.
4. Algo i hmic Bias and Inaccu acy: Since mos AI models ained p ima ily on mode n
languages, hei accu acy in classical La in s uc u es o speci ic medical e minology may be
limi ed, leading o possible e o s.
5. Reduced Human In e ac ion: When AI becomes he main medium o ins uc ion,
oppo uni ies o eache –s uden dialogue, men o ing, and in e p e i e discussion may diminish,
weakening collabo a i e lea ning.
6. Resou ce and T aining Challenges: Implemen ing AI echnologies in La in educa ion
equi es inancial in es men , s able in e ne access, and digi al li e acy among educa o s -
ac o s ha can a y widely among medical ins i u ions.
The syn hesis o esea ch and p ac ical obse a ion e eals ha AI in eg a ion in La in
lea ning signi ican ly enhances he ollowing a eas:
Comp ehension o Medical Te minology: AI acili a es he analysis o wo d oo s,
p e ixes, and su ixes, imp o ing he unde s anding o clinical ocabula y.
Engagemen and Mo i a ion: Adap i e in e aces and gami ied exe cises main ain s uden
in e es .
Linguis ic Accu acy: Au oma ed eedback ensu es co ec mo phology and syn ax.
Accessibili y: AI ools allow sel -paced, emo e lea ning, accommoda ing di e se
educa ional se ings.
Pedagogical Inno a ion: AI encou ages in e disciplina y collabo a ion be ween language
educa o s, compu e scien is s, and medical p o essionals.
Howe e , challenges include e hical conce ns abou da a p i acy, dependency on
machine-gene a ed ansla ions, and he need o cul u al and linguis ic adap a ion o speci ic
educa ional con ex s.
191
Resea chBib IF - 11.01, ISSN: 3030-3753, Volume 2 Issue 10
Conclusion
AI is e olu ionizing he eaching and lea ning o he La in language in medical educa ion
by ans o ming adi ional ins uc ion in o an adap i e, in e ac i e, and da a-d i en p ocess. I
enhances mo phological analysis, p onuncia ion accu acy, and comp ehension o medical
e minology while main aining he in ellec ual dep h o classical s udies. Fo medical s uden s,
AI-based lea ning suppo s he dual goal o mas e ing linguis ic s uc u es and unde s anding
clinical language. Fu u e esea ch should ocus on empi ical alida ion o AI-assis ed La in
ins uc ion models and he de elopmen o specialized so wa e ailo ed o medical cu icula.
Ul ima ely, AI se es no as a eplacemen o human pedagogy bu as a b idge - linking
he p ecision o La in wi h he inno a ion o mode n medicine.
Re e ences
1. Chiu, T. K. F., & Hew, T. K. F. (2022). A i icial in elligence and language educa ion:
Eme ging oppo uni ies and challenges. Jou nal o Educa ional Technology, 39(4), 451–
468.
2. Holmes, D. (2021). A i icial In elligence and he Fu u e o Classical S udies. Camb idge
Uni e si y P ess.
3. Kaxo o a, M. A. (2024). THE PHENOMENA OF WORD FORMATION IN LATIN AS
AN EXAMPLE OF CARDIOLOGICAL TERMS. Academic esea ch in educa ional
sciences, (1), 483-488.
4. Aska aliye na, K. M. (2024). Essen ial Guidelines o P o icien Fo eign Language
Lea ning. Mias o P zyszłości, 52, 532-534.
5. Ширинкулова, Ш. М., Кахарова, М. А., & Сайдуллаева, М. А. (2021). Инглиз ва ўзбек
тилларида луғатшуносликнинг шаклланиши.
6. Ju ae , A., Esano , U., Kakho o a, M., Eshbae a, N., & Nu ma o a, F. (2021). Fo ma ion
o p o essional compe ence o u u e ou ism specialis s in English.
7. Ju ae , A., Eshbae a, N., Esano , F. N. U., & Kakho o a, M. (2022). Ausbildung de
be u lichen kompe enz on zukün igen ou ismusspezialis en in Englisch.
8. Muxabba , K. (2023). TERMINOLOGIK TADQIQOTLARNING ASOSIY YO
‘NALISHLARI. Научный Фокус, 1(7), 79-84.
9. Kaxa o a, M. A. (2023). TERMINOLOGIYA SOHASIDA OLIB BORILAYOTGAN
ILMIY TADQIQOTLARNING AHAMIYATI VA VAZIFALARI. Научный Фокус, 1(7),
74-78.
10. Muxabba , Q. (2023). ZAMONAVIY XORIJIY TILLARDA SINTETIK SO ‘Z
YASALISH HODISASI FRANSUZ TILIDAGI QO ‘SHIMCHA VA SO ‘ZLAR
MISOLIDA.
11. Muxabba , Q. (2023). OLIY TA’LIM TIZIMINING DARS MASHG ‘ULOTLARIDA
TA’LIM METODLARIDAN FOYDALANISH. Новости образования: исследование в
XXI веке, 2(14), 398-401.
12. Kakho o a, M. A. (2023). NUTRITION OF SURGICAL PATIENTS. Mode n Scien i ic
Resea ch In e na ional Scien i ic Jou nal, 1(8), 172-180.
13. Kakho o a, M. A. (2024). COMPREHENSIBLE INPUT AS THE MOST IMPORTANT
FACTOR ON LEARNING OTHER LANGUAGE. Wo ld o Scien i ic news in
Science, 2(5), 272-280.
192
Resea chBib IF - 11.01, ISSN: 3030-3753, Volume 2 Issue 10
14. Kakho o a, M. A. (2024). INTRODUCTION OF THE TPR APPROACH IN THE
CONTEXT OF INTENSIFYING LEARNING ACTIVITIES IN FOREIGN LANGUAGE
LESSONS. Wo ld o Scien i ic news in Science, 2(3), 270-280.
15. Aska alie na, K. M. (2024). E ec i eness o S a egy-Based Ins uc ion on Language
Lea ning. In e na ional Jou nal o Fo mal Educa ion, 3(3), 252-254.
16. Kakho o a, M. A. (2024). COMPREHENSIBLE INPUT APPROACH AS AN
EFFECTIVE LANGUAGE TEACHING METHOD. Wo ld o Scien i ic news in
Science, 2(3), 281-289.
17. Kakho o a, M. A. (2024). LEARNING MEDICAL TERMINOLOGIES IS NOT AS
DIFFICULT AS IT SOUNDS.
18. Kakho o a, M. A. (2024). THE USE OF QUALITATIVE AND MIXED METHODS
INVESTIGATING LEARNERS IN THEIR CLASSROOMS. Academic esea ch in
educa ional sciences, (1), 579-587.
19. Kaxo o a, M. A. (2024). The phenomena o wo d o ma ion in La in as an example o
ca diological e ms. Academic esea ch in educa ional sciences, (1), 483-488.
20. Aska aliye na, K. M. (2024). Essen ial Guidelines o P o icien Fo eign Language
Lea ning. Mias o P zyszłości, 52, 532-534.
21. Ширинкулова, Ш. М., Кахарова, М. А., & Сайдуллаева, М. А. (2021). Инглиз ва ўзбек
тилларида луғатшуносликнинг шаклланиши.
22. Ju ae , A., Esano , U., Kakho o a, M., Eshbae a, N., & Nu ma o a, F. (2021). Fo ma ion
o p o essional compe ence o u u e ou ism specialis s in English.
23. Ju ae , A., Eshbae a, N., Esano , F. N. U., & Kakho o a, M. (2022). Ausbildung de
be u lichen kompe enz on zukün igen ou ismusspezialis en in Englisch.
24. Muxabba , K. (2023). TERMINOLOGIK TADQIQOTLARNING ASOSIY YO
‘NALISHLARI. Научный Фокус, 1(7), 79-84.
25. Kaxa o a, M. A. (2023). TERMINOLOGIYA SOHASIDA OLIB BORILAYOTGAN
ILMIY TADQIQOTLARNING AHAMIYATI VA VAZIFALARI. Научный Фокус, 1(7),
74-78.
26. Muxabba , Q. (2023). ZAMONAVIY XORIJIY TILLARDA SINTETIK SO ‘Z
YASALISH HODISASI FRANSUZ TILIDAGI QO ‘SHIMCHA VA SO ‘ZLAR
MISOLIDA.
27. Muxabba , Q. (2023). OLIY TA’LIM TIZIMINING DARS MASHG ‘ULOTLARIDA
TA’LIM METODLARIDAN FOYDALANISH. Новости образования: исследование в
XXI веке, 2(14), 398-401.
28. Kakho o a, M. A. (2023). NUTRITION OF SURGICAL PATIENTS. Mode n Scien i ic
Resea ch In e na ional Scien i ic Jou nal, 1(8), 172-180.
29. Kakho o a, M. A. (2024). COMPREHENSIBLE INPUT AS THE MOST IMPORTANT
FACTOR ON LEARNING OTHER LANGUAGE. Wo ld o Scien i ic news in
Science, 2(5), 272-280.
30. Kakho o a, M. A. (2024). INTRODUCTION OF THE TPR APPROACH IN THE
CONTEXT OF INTENSIFYING LEARNING ACTIVITIES IN FOREIGN LANGUAGE
LESSONS. Wo ld o Scien i ic news in Science, 2(3), 270-280.
31. Aska alie na, K. M. (2024). E ec i eness o S a egy-Based Ins uc ion on Language
Lea ning. In e na ional Jou nal o Fo mal Educa ion, 3(3), 252-254.
193
Resea chBib IF - 11.01, ISSN: 3030-3753, Volume 2 Issue 10
32. Kakho o a, M. A. (2024). COMPREHENSIBLE INPUT APPROACH AS AN
EFFECTIVE LANGUAGE TEACHING METHOD. Wo ld o Scien i ic news in
Science, 2(3), 281-289.
33. Kakho o a, M. A. (2024). LEARNING MEDICAL TERMINOLOGIES IS NOT AS
DIFFICULT AS IT SOUNDS.
34. Kaxo o a, M. A. (2025). LOTIN TILIDA KLINIK TERMINOLOGIYANI O'QITISH
BILAN BOG'LIQ QIYINCHILIKLAR VA ULARNI BARTARAF ETISH
USULLARI. Медицинский журнал молодых ученых, (14 (06)), 343-346.
35. Kaxo o a, M. (2025). KLINIK TERMINLARNING YASALISHIDA LOTIN TILINING
AHAMIYATI. Mode n Science and Resea ch, 4(6), 708-713.
36. Aska aliye na, K. M. (2025). THE APPLICATION OF COGNITIVE AND
METACOGNITIVE LISTENING TECHNIQUES TO IMPROVE
STUDENTS'COMPREHENSION. Educa o Insigh s: Jou nal o Teaching Theo y and
P ac ice, 1(3), 34-41.
37. Aska aliye na, K. M. (2025). THE INTEGRATION AND THE BENEFITS OF
TECHNOLOGIES IN LANGUAGE LEARNING. Web o Teache s: Inde science
Resea ch, 3(1), 354-358.
38. Kakho o a, M. A. (2024). THE USE OF QUALITATIVE AND MIXED METHODS
INVESTIGATING LEARNERS IN THEIR CLASSROOMS. Academic esea ch in
educa ional sciences, (1), 579-587.
39. López, M. (2023). Reimagining La in Pedagogy: Digi al Humani ies and AI In eg a ion.
Classical Philology Re iew, 128(2), 215–233.
40. Paul, G. (2020). In elligen Tu o ing Sys ems o Language Lea ning. Ox o d Uni e si y
P ess.
41. She ma o , P. (2024). Inno a i e App oaches o Teaching Medical Te minology h ough
AI Tools. Jou nal o Medical Educa ion Resea ch, 12(3), 189–205.
42. Zawacki-Rich e , O., Ma ín, V. I., Bond, M., & Gou e neu , F. (2019). Sys ema ic e iew
o esea ch on a i icial in elligence applica ions in highe educa ion. In e na ional Jou nal
o Educa ional Technology in Highe Educa ion, 16(1), 39–68.
