Wiadomości Lekarskie Medical Advances, VOLUME LXXVIII, ISSUE 2, FEBRUARY 2025 © Aluna Publishing

REVIEW ARTICLE CONTENTS

Microbial infection disease diagnosis and treatment by

artificial intelligence

Laith M Abbas Al-Huseini1, Nisreen Jawad Kadhim2, Mohammed Salih Mahdi2, Raed H. Ogaili3,
Orooba Al-hammood4
1
DEPARTMENT OF PHARMACOLOGY, COLLEGE OF MEDICINE, WARITH AL-ANBIYAA UNIVERSITY, KARBALA, IRAQ
2
DEPARTMENT OF MICROBIOLOGY, COLLEGE OF MEDICINE, WARITH AL-ANBIYAA UNIVERSITY, KARBALA, IRAQ
3
COLLEGE OF VETERINARY MEDICINE, UNIVERSITY OF KERBALA. KARBALA, IRAQ
4
DEPARTMENT OF BIOLOGY, COLLEGE OF SCIENCES, AL-NAHRAIN UNIVERSITY, BAGHDAD, IRAQ

ABSTRACT
Aim: The main objective of this study was to examine current perspectives on initiatives to identify viable approaches for more accurate diagnosis of infectious diseases.
Materials and Methods: Indexed databases, such as EMBASE, Scopus, and PubMed/Medline, and online searches were performed. Cross-referencing of
important articles led to additional references. This study reviews important clinical applications and provides an overview of several Artificial intelligence
algorithms used in diagnosis of diseases caused by pathogenic microorganisms.
Conclusions: Artificial intelligence technologies could be used in nearly every area of medicine. Before these new technologies may be used in actual clinical
settings, more carefully planned clinical trials are required.
KEY WORDS: Microbial, Infection, Artificial Intelligence

Wiad Lek. 2025;78(2):442-447. doi: 10.36740/WLek/200511 DOI

INTRODUCTION of sophisticated microbiology diagnostics is one of

The term artificial intelligence (AI), first coined in 1956, the largest problems facing the clinical microbiology
refers to digital systems that attempt to solve prob- community. It would be highly beneficial to provide
lems and continuously improve their data processing explicit guidance on how to identify and demonstrate
skills by using algorithms that mimic human intellect. treatment value [4, 5]. There are two technologies used
These days, artificial intelligence has expanded too in medicine: visual and artificial intelligence, the latter of
many industries and started to help them thanks to which is related to web design. These features include
the rise in data entry, the usage of more potent cod- electronic health records, appointment scheduling, pre-
ing languages, and the application of sophisticated scribing, drug interactions, imaging and osteoporosis,
algorithms [1]. This implies that they should also play and score systems for diagnosis and verification. Con-
a bigger role in bacterial epidemiology. For instance, versely, physical components include post-operative
at major hospitals, machine learning algorithms can technical support, social assistive technology used in
forecast patients’ likelihood of contracting Clostridium elder care, rehabilitation, and televiewing [6, 7]. Artificial
diffusible infection in advance, enabling medical staff to intelligence is the imitation of human intelligence via
take proactive precautions before an infection happens the use of computers. This new science explores and
[2, 3]. Contact tracing in the emergency room can be creates ideas, methods, instruments, and strategies to
done more quickly and effectively with real-time locator duplicate, improve, and broaden human knowledge.
devices than with tracing techniques that depend on Machine learning, a branch of artificial intelligence,
electronic medical data. This maximize the utilization allows machines to learn tasks by identifying patterns
of time and money while significantly increasing the in data. Neural networks are adaptable mathematical
number of potentially susceptible individuals iden- models that can use a range of methods to express intri-
tified. Selling hospitals and payers on the usefulness cate relationships in big data sets. Artificial intelligence,

442
 Microbial infection disease diagnosis and treatment by artificial intelligence

particularly its variations like as deep learning and con- more difficult and prone to false negative results (Fig.1-
volutional neural networks (CNNs), is currently the most 2). The inherent delay in traditional microbiological
used machine learning technique. Data is sent to the detection can result in antibiotic resistance through
input layer, which uses a hidden multi-layer algorithm empirical therapy by letting diseases deteriorate [10].
to process it. The outcomes are displayed in the results. The early detection of pathogens and the development
Instead of being a straightforward neural network with of successful prevention measures depend on AI algo-
one or a few convolutional layers between the input rithms’ ability to quickly and accurately identify trends
and output layers, deep learning may be thought of as and abnormalities in large microbial datasets [11, 12].
a computational process with several hidden layers. The Artificial intelligence’s predictive modeling predicts
hidden layers can be piled endlessly to create a machine microbial activity based on historical data, which aids
with greater sensitivity and accuracy as processing in improving treatment approaches, anticipating illness
power increases [8]. outbreaks, and better understanding patterns in anti-
biotic resistance [13].

AIM
This study sought to investigate how AI can raise the STRUCTURE AND ROLE OF ARTIFICIAL
degree of individualized treatment and the precision INTELLIGENCE IN CLINICAL MEDICINE
and effectiveness of clinical diagnosis in light of the Artificial intelligence in healthcare can be separate into
potential obstacles to its clinical deployment. It was two collection depending connected how it works: vi-
based on a careful examination of existing literature sual and physical [14]. The term “physical AI” describes
and findings from recent studies. By providing medical devices that may help with and carry out a range of use-
professionals with an in-depth understanding of how AI ful functions, such as surgery and the deployment of ro-
can be used to diagnose and treat infectious diseases, bots in medical procedures. Virtual artificial intelligence
by working together to advance the use of AI to com- includes any program that can process, analyze, and
bat infectious diseases, and by providing patients with pass on with other inclination connected to a system
more accurate and efficient healthcare , this will not (Fig.3). More precisely, artificial intelligence computes
only be important in improving global public health. data and provides a deterministic response using two
methods. AI software may be able to make accurate
decisions about a patient’s health and treatment in
MATERIALS AND METHODS “real-time” thanks to machine learning (ML), which is the
capacity of an AI system to develop suitable algorithms
METHODOLOGY AND INTEGRATION OF THE that generate decisions and/or predictions based on the
SEARCH data generated [15]. This method, known as the “flow
Indexed databases, such as EMBASE, Scopus, and chart technique,” mimics how a doctor would compile
PubMed/Medline, were separately searched in English information from a patient’s medical history and clinical
only, without regard to time constraints. Cross-referenc- test results. AI programs can also use a more complex
ing of important articles led to additional references. type of flow chart.
This study reviews important clinical applications and
provides an overview of several Artificial intelligence
algorithms used in diagnosis of diseases caused by MONITORING AND IDENTIFYING
pathogenic microorganisms. EMERGENCIES
By gathering and examining data on risk factors, clini-
cal outcomes, and patterns of disease transmission, AI
REVIEW AND DISCUSSION can also be a helpful tool in case analysis. Healthcare
practitioners might use this to pinpoint high-risk
USING ARTIFICIAL INTELLIGENCE TO groups, track the transmission of illnesses, and antic-
DIAGNOSE MICROORGANISMS ipate any outbreaks. This tends to maximize resource
Every diagnostic method, from sample collection to use while improving early intervention tactics [16].
identification and susceptibility testing, poses chal- Thus, as has been emphasized throughout history,
lenges to traditional microbiology. Improper sample detection and management of disease outbreaks are
processing causes problems and can lead to incorrect critical. Conventional surveillance techniques require
conclusions [9]. The presence of antibiotics in clinics manual data collection, which eventually results in
makes the process of cultivating and isolating germs underreporting or delays in the reporting of infectious

443
Laith Abbas Al-Huseini et al.

Fig. 1. Flow chat of future

diagnostics microbial infec-
tion identification of diseas-
es by traditional methods
of detection and current
(modern methods of iden-
tification).

Fig. 2. Flow chat of future

diagnostics microbial infec-
tion identification of diseas-
es by Artificial Intelligence.

disease cases. AI-based surveillance systems, on the profession imagination, which is essential for diag-
other hand, automatically gather information from nosis. Profound eruditeness systems, a different kind
social media and medical records while evaluating of artificial intelligence, have demonstrated accuracy
real-time data streams to improve public health in analyzing medical pictures, including X-ray and
response and situational awareness [17]. At the ex- histopathology CT scans. All things considered, the
tremely least, machine learning-based alert systems application of AI in TDM may lead to improved patient
have been created that detect deviations in disease outcomes. Improve the precision and effectiveness of
rates or the ways infectious diseases are spread, alert- medical care delivery to lower medical expenses. It is
ing health authorities to potential outbreaks [18]. anticipated that AI will become more significant in
AI has shown great potential in the tract of learned TDM as it develops [19].

444
 Microbial infection disease diagnosis and treatment by artificial intelligence

Fig. 3. Structure and func-

tions of artificial intelligence
in clinical medicine.

RISKS, ETHICS, AND LEGAL ISSUES RELATED by utilizing multiple reliable AI algorithms. Artificial
TO AI IN MEDICAL FIELD intelligence in healthcare offers numerous benefits,
Developing AI technology for use in healthcare, safe including process simplification, increased productivity,
practices, services, and policies is costly and risky. It time and resource savings, support for research, and
is becoming more and more crucial to safeguard the a reduction in medical stress, despite concerns about
financial interests of AI and data-driven healthcare data privacy and security breaches. The impact of digital
advances [20]. Previously, vital signs such as blood technologies on healthcare supply chain stakeholders
pressure, heart rate and glucose levels could only be was assessed using an epistemological framework for
monitored by medical personnel [21], however, the ethical assessment that places a high priority on ethical
ongoing collecting of this data is now made possible awareness, transparency, and accountability [28].
by contemporary mobile applications. The ethical
issues surrounding the application of AI technology
must be addressed, particularly those pertaining to CUSTOMIZATION OF TREATMENT
patient autonomy, informed consent, and abuse of data AAI can provide creative answers for monitoring epi-
privacy and confidentiality [22]. The GDPR introduces demics and providing individualized care. Algorithms
comprehensive data protection legislation within the in microbial identification powered by artificial intelli-
EU, causing a shift in data protection globally, whereas gence have shown impressive accuracy and efficacy in
HIPAA primarily protects sensitive health information identifying pathogenic microorganisms from a variety
processed by lawful organizations [23-26]. The intro- of clinical samples [29]. These algorithms swiftly and
duction of AI into the healthcare system may distort accurately diagnose infections by analyzing massive
patient data and affect important medical examination databases of genomic, proteomic, and clinical data,
results. Cyber-attacks have increased [27]. Certain cyber enabling healthcare to create individualized treatment
threats can be identified and avoided with the use of programs [30]. Epidemic surveillance has been greatly
predictive algorithms. A comprehensive examination enhanced by the quick identification and analysis of
of cyber security and the cyber risk environment of trends in epidemiological data. AI systems can identify
healthcare systems is necessary to protect data pri- new epidemics, monitor the spread of illnesses, and
vacy and preserve system integrity [27]. It is possible identify possible hotspots by processing and analyzing
to mitigate the risk of relying solely on one solution real-time data from several origin, including medical

445
Laith Abbas Al-Huseini et al.

records, and environmental detector. During infectious and cost-effectiveness of clinical laboratory testing and
disease emergencies, this proactive approach helps disease detection. As AI is incorporated, the method for
containment and mitigation efforts by enabling prompt diagnosing microorganisms is changing. It makes it possi-
intervention measures. Essentially, artificial intelligence ble to identify pathogens quickly and accurately, identify
in microbial diagnosis and epidemic monitoring plays a antibiotic resistance early, and develop better diagnostic
critical role in protecting public health globally in addi- methods. AI is also crucial for drug research, outbreak detec-
tion to improving healthcare by optimizing treatment tion, early disease diagnosis, and individualized treatment.
approaches [31]. Consequently, there have been significant improvements
in healthcare results and public health benefits. But as AI
becomes more prevalent in medical decision-making,
CONCLUSIONS ethical concerns like patient privacy, algorithmic biases,
The methods for diagnosing microbial infectious diseases data security, transparency, accessibility, and human over-
have evolved from serological techniques to advanced sight must be addressed. Further improvements in illness
molecular approaches [32,33]. Today, AI has become a prevention and treatment are now acceptable due to the
powerful tool applicable across all fields of life. AI-driven development of AI in microbiological detection, which also
predictive analytics can improve the accuracy, efficiency, ensures ethical and equitable healthcare practices.

REFERENCES
1. Kandilci M, Yakıcı G, Kayar MB. Artificial Intelligence and Microbiology. Experimental and Applied Medical Science. 2024;5(2):119 – 128.
doi:10.46871/eams.1458704. DOI
2. Oh J, Makar M, Fusco C et al. A generalizable, data-driven approach to predict daily risk of Clostridium difficile infection at two large
academic health centers. Infect. Control Hosp. Epidemiol. 2018;39:425–433. doi: 10.1017/ice.2018.16. DOI
3. Tilton CS, Johnson SW. Development of a risk prediction model for hospital-onset Clostridium difficile infection in patients receiving
systemic antibiotics. Am. J. Infect. Control. 2019;47:280-284. doi: 10.1016/[Link].2018.08.021. DOI
4. Miller MB, Atrzadeh F, Burnham C-AD et al. Clinical utility of advanced microbiology testing tools. J Clin Microbiol. 2019;57(9):10-11282.
doi:10.1128/JCM.00495-19. DOI
5. Salazar BM, Balczewski EA, Ung CY, Zhu S. Neuroblastoma, a paradigm for big data science in pediatric oncology. Int J Mol Sci. 2016;18(1):37.
doi:10.3390/ijms18010037. DOI
6. Hamet P, Tremblay J. Artificial intelligence in medicine. Metabolism. 2017;69:S36-S40. doi:10.1016/[Link].2017.01.011. DOI
7. Abdi J, Al-Hindawi A, Ng T, Vizcaychipi MP. Scoping review on the use of socially assistive robot technology in elderly care. BMJ Open.
2018;8(2):e018815. doi:10.1136/bmjopen-2017-018815. DOI
8. Jartarkar SR. Artificial intelligence: Its role in dermatopathology. Indian J Dermatol Venereol Leprol. 2023;89(4): 549-552. doi: 10.25259/
IJDVL_725_2021. DOI
9. Franco-Duarte R, Cernáková L, Kadam S et al. Advances in chemical and biological methods to identify microorganisms – From past to
present. Microorganisms. 2019;7(5):130. doi: 10.3390/microorganisms7050130. DOI
10. Uddin TM, Chakraborty AJ, Khusro A et al. Antibiotic resistance in microbes: History, mechanisms, therapeutic strategies and future
prospects. J. Infect. Public Health. 2021;14:1750-1766. doi: 10.1016/[Link].2021.10.020. DOI
11. Agbehadji IE, Awuzie BO, Ngowi AB, Millham RC. Review of big data analytics, artificial intelligence and nature-inspired computing
models towards accurate detection of COVID-19 pandemic cases and contact tracing. Int. J. Environ. Res. Public Health. 2020;17:5330.
doi:10.3390/ijerph17155330. DOI
12. Rabaan AA, Alhumaid S, Al Mutair A et al. Application of artificial intelligence in combating high antimicrobial resistance rates. Antibiotics.
2022;11:784. doi:10.3390/antibiotics11060784. DOI
13. Hamet P, Tremblay J. Artificial Intelligence in Medicine. Metab. Clin. Exp. 2017;69:S36–S40. doi: 10.1016/[Link].2017.01.011. DOI
14. Krishnan G, Singh S, Pathania M et al. Artificial Intelligence in Clinical Medicine: Catalyzing a Sustainable Global Healthcare Paradigm.
Front. Artif. Intell. 2023;6:1227091. doi:10.3389/frai.2023.1227091. DOI
15. Beam AL, Kohane IS. Big Data and Machine Learning in Health Care. JAMA. 2018;319:1317-1318. doi: 10.1001/jama.2017.18391. DOI
16. Yang W, Olson DR, Shaman J. Forecasting Influenza Outbreaks in Boroughs and Neighborhoods of New York City. PLoS Comput. Biol.
2016;12:e1005201. doi:10.1371/[Link].1005201. DOI
17. Liu JYH, Rudd JA. Predicting drug adverse effects using a new Gastro-Intestinal Pacemaker Activity Drug Database (GIPADD). Sci Rep.
2023;13(1):6935. doi:10.1038/s41598-023-33655-5. DOI
18. Subramanian M, Wojtusciszyn A, Favre L et al. Precision medicine in the era of artificial intelligence: implications in chronic disease
management. J Transl Med. 2020;18(1):472. doi:10.1186/s12967-020-02658-5. DOI

446
 Microbial infection disease diagnosis and treatment by artificial intelligence

19. Gerke S, Minssen T, Cohen G. Ethical and legal challenges of artificial intelligence-driven healthcare. Artif Intell Healthc. 2020, pp.295–336.
doi:10.1016/b978-0-12-818438-7.00012-5. DOI
20. Cohen IG, Mello MM. HIPAA and protecting health information in the 21st Century. JAMA. 2018;320(3):231. doi:10.1001/jama.2018.5630.
DOI

21. Yuan B, Li J. The policy effect of the General Data Protection Regulation (GDPR) on the digital public health sector in the European Union:
an empirical investigation. Int J Environ Res Public Health. 2019;16(6):1070. doi:10.3390/ijerph16061070. DOI
22. Alotaibi S, Mehmood R, Katib I et al. A Big Data Analytics Tool for Healthcare symptoms and Diseases Detection using Twitter, Apache
Spark, and machine learning. Appl Sci. 2020;10:1398. doi:10.3390/ app10041398. DOI
23. Al-Mistarehi A-HM, Mijwil M, Filali Y et al. Artificial Intelligence Solutions for Health 4.0: Overcoming Challenges and Surveying
Applications. MJAIH. 2023. doi: 10.58496/MJAIH/2023/003. DOI
24. Radanliev P, De Roure D. Epistemological and bibliometric analysis of Ethics and Shared responsibility—health policy and IoT Systems.
Sustainability. 2021;13(15):8355. doi: 10.3390/su13158355. DOI
25. Radanliev P, De Roure D, Ani U, Carvalho G. The ethics of shared Covid-19 risks: an epistemological framework for ethical health technology
assessment of risk in vaccine supply chain infrastructures. Health Technol (Berl). 2021;11(5):1083–91. doi: 10.1007/s12553-021-00565-3.
DOI

26. Ransbotham S, Candelon F, Kiron D et al. The Cultural Benefits of Artificial Intelligence in the Enterprise. MIT Sloan Management Review and
Boston Consulting Group. 2021. [Link]
[Accessed 12 December 2024]
27. Rigby MJ. Ethical Dimensions of Using Artificial Intelligence in Health Care. AMA Journal of Ethics. 2019;21(2):121-124. doi: 10.1001/
amajethics.2019.121. DOI
28. Rutala WA, Weber DJ. Best practices for disinfection of noncritical environmental surfaces and equipment in health care facilities: A
bundle approach. American Journal of Infection Control. 2019;47:A96–A105. doi: 10.1016/[Link].2019.01.014. DOI
29. Bohr A, Memarzadeh K. The rise of artificial intelligence in healthcare applications. Artificial Intelligence in Healthcare. Elsevier, Amsterdam,
the Netherlands. 2020. doi:10.1016/B978-0-12-818438-7.00002-2. DOI
30. Vora LK, Gholap AD, Jetha K et al. Artificial intelligence in pharmaceutical technology and drug delivery design. Pharmaceutics.
2023;15:1916. doi: 10.3390/pharmaceutics15071916. DOI
31. Agrebi S, Larbi A. Use of artificial intelligence in infectious diseases. Artificial Intelligence in Precision Health. Elsevier, Amsterdam, the
Netherlands. 2020. doi: 10.1016/B978-0-12-817133-2.00018-5. DOI

CONFLICT OF INTEREST
The Authors declare no conflict of interest

CORRESPONDING AUTHOR
Laith Abbas Al-Huseini
Warith Al-Anbiyaa University
Karbala, Baghdad Road, Karbala, Iraq
e-mail: [Link]@[Link]

ORCID AND CONTRIBUTIONSHIP

Laith Abbas Al-Huseini: 0000-0002-5170-1865
Nisreen Jawad Kadhim: 0000-0002-7255-8383
Mohammed Salih Mahdi: 0000-0003-4825-6892
Raed H. Ogaili: 0000-0001-7092-4936
Orooba Al-hammood: 0000-0002-1534-3546

– Work concept and design, – Data collection and analysis, – Responsibility for statistical analysis, – Writing the article, – Critical review, – Final approval of the article

RECEIVED: 02.12.2024
ACCEPTED: 06.01.2025 C R E AT I V E C O M M O N S 4 . 0

447