Open Access Review
Article DOI: 10.7759/cureus.49366
Applications of Artificial Intelligence in Microbial
Diagnosis
Received 10/03/2023
Yogendra P. Shelke 1 , Ankit K. Badge 2 , Nandkishor J. Bankar 3
Review began 11/07/2023
Review ended 11/16/2023 1. Microbiology, Bhaktshreshtha Kamalakarpant Laxmanrao Walawalkar Rural Medical College, Ratnagiri, IND 2.
Published 11/24/2023
Microbiology, Datta Meghe Medical College, Datta Meghe Institute of Higher Education and Research (Deemed to Be
© Copyright 2023 University), Wardha, IND 3. Microbiology, Jawaharlal Nehru Medical College, Datta Meghe Institute of Higher
Shelke et al. This is an open access article Education and Research (Deemed to Be University), Wardha, IND
distributed under the terms of the Creative
Commons Attribution License CC-BY 4.0.,
Corresponding author: Nandkishor J. Bankar, drbankarnj28@[Link]
which permits unrestricted use, distribution,
and reproduction in any medium, provided
the original author and source are credited.
Abstract
The diagnosis is an important factor in healthcare care, and it is essential to identify microorganisms that
cause infections and diseases. The application of artificial intelligence (AI) systems can improve disease
management, drug development, antibiotic resistance prediction, and epidemiological monitoring in the
field of microbial diagnosis. AI systems can quickly and accurately detect infections, including new and
drug-resistant strains, and enable early detection of antibiotic resistance and improved diagnostic
techniques. The application of AI in bacterial diagnosis focuses on the speed, precision, and identification of
pathogens and the ability to predict antibiotic resistance.
Categories: Other
Keywords: pathogen identification, epidemiological monitoring, antibiotic resistance prediction, artificial
intelligence in healthcare, microbial diagnosis
Introduction And Background
Microbial diagnosis entails the identification of microorganisms through techniques such as culture,
molecular analysis, and imaging, which constitute a pivotal domain within the realm of healthcare. It starts
with appropriate sample collection and runs into several problems with conventional procedures, including
sample handling, difficulty in culture, incorrect identification, and antimicrobial susceptibility testing
difficulties. These traditional methods require manpower, and treatment is often delayed [1]. Artificial
intelligence (AI) has revolutionized the field of microbial diagnostics by providing more precise and current
findings. AI analyzes data, pattern recognition, and diagnostic processes faster. It is essential for early
identification of the disease, advancement of treatment, custom treatment, and epidemic monitoring.
Advanced data sets are analyzed by AI-driven algorithms to detect infections rapidly, anticipate disease
outbreaks, and improve treatment approaches and outcomes [2]. The use of AI in microbial diagnosis raises
concerns about ethics. Essential ethical considerations include protecting patient privacy, addressing
algorithmic biases, maintaining data security, promoting transparency, and ensuring equal treatment. To
maintain patient safety, personnel surveillance is still necessary [3]. As policies and ethical regulations for AI
are implemented in healthcare, it can play a crucial role in providing precise, individualized diagnoses while
ensuring patient rights and access to medical devices [4]. This review aims to analyze the use of AI in
microbial diagnosis.
Review
Microbial diagnosis
Identifying microorganisms through microbial diagnosis is vital to healthcare as it helps determine the
causative agents of infections and diseases. The techniques employed for detection include cultivating
bacteria and fungi on appropriate growth media, isolating viruses through cell culture, and characterizing
the infectious agent through biochemical, antigenic, or genetic means [5]. Alternatively, infectious diseases
may also be discerned by the detection of a specific immune response, typically in the form of antibodies
that develop over the course of the illness. In some instances, the visualization of the infectious agent
within infected tissue can furnish a diagnosis based on distinctive morphological attributes or, at the very
least, aid in categorizing the type of organism responsible for the infection [6]. Conventional methodologies
employed for this purpose are well established but recognized for their protracted timelines and demanding
labor requirements. These conventional techniques encompass the utilization of culture media and labor-
intensive biochemical tests. In contrast, contemporary approaches necessitate swift, cost-effective
methodologies for the initial categorization of bacterial and fungal isolates. Moreover, modern analytical
methods require comprehensive microbial profiling, often relying on molecular techniques, such as
polymerase chain reaction (PCR), targeting the 16S ribosomal RNA gene. These findings are crucial in
developing effective therapeutic strategies [1]. Diagnosing microorganisms involves multiple steps,
beginning with sample collection, transport, and storage [7]. This is a crucial step in the diagnostic process,
as the accuracy of subsequent test results depends on the proper collection and handling of clinical samples
How to cite this article
Shelke Y P, Badge A K, Bankar N J (November 24, 2023) Applications of Artificial Intelligence in Microbial Diagnosis. Cureus 15(11): e49366. DOI
10.7759/cureus.49366
[8].
Challenges in traditional microbial diagnosis
Microbial diagnosis, a fundamental aspect of modern medicine and microbiology, faces challenges that span
the entire diagnostic process. Sample collection and transport represent a critical initial challenge [9]. The
process begins with the collection of clinical specimens. However, ensuring the correct and timely collection
and transportation of clinical samples to the laboratory poses a formidable challenge. Improper handling,
storage, and transport delays can increase the risk of the viability and integrity of microorganisms within the
sample, leading to inaccurate diagnostic results [10]. Subsequently, the culture and isolation of
microorganisms are considered a primary traditional diagnostic method. This process takes a long time for
culture results. Improper cultivation of microbes raises the possibility of false negative results. The excessive
use of antibiotics in clinical practice can further affect the growth and isolation of specific organisms [11].
Accurate identification and classification of microbial species represent another significant challenge.
Traditional methods, including biochemical tests and microscopy, may not consistently detect the correct
identification due to misleading morphological characteristics or atypical behaviors exhibited by certain
microorganisms [12]. Determining the susceptibility of bacterial isolates to antibiotics in treatment
selection is also challenging. Traditional susceptibility testing techniques, such as the disk diffusion method,
are time-consuming and sometimes need to accurately predict the response of the infecting strain to
antibiotics, leading to suboptimal treatment choices and potential therapeutic complications [13].
Traditional methods often require a team of highly qualified personnel, specialized equipment, and
significant resources to diagnose medical conditions. There is an increased chance of human error in
settings with limited resources due to the dependence on skilled professionals. As a result, it is crucial to
develop new and user-friendly diagnostic methods [14].
Traditional microbial diagnosis often causes a delay in the initial phase of therapy, allowing diseases to
progress uncontrolled due to a delay in results [15]. Empirical therapy increases antibiotic resistance, but
traditional methods detect microorganisms, leading to misdiagnosing emerging pathogens [16].
Conventional diagnosis is fraught with the possibility of cross-contamination and false positives, making it
more challenging. As traditionally performed, microbial diagnosis may not provide real-time data for
effective epidemiological surveillance due to the risk of cross-contamination. This could lead to false-
positive results from serological examinations [17]. The lack of standardized procedures and quality
measures in diagnostic laboratories may result in inconsistent results that are less accurate and consistent
[18]. Challenges in microbial diagnosis are depicted in Table 1.
2023 Shelke et al. Cureus 15(11): e49366. DOI 10.7759/cureus.49366 2 of 8
Challenge/issue Description
Collection and transportation of clinical samples to the laboratory can be error-prone, affecting the viability and
Sample collection and transport
integrity of microorganisms and leading to inaccurate results [10].
Traditional culture methods are time-consuming, may yield false negatives, and can be impacted by the overuse
Culture and isolation
of antibiotics [11].
Correct identification of microbial species can be challenging due to the misleading morphological characteristics
Identification and classification
and atypical behaviors of certain microorganisms [12].
Traditional susceptibility testing techniques are slow and sometimes inaccurate, leading to suboptimal treatment
Antibiotic susceptibility testing
choices and potential complications [13].
Traditional methods rely on highly qualified personnel, specialized equipment, and significant resources, making
Dependence on skilled personnel
them error-prone in settings with limited resources [14].
Traditional microbial diagnosis can cause delays in treatment initiation, allowing diseases to progress and
Delay in initial therapy
increasing the risk of antibiotic resistance [15].
The delay in diagnosis may lead to empirical therapy, which can promote antibiotic resistance and misdiagnose
Empirical therapy
emerging pathogens [16].
Cross-contamination and false Conventional methods carry a risk of cross-contamination and false-positive results, further complicating the
positives diagnostic process [17].
Lack of real-time epidemiological Traditional diagnosis may not provide real-time data for effective epidemiological surveillance due to the risk of
surveillance cross-contamination and false positives [17].
Lack of standardized procedures Inconsistent results and accuracy issues may arise due to the absence of standardized procedures and quality
and quality measures measures in diagnostic laboratories [18].
TABLE 1: Challenges in microbial diagnosis by traditional methods.
The role of AI in microbial diagnosis
The application of AI in microbial identification and analysis has revolutionized the field, leading to more
rapid and reliable results compared to conventional methods [19]. AI algorithms are capable of analyzing
genomic data, aiding scientists and clinicians in identifying pathogens, predicting antibiotic resistance, and
even discovering new microbial species. Furthermore, machine learning models can increase the speed and
accuracy of microbial diagnosis by quickly analyzing complex data patterns [4]. The use of AI in microbe
diagnosis has become a multifaceted and essential tool that encompasses pattern recognition, prediction
modeling, and enhancement of microbe analysis efficiency. AI-powered algorithms have revolutionized the
field by examining vast datasets of microbial information and identifying patterns and irregularities that
would be challenging for human analysts to detect quickly and accurately. This capacity for pattern
recognition is particularly critical in the early detection of infectious diseases, where rapid identification of
viral species and their transmission patterns can inform effective containment strategies [2,4]. AI plays a
crucial role in predictive modeling, using historical data to forecast microbial behavior and guide future
decision-making. This predictive power is indispensable in foreseeing disease outbreaks, comprehending
antibiotic resistance trends, and streamlining treatment protocols [20]. One of the best examples is that
machine learning models, such as deoxyribonucleic acid (DNA) sequencer, can analyze the genomic
sequences of bacteria and viruses to predict their propensity for mutations and resistance to specific drugs,
guiding clinicians in selecting the most effective treatment options [21]. AI-powered automation speeds up
processes such as sample processing, image analysis, and data interpretation. This not only shortens the
diagnostic turnaround time but also allows healthcare professionals to concentrate on the most challenging
aspects of patient care [19,22].
Early disease detection
Early Pathogen Detection
AI-powered algorithms have proven to be invaluable in quickly and effectively detecting microbial
pathogens in clinical samples. These algorithms are trained to recognize specific patterns or genetic markers
associated with various pathogens. This rapid and accurate detection of pathogens allows for immediate
therapeutic interventions, significantly reducing the risk of infection growth [23].
Disease Outbreak Prediction and Hotspot Identification
2023 Shelke et al. Cureus 15(11): e49366. DOI 10.7759/cureus.49366 3 of 8
AI plays a crucial role in predicting disease outbreaks and identifying hotspots. By analyzing a wealth of data
sources, including medical records and environmental data, AI algorithms can identify trends and patterns
indicative of potential outbreaks. This early detection enables public health authorities to implement
targeted preventive measures and allocate resources where they are most needed [24].
Early Warning Systems
AI is integrated into early warning systems that continuously monitor data from diverse sources. These
systems are designed to detect unusual patterns of microbial infections that may signal an emerging health
threat. By scrutinizing data in real time, AI-driven early warning systems facilitate prompt investigation and
intervention, helping to prevent the spread of diseases and mitigate their impact [25].
Real-Time Monitoring of Microbial Populations
The ability of AI to analyze real-time data is instrumental in monitoring microbial populations within
healthcare facilities. By continuously tracking and analyzing changes in microbial populations, AI can
promptly identify deviations from baseline patterns. This early detection capability allows for swift
responses to potential health risks, such as hospital-acquired infections, ensuring patient safety and
efficient healthcare delivery [25].
Drug discovery
AI-assisted microbial detection is changing not just clinical procedures but also the field of drug research to
discover prospective therapeutic targets, improve the drug development process, and improve the search for
antimicrobial agents to prevent a wide range of infections [26]. AI significantly affects the identification of
targets since it analyzes microbial genomes, proteomes, and metabolic pathways. Machine learning models
accelerate drug development by predicting affinities for compound microbial target binding, accelerating the
selection of potential drugs for experimental validation [27]. AI can help improve drug repurposing by
utilizing knowledge about authorized medications and their modes of action. By analyzing data, AI can
identify recently approved medicines that can be repurposed for treating microbial diseases, potentially
avoiding the time-consuming drug development process [28]. The impact of AI in predicting
pharmacokinetic and pharmacodynamic characteristics is significant. AI-driven modeling reduces adverse
effects, optimizes dosage, and ensures safety, effectiveness, and compatibility for clinical development [29].
To predict potential resistance mechanisms, AI algorithms analyze microbial genomic data. These data
enable developers to create treatments that are less likely to cause resistance, promoting the development of
more effective and durable antimicrobial drugs [4]. Various applications of AI in drug discovery and
treatment are shown in Table 2.
Application Description
Prospective AI aids in the discovery of potential therapeutic targets by analyzing microbial genomes, proteomes, and metabolic pathways.
therapeutic target This accelerates the drug development process by predicting affinities for compound-microbial target binding, expediting the
identification selection of potential drugs for experimental validation [26,27].
AI leverages knowledge about authorized medications and their mechanisms of action to identify approved drugs that can be
Drug repurposing
repurposed for treating microbial diseases. This approach can save time by avoiding lengthy drug development processes [28].
Pharmacokinetic
and AI plays a significant role in predicting pharmacokinetic and pharmacodynamic characteristics of drugs. AI-driven modeling
pharmacodynamic reduces adverse effects; optimizes dosages; and ensures safety, effectiveness, and compatibility for clinical development [29].
modeling
Predicting AI algorithms analyze microbial genomic data to predict potential resistance mechanisms. This data-driven approach helps in
resistance developing treatments that are less likely to induce resistance, promoting the creation of more effective and durable antimicrobial
mechanisms drugs [4].
TABLE 2: Application of AI in drug discovery and treatment.
AI: Artificial intelligence.
Treatment personalization
AI can offer innovative solutions for personalized treatment and epidemic monitoring. In microbial
diagnosis, AI-powered algorithms have shown exceptional accuracy and efficiency in identifying pathogenic
microorganisms from various clinical samples. These algorithms analyze large datasets of genetic,
proteomic, and clinical information to diagnose infections quickly and precisely, allowing healthcare
2023 Shelke et al. Cureus 15(11): e49366. DOI 10.7759/cureus.49366 4 of 8
providers to develop tailored treatment plans [30]. The ability to rapidly detect and analyze patterns in
epidemiological data has significantly improved epidemic monitoring. By processing and interpreting real-
time data from various sources, such as social media, healthcare records, and environmental sensors, AI
systems can recognize emerging outbreaks, track the spread of diseases, and predict potential hotspots. This
proactive approach allows for timely intervention measures, facilitating containment and mitigation efforts
during infectious disease crises [31]. In essence, AI in microbial diagnosis and epidemic monitoring not only
advances healthcare by optimizing treatment strategies but also plays a pivotal role in safeguarding public
health on a global scale [2].
Epidemic monitoring
AI has proven to be an effective tool in the monitoring of epidemics. Its wide-ranging applications in this
field are transformative and multifaceted. Additionally, by analyzing various factors, including climate,
population density, and travel patterns, machine learning models may predict disease breakout trends that
promote health authorities with the development of prevention intervention techniques [32]. In real time, AI
can analyze clinical and epidemiological data to aid contact tracking and assess the effectiveness of
containment measures. AI-assisted microbial detection is revolutionizing the identification and
management of epidemics, ultimately saving lives and decreasing the impact of infectious diseases on
global health [33]. Table 3 presents the advantages and disadvantages of AI in microbial diagnosis
[2,15,19,30,34,35].
Advantages Disadvantages
AI systems may be costly to purchase and install, which could
Rapid analysis of microbiological data enables fast diagnosis, improving accuracy
pose difficulties for smaller healthcare facilities and those with
and minimizing false positives for better patient results.
limited finances.
AI learning and training require unbiased, high-quality data, as
AI systems can identify intricate details and patterns that humans may miss, leading
incomplete or biased data may lead to incorrect diagnoses and
to more accurate identification of pathogens and their characteristics.
treatment suggestions.
AI decision-making processes can be difficult to understand,
AI can assist academics in making justifiable decisions by identifying hidden patterns
which may lead healthcare professionals to distrust AI
for valuable scientific discoveries.
recommendations.
Personalized treatments utilizing patient data can enhance outcomes and minimize AI systems may provide inaccurate suggestions due to the
adverse effects. biases they acquire from the training data.
Qualified experts are necessary for monitoring AI operations
AI reduces manual labor requirements, resulting in labor savings on expenses.
and analyzing results. Highly qualified AI experts are abundant
Diagnosis may be lower in cost when it relies less on costly laboratory equipment.
in certain regions.
Healthcare practitioners are refusing to adopt AI due to job
AI systems are constantly evolving to stay ahead of novel diseases.
displacement fear.
Remote deployment of AI-powered diagnostics increases access to healthcare,
Ethical and privacy issues arise in the handling of patient data
reaching populations with limited resources and spanning geographic barriers. AI is
used for diagnosis purposes.
particularly useful in times of epidemics.
AI minimizes human errors, resulting in consistent and verifiable outcomes, making The lack of internet access in resource-limited regions may
treatments safer and more successful. hinder the application and maintenance of AI systems.
TABLE 3: Advantages and disadvantages of AI in microbial diagnosis.
AI: Artificial intelligence.
Ethical considerations
The integration of AI into microbial diagnosis is a rapid advancement that presents unparalleled
opportunities to improve healthcare outcomes. Healthcare data can be gathered and stored online by social
media, genetic testing, and bioinformatic companies. These data can be hacked and used for unethical
purposes [36]. These ethical issues encompass a wide range of topics, including patient privacy, algorithmic
biases, data security, accessibility, and overall responsibility of healthcare providers [37].
Patient Privacy and Informed Consent
Ensuring patient privacy is one of the primary ethical concerns of using AI systems. Since these systems rely
2023 Shelke et al. Cureus 15(11): e49366. DOI 10.7759/cureus.49366 5 of 8
on vast datasets that may contain sensitive health information, it is crucial to protect patient privacy [38].
Ethical guidelines require informed consent from patients before collecting and using their data for AI-
driven diagnostics. It is essential to balance anonymizing data to protect patient identities and retaining
clinical relevance to ensure ethical use of patient information [39].
Algorithmic Biases and Fairness
AI may be associated with structural barriers like language and cultural differences or situational challenges
and may influence the inclusion of a particular patient in the data. Automated customer service or
scheduling software may cause systematic disparities. Then, natural language processing may be associated
with gender and racial biases. Consequently, it is essential that developers and healthcare organizations put
robust procedures for bias recognition and management [40].
Data Security and Cybersecurity
There are new data security concerns due to the increased reliance on connected systems and cloud-based
data storage. Patient data must be protected against cyberattacks, and unauthorized access is ethically
required. Healthcare organizations and AI developers must invest in adequate cybersecurity protections,
encryption procedures, and compliance with privacy regulations to protect the confidentiality and integrity
of patient information [41].
Transparency
Clinicians and patients must understand the way AI-powered diagnostic decisions work. The advancement of
transparent AI models that can provide quick justifications for their predictions is encouraged by ethical
standards. As a result, AI systems are more trusted, and healthcare professionals can confidently act on AI
advice [42].
Accessibility and Equity
It is morally required to ensure appropriate access to AI-powered diagnostic tools. Healthcare organizations
should work to close the technological gap and give underprivileged communities access to innovative AI
diagnosis. To promote integration and appropriate access to healthcare, AI-driven healthcare solutions must
additionally keep people with disabilities [3].
Human Oversight and Accountability
AI has the potential to improve the accuracy of diagnoses, but it should continue the role of healthcare
personnel. Maintaining a balance between AI-driven automation and human intelligence is necessary for
ethical practice and patient safety. Healthcare providers are responsible for patient care. AI should be viewed
as a tool that supports and improves medical opinion rather than replacing it [19].
The future of AI in microbial diagnosis
AI-powered diagnostic tools will have a significant impact as machine learning and computational
capabilities improve. The development of AI systems has transformed disease management and public
health responses by quickly identifying infections, including novel and drug-resistant strains. Individuals
will eventually be able to monitor their health and identify microbial diseases in real time [43]. The role in
vaccine development, antimicrobial resistance, and epidemiological surveillance will continue to expand,
enhancing our ability to respond to infectious diseases effectively [44]. As ethical considerations and
regulatory frameworks continue to develop, the use of AI in microbial diagnosis is expected to become a
vital component in the significant transformation of the future of healthcare by providing personalized and
accurate diagnostic solutions, ensuring patient privacy protection and equitable access to innovative
healthcare technologies [45].
Conclusions
The technique for microbial diagnosis is evolving as an outcome of the integration of AI. It enables rapid and
accurate pathogen detection, early detection of antibiotic resistance, and improved diagnostic techniques.
Additionally, AI is essential for early diagnosis of diseases, drug development, personalized treatment, and
outbreak detection. As a result, public health benefits and healthcare outcomes have improved considerably.
However, as AI becomes more active in medical decision-making, ethical concerns such as patient
confidentiality, algorithmic biases, data security, transparency, accessibility, and human supervision must
be addressed. Even further improvements in disease treatment and prevention are acceptable in the future
with the advancement of AI in microbial diagnosis, which also ensures ethical and just healthcare practices.
Additional Information
2023 Shelke et al. Cureus 15(11): e49366. DOI 10.7759/cureus.49366 6 of 8
Author Contributions
All authors have reviewed the final version to be published and agreed to be accountable for all aspects of the
work.
Concept and design: Nandkishor J. Bankar, Ankit K. Badge
Acquisition, analysis, or interpretation of data: Nandkishor J. Bankar, Ankit K. Badge, Yogendra P.
Shelke
Critical review of the manuscript for important intellectual content: Nandkishor J. Bankar, Yogendra
P. Shelke
Supervision: Nandkishor J. Bankar, Yogendra P. Shelke
Drafting of the manuscript: Ankit K. Badge
Disclosures
Conflicts of interest: In compliance with the ICMJE uniform disclosure form, all authors declare the
following: Payment/services info: All authors have declared that no financial support was received from
any organization for the submitted work. Financial relationships: All authors have declared that they have
no financial relationships at present or within the previous three years with any organizations that might
have an interest in the submitted work. Other relationships: All authors have declared that there are no
other relationships or activities that could appear to have influenced the submitted work.
References
1. Franco-Duarte R, Černáková L, Kadam S, et al.: Advances in chemical and biological methods to identify
microorganisms-from past to present. Microorganisms. 2019, 7:130. 10.3390/microorganisms7050130
2. Bohr A, Memarzadeh K: The rise of artificial intelligence in healthcare applications . Artificial Intelligence in
Healthcare. Elsevier, Amsterdam, The Netherlands; 2020. 25-60. 10.1016/B978-0-12-818438-7.00002-2
3. Naik N, Hameed BM, Shetty DK, et al.: Legal and ethical consideration in artificial intelligence in
healthcare: who takes responsibility?. Front Surg. 2022, 9:862322. 10.3389/fsurg.2022.862322
4. Ali T, Ahmed S, Aslam M: Artificial intelligence for antimicrobial resistance prediction: Challenges and
opportunities towards practical implementation. Antibiotics (Basel). 2023, 12:523.
10.3390/antibiotics12030523
5. Buchan BW, Ledeboer NA: Emerging technologies for the clinical microbiology laboratory . Clin Microbiol
Rev. 2014, 27:783-822. 10.1128/CMR.00003-14
6. Walker DH: Principles of Diagnosis of Infectious Diseases . Pathobiology of Human Disease. Elsevier,
Amsterdam, The Netherlands; 2014. 222-5. 10.1016/B978-0-12-386456-7.01713-5
7. Gori E, Callea E, Alberani F, Orlando L: Microbial monitoring and methods of sample collection: a GITMO
survey (Gruppo Trapianto di Midollo Osseo). ecancermedicalscience. 2014, 8:421. 10.3332/ecancer.2014.421
8. Baron EJ, Miller JM, Weinstein MP, et al.: A guide to utilization of the microbiology laboratory for diagnosis
of infectious diseases: 2013 recommendations by the Infectious Diseases Society of America (IDSA) and the
American Society for Microbiology (ASM). Clin Infect Dis. 2013, 57:e22-e121. 10.1093/cid/cit278
9. Rodrigues CM, Groves H: Community-acquired pneumonia in children: the challenges of microbiological
diagnosis. J Clin Microbiol. 2018, 56:e01318-17. 10.1128/JCM.01318-17
10. Shrestha LB, Pokharel K: Standard operating procedure for specimen collection, packaging and transport for
diagnosis of SARS-COV-2. JNMA J Nepal Med Assoc. 2020, 58:627-9. 10.31729/jnma.5260
11. Khan ZA, Siddiqui MF, Park S: Current and emerging methods of antibiotic susceptibility testing .
Diagnostics (Basel). 2019, 9:49. 10.3390/diagnostics9020049
12. Zhang J, Li C, Rahaman MM, et al.: A comprehensive review of image analysis methods for microorganism
counting: from classical image processing to deep learning approaches. Artif Intell Rev. 2022, 55:2875-944.
10.1007/s10462-021-10082-4
13. Gajic I, Kabic J, Kekic D, et al.: Antimicrobial susceptibility testing: A comprehensive review of currently
used methods. Antibiotics (Basel). 2022, 11:427. 10.3390/antibiotics11040427
14. Parsons LM, Somoskövi A, Gutierrez C, et al.: Laboratory diagnosis of tuberculosis in resource-poor
countries: challenges and opportunities. Clin Microbiol Rev. 2011, 24:314-50. 10.1128/CMR.00059-10
15. Peri AM, Stewart A, Hume A, Irwin A, Harris PN: New microbiological techniques for the diagnosis of
bacterial infections and sepsis in ICU including point of care. Curr Infect Dis Rep. 2021, 23:12.
10.1007/s11908-021-00755-0
16. Ventola CL: The antibiotic resistance crisis: part 1: causes and threats . P T. 2015, 40:277-83.
17. Ruddy M, McHugh TD, Dale JW, et al.: Estimation of the rate of unrecognized cross-contamination with
Mycobacterium tuberculosis in London microbiology laboratories. J Clin Microbiol. 2002, 40:4100-4.
10.1128/JCM.40.11.4100-4104.2002
18. Agarwal R: Quality-improvement measures as effective ways of preventing laboratory errors . Lab Med. 2014,
45:80-8. 10.1309/LMD0YIFPTOWZONAD
19. Davenport T, Kalakota R: The potential for artificial intelligence in healthcare . Future Healthc J. 2019, 6:94-
8. 10.7861/futurehosp.6-2-94
20. Rabaan AA, Alhumaid S, Mutair AA, et al.: Application of artificial intelligence in combating high
antimicrobial resistance rates. Antibiotics (Basel). 2022, 11:784. 10.3390/antibiotics11060784
2023 Shelke et al. Cureus 15(11): e49366. DOI 10.7759/cureus.49366 7 of 8
21. Májek P, Lüftinger L, Beisken S, Rattei T, Materna A: Genome-wide mutation scoring for machine-learning-
based antimicrobial resistance prediction. Int J Mol Sci. 2021, 22:13049. 10.3390/ijms222313049
22. Behara K, Bhero E, Agee JT, Gonela V: Artificial intelligence in medical diagnostics: a review from a South
African context. Sci Afr. 2022, 17:e01360. 10.1016/[Link].2022.e01360
23. Goodswen SJ, Barratt JL, Kennedy PJ, Kaufer A, Calarco L, Ellis JT: Machine learning and applications in
microbiology. FEMS Microbiol Rev. 2021, 45:fuab015. 10.1093/femsre/fuab015
24. Zeng D, Cao Z, Neill DB: Artificial intelligence-enabled public health surveillance—from local detection to
global epidemic monitoring and control. Artificial Intelligence in Medicine. Elsevier, Amsterdam, The
Netherlands; 2020. 437-53. 10.1016/B978-0-12-821259-2.00022-3
25. Visibelli A, Roncaglia B, Spiga O, Santucci A: The impact of artificial intelligence in the odyssey of rare
diseases. Biomedicines. 2023, 11:887. 10.3390/biomedicines11030887
26. Paul D, Sanap G, Shenoy S, Kalyane D, Kalia K, Tekade RK: Artificial intelligence in drug discovery and
development. Drug Discov Today. 2021, 26:80-93. 10.1016/[Link].2020.10.010
27. Qureshi R, Irfan M, Gondal TM, et al.: AI in drug discovery and its clinical relevance . Heliyon. 2023,
9:e17575. 10.1016/[Link].2023.e17575
28. Yin Z, Wong STC: Artificial intelligence unifies knowledge and actions in drug repositioning . Emerg Top Life
Sci. 2021, 5:803-13. 10.1042/ETLS20210223
29. Vora LK, Gholap AD, Jetha K, Thakur RR, Solanki HK, Chavda VP: Artificial intelligence in pharmaceutical
technology and drug delivery design. Pharmaceutics. 2023, 15:1916. 10.3390/pharmaceutics15071916
30. Agrebi S, Larbi A: Use of artificial intelligence in infectious diseases . Artificial Intelligence in Precision
Health. Elsevier, Amsterdam, The Netherlands; 2020. 415-38. 10.1016/B978-0-12-817133-2.00018-5
31. Thomas LB, Mastorides SM, Viswanadhan NA, Jakey CE, Borkowski AA: Artificial intelligence: review of
current and future applications in medicine. Fed Pract. 2021, 38:527-38. 10.12788/fp.0174
32. Yang H, Nguyen T-N, Chuang T-W: An integrative explainable artificial intelligence approach to analyze
fine-scale land-cover and land-use factors associated with spatial distributions of place of residence of
reported dengue cases. Trop Med Infect Dis. 2023, 8:238. 10.3390/tropicalmed8040238
33. Kaur I, Behl T, Aleya L, Rahman H, Kumar A, Arora S, Bulbul IJ: Artificial intelligence as a fundamental tool
in management of infectious diseases and its current implementation in COVID-19 pandemic. Environ Sci
Pollut Res Int. 2021, 28:40515-32. 10.1007/s11356-021-13823-8
34. Norori N, Hu Q, Aellen FM, Faraci FD, Tzovara A: Addressing bias in big data and AI for health care: a call
for open science. Patterns (N Y). 2021, 2:100347. 10.1016/[Link].2021.100347
35. Quinn TP, Senadeera M, Jacobs S, Coghlan S, Le V: Trust and medical AI: the challenges we face and the
expertise needed to overcome them. J Am Med Inform Assoc. 2021, 28:890-4. 10.1093/jamia/ocaa268
36. Farhud DD, Zokaei S: Ethical issues of artificial intelligence in medicine and healthcare . Iran J Public
Health. 2021, 50:i-v. 10.18502/ijph.v50i11.7600
37. Jeyaraman M, Balaji S, Jeyaraman N, Yadav S: Unraveling the ethical enigma: Artificial intelligence in
healthcare. Cureus. 2023, 15:e43262. 10.7759/cureus.43262
38. Murdoch B: Privacy and artificial intelligence: challenges for protecting health information in a new era .
BMC Med Ethics. 2021, 22:122. 10.1186/s12910-021-00687-3
39. Padmapriya ST, Parthasarathy S: Ethical data collection for medical image analysis: a structured approach .
Asian Bioeth Rev. 2023, 1-14. 10.1007/s41649-023-00250-9
40. Agarwal R, Bjarnadottir M, Rhue L, Dugas M, Crowley K, Clark J, Gao G: Addressing algorithmic bias and the
perpetuation of health inequities: an AI bias aware framework. Health Policy Technol. 2023, 12:100702.
10.1016/[Link].2022.100702
41. Javaid M, Haleem A, Singh RP, Suman R: Towards insighting cybersecurity for healthcare domains: a
comprehensive review of recent practices and trends. Cyber Secur Appl. 2023, 1:100016.
10.1016/[Link].2023.100016
42. Johnson KB, Wei WQ, Weeraratne D, et al.: Precision medicine, AI, and the future of personalized health
care. Clin Transl Sci. 2021, 14:86-93. 10.1111/cts.12884
43. Kumar Y, Koul A, Singla R, Ijaz MF: Artificial intelligence in disease diagnosis: a systematic literature
review, synthesizing framework and future research agenda. J Ambient Intell Humaniz Comput. 2023,
14:8459-86. 10.1007/s12652-021-03612-z
44. Arora G, Joshi J, Mandal RS, Shrivastava N, Virmani R, Sethi T: Artificial intelligence in surveillance,
diagnosis, drug discovery and vaccine development against COVID-19. Pathogens. 2021, 10:1048.
10.3390/pathogens10081048
45. Gerke S, Minssen T, Cohen G: Ethical and legal challenges of artificial intelligence-driven healthcare .
Artificial Intelligence in Healthcare. Elsevier, Amsterdam, The Netherlands; 2020. 295-336. 10.1016/B978-0-
12-818438-7.00012-5
2023 Shelke et al. Cureus 15(11): e49366. DOI 10.7759/cureus.49366 8 of 8