Accuracy of AI-facilitated data and diagnoses is also a concern . As Marra , et al . ( 2023 ) confirm , “ In medical practice , diagnoses commonly lack a definitive confirmatory test , relying instead on clinicians reaching a diagnostic consensus from the clinical presentation and available laboratory analyses . Although AI is valuable in objectively diagnosing conditions with clear numerical indicators , determining conditions like ventilator-associated pneumonia is more complex . Assessing the accuracy of AI is challenging because clinical diagnosis often involves interpreting imprecise and nonnumerical data , with no definitive tests available .” They add that “ Researchers should be cautious about overreliance on AI language models and instead cultivate their own expertise , conduct through literature reviews , and engage in scholarly discourse . Scientific originality and transparency must prevail . Although the AI language models can provide a quick response , it lacks the ability to engage in meaningful discussions , consider alternative viewpoints , or evaluate the quality and validity of sources .”
Marra , et al . ( 2023 ) acknowledge what some critics of AI have characterized as AI ’ s potential to supersede human oversight , noting that “ the more information we feed it , the more we help to refine it and fuel our ‘ enemy ’ … As these models continue to evolve and improve through the accumulation of vast amounts of data , they may become increasingly autonomous and independent from human control . This raises important ethical and societal questions about the extent to which we should rely on AI systems to make decisions or provide information without human intervention .”
Avoiding extremes may always be the best approach , specially when it comes to new disruptive technologies , and Marra , et al . ( 2023 ) suggest that a voice of reason stemming from a middle path could be the right tactic for the healthcare sector : “ Finding a middle ground in the development and deployment of AI is critically important to harness its potential and mitigate both risks and ethical concerns .”
They say that the data sets used to train AI models must be broadly representative and free from systemic biases , and that regular audits and assessments should be conducted to detect and mitigate any biases that may emerge in AI systems . They add , “ Transparency should be encouraged by explainable AI , which can help clinicians and patients peer inside the ‘ black box ’ and foster trust in AI strategies in healthcare … Empowering users to employ and navigate AI language models is key to their successful adaptation . This requires user-friendly interfaces . With ease of use , AI systems may be immediately employed in both antimicrobial stewardship and infection prevention . AI can predict anti-infective drug activity , drug – target interactions , and therapeutic design . Antimicrobial stewards and infection preventionists should be encouraged to seek opportunities to apply AI for daily functions ( becoming familiar with generative AI ) and larger pursuits ( idea suggestions for a scientific paper or presentation , pursuing research funding opportunities , and developing task forces to address AI application ) to improve productivity in their respective fields .”
The Future of AI and IP & C
Soon , ML / AI-based HAI control systems might be integrated in hospital clinical practice , with the potential to improve effectiveness and reduce costs of patient safety interventions . ML / AI could also lead to improved understanding of HAIs risk factors , improved patient risk stratification , as well as timely or real-time HAIs detection and control . But experts say that for the implementation and use of ML / AI-based HAI control systems in clinical practice , large volumes of electronic health data should be available , accessible and linkable . They add that strengthened and multidisciplinary collaboration between IT and clinical disciplines is envisaged to promote the adoption and use of ML / AI-based HAI control systems in clinical practice .
Fitzpatrick , et al . ( 2020 ) caution that “ AI in itself will not improve IP & C ,” adding that “ Sustainable improvements in IP & C require culture and behavior change supported by appropriate governance structures . The consideration that “ correlation does not imply causation ” is particularly relevant when the use of AIs in healthcare is considered . AIs are driven by “ big data ” to find the correlations that may indicate medically relevant conditions or to identify potential risk factors . However , AIs can sometimes overlook small clusters that may be clinically relevant and are currently unable to use deep knowledge of the underlying processes to reason about small datasets . Rather than focus on the AI tools themselves , the focus should be on the IP & C problem that needs to be addressed with development of strategy , goals , and processes to support this which may include AI . Organizations that have successfully led digital transformations have used this approach , understanding culture and drivers first before choosing appropriate technological tools . In addition , involving insiders that are familiar with the culture , appreciating that one size does not fit all settings , and adopting a flat hierarchy to support rapid iterative modifications are important considerations . IP & C practitioners need to be aware of the limitations and biases within AI and the tendency of staff to offload tasks on to the AI and be overconfident in its abilities . Issues around
privacy and data ownership require careful consideration ; AI applications need to be tested and integrated into real-life clinical practice and for most healthcare settings , significant investment in data infrastructure is required to truly realize its potential .”
Wong , et al . ( 2023 ) state that , “ Beyond medical and biotechnological approaches to infectious diseases , ML — and more broadly , AI — has also led to substantive advances in epidemiology and our understanding of disease transmission . Better leveraging AI to address infectious diseases will require a collaborative effort among scientists , clinicians , and public health officials .”
References :
Agrebia S and Larbib A . Use of artificial intelligence in infectious diseases . Artificial Intelligence in Precision Health . 2020:415-438 . Published online March 13 , 2020 . doi : 10.1016 / B978-0-12-817133- 2.00018-5
Fitzpatrick F , Doherty A and Lacey G . Using Artificial Intelligence in Infection Prevention . Curr Treat Options Infect Dis . 2020 ; 12 ( 2 ): 135 – 144 . doi : 10.1007 / s40506-020-00216-7
Hirani R , Noruzi K , et al . Artificial Intelligence and Healthcare : A Journey through History , Present Innovations , and Future Possibilities . Life 2024 , 14 ( 5 ), 557 ; https :// doi . org / 10.3390 / life14050557
Marra AR , Nori P , Langford BJ , et al . Brave new world : Leveraging artificial intelligence for advancing healthcare epidemiology , infection prevention , and antimicrobial stewardship . Infect Control Hosp Epidemiol . 2023 Dec ; 44 ( 12 ): 1909-1912 . doi : 10.1017 / ice . 2023.122 . Epub 2023 Jul 3 . DOI : 10.1017 / ice . 2023.122
Parums DV . Editorial : Infectious Disease Surveillance Using Artificial Intelligence ( AI ) and its Role in Epidemic and Pandemic Preparedness . Med Sci Monit . 2023 ; 29 : e941209-1 – e941209-4 . doi : 10.12659 / MSM . 941209
Rabaan AA , Bakhrebah MA , et al . Unleashing the power of artificial intelligence for diagnosing and treating infectious diseases : A comprehensive review . J Infect Public Health . Vol . 16 , Issue 11 . Pages 1837-1847 . November 2023 .
Scardoni A , Balzarini F , Signorelli C , Cabitza F and Odone A . Artificial intelligence-based tools to control healthcare associated infections : A systematic review of the literature . Journal of Infection and Public Health . J Infect Public Health . Vol . 13 , Issue 8 . Pages 1061-1077 . August 2020 . https :// doi . org / 10.1016 / j . jiph . 2020.06.006
Secinaro S , Calandra , D , et al . The role of artificial intelligence in healthcare : a structured literature review . BMC Med Inform Decis Mak 21 , 125 ( 2021 ). https :// doi . org / 10.1186 / s12911-021-01488-9 .
Turing AM . Computing machinery and intelligence . Mind . 1950 ; 59:433 – 60 . Available at : https :// academic . oup . com / mind / article / LIX / 236 / 433 / 986238 . [ Google Scholar ]
Wiemken TL and Carrico RM . Assisting the infection preventionist : Use of artificial intelligence for healthcare-associated infection surveillance . Am J Infect Control . March 13 , 2024 . DOI : https :// doi . org / 10.1016 / j . ajic . 2024.02.007
Wong F , de la Fuente-Nunez C and Collins JJ . Leveraging artificial intelligence in the fight against infectious diseases . Science . 2023 Jul 14 ; 381 ( 6654 ): 164-170 . doi : 10.1126 / science . adh1114 .
june 2024 • www . healthcarehygienemagazine . com •
21