Artificial Intelligence in Nursing Practice: Applications, Opportunities, Challenges, and Future Perspectives

 Introduction:

Artificial intelligence.  (AI)

Artificial intelligence: AI is commonly characterized as an innovation that empowers digital devices or automated machinery to process information, logically deduce conclusions, comprehend surroundings, interact, and execute judgments at or above human capabilities {3} or it can also be defined as the integration of science and engineering to develop computer based soft wares to aid health care. The phrase “artificial intelligence” was originally introduced by computer scientist John McCarthy during the mid-1950s

(Lippincott cott Williams and Wilkins)

Modern individuals interact with machine intelligence routinely via ubiquitous items like smartphones, internet-connected televisions, and biometric tracking wearables {4}

Classification of Machine Intelligence

Automated technology progresses through three distinct evolutionary phases:

• Specialized Machine Intelligence
• Human-Level Machine Intelligence
• Hyper evolved Machine Intelligence

Specialized machine intelligence operates within a restricted domain, utilizing computing power to execute highly specific objectives. This phase is frequently designated as “weak AI.” where in synthetic systems possess the cognitive power to process concepts and execute judgments independently, an evolutionary step known as “strong AI.”

Hyper-evolved machine intelligence represents the ultimate phase of automation, where computational systems operate and solve problems at a level that fundamentally eclipses human intellectual capacity

Advantages of artificial intelligence

• AI   improves decision-making power that will save human lives.
• AI   aids in solving complex problems in health care.
• AI performs high-level computations.
• AI   has increased accuracy and power.

Artificial intelligence in nursing

The implementation of AI within clinical nursing involves utilizing cutting-edge systems to elevate patient outcomes, accelerate clinical judgments, and provide medical intervention in perilous settings while safeguarding staff from unnecessary risks Nursing is emerging day by day; addition of artificial intelligence will augment nursing care.{6}

(WHO)

Fundamentally, machine intelligence describes a computer’s capacity to autonomously transform raw metrics into actionable insights that direct clinical actions its use will save human lives, reduce nurses’ workload and enable prompt action within the golden hour.

Need of artificial intelligence in the nursing profession

• Its application will save nurses time, energy, and resources
• It will lessen the burden on hospitals’ inpatient departments and outpatient department thus lessening the workload of nurses
• Its application will provide specialist-based care in the rural population
• Its application will provide need-based care
• Its application will also save clients time and unnecessary walks to hospitals for minor ailments.{7}

Principles of Artificial intelligence in the Nursing profession

• Protecting human autonomy
• Promoting human well-being and safety and the public interest
• Ensuring transparency, explainability intelligentibility
• Fostering responsibility and accountability
• Ensuring inclusiveness and equity
• Promotion of Artificial Intelligence that is responsive
• and sustainable

Clinical artificial intelligence tools in the nursing profession {8}

• Monitoring patients
• Improving medication adherence
• Recording digital notes
• Automatic laborious work

Monitoring patients:

Monitoring patients is one of the important nursing work domains. Artificial intelligence is likely to have the greatest influence in patient monitoring e.g., nurses can use AI analysis of vital signs for cardiovascular and respiratory monitoring of patients admitted in intensive care units {9}

Patient monitoring is very important. According to a report of 2015, hundreds of thousands of patients fall each year, of which to 30 to 50 per cent of patients have suffered injuries due to falls, which can increase the hospital stay and can even result to death. Artificial intelligence tools like sensors, to analyses movements of patients in patient care rooms or wards, can alert nurses when a fall is predicted

During covid 19 pandemics, the FDA has granted permission to use a software (CLEWICU) which predicts whether the patient will develop dangerously low blood pressure or respiratory failure. {10}

 Improving medication adherence

Artificial intelligence can be tremendously helpful in improving patients’ medication adherence with the help of machine learning. Some of the solutions that have shown results in this field are {11}

• Chabot
• Apps
• Smart packaging
• Smart pills
• Clever caps

E.g.,

Federal health regulators have cleared the inaugural pharmaceutical product featuring an integrated electronic tracking mechanism (The US Food and Drug Administration)

This specialized antipsychotic medication utilizes an internal, edible micro-sensor that logs exact consumption data. Upon dissolution, the internal sensor signals a small patch worn on the skin, which relays the metrics to a smartphone app for patient tracking. Concurrently, clinical teams can monitor compliance metrics remotely via a secure online platform. e., g

(Abilify My Cite) (aripiprazole tablet with sensor) This tablet has an ingestible sensor embedded in the pill that records whether the medication was taken or not. It works by sending a message from the pill sensor to a wearable patch. This patch transmits the information to a mobile application so that the patients can track the ingestion of medication. The healthcare workers can also access this information through a web portal, so it will be helpful for nurses to track medication adherence of discharged or admitted patients. {12}

 Recording digital clinical notes

Documentation in health care is very important, and it needs a huge amount of time to document each and every thing related to patients. Nurses suffer a huge workload of documentations {13}

To ease nurses’ documentation workload, voice-to-text algorithms and linguistic software can streamline the entry of clinical documentation directly into electronic health records (EHR)

Streamlining Routine Physical Duties

A substantial portion of shifts is consumed by transiting between wards, patient bedsides, and centralized desks. Within surgical suites, staff must constantly travel to retrieve sterilized instruments. Artificial intelligence can automate such tasks, allowing nurses to spend more time with the patients. e.g., in the developed nations, many hospitals have employed robots for delivering.{14}

Applications of artificial intelligence in clinical nursing practice:

• Clinical decision-making support
• Sensor-based technologies
• Mobile health
• Robotics
• Risk assessment
• Voice assistants
• Text mining
• Speech recognition technologies {15}

Clinical decision-based support

AI will aid nurses to make decisions regarding patient care at a glance as electronic health record alarms and alerts, clinical practice guidelines, order sheets and dashboards will help nurses in prompt decision making in a clinical setting.{16}

 Clinical decision support can be integrated with mobile health apps that can provide various actionable options and actions to be taken. When coupled with AI, clinical decision support can offer predictions and suggestions with accuracy and specificity beyond human capacity.

Sensor-based technologies {17}

Advanced monitoring devices have revolutionized clinical environments. These utilities convert physiological metrics into readable electronic signals, helping frontline clinicians capture vital signs such as pulse frequency and systemic metrics such as heart rate, blood sugar level, stress rate, oxygen saturation rate, temperature, weight, and blood pressure, which are usually captured with sensory smart devices and transmitted as electrical pulses for further processing. Sensors continue to transform health systems globally and unlock new opportunities to provide care virtually, especially during the pandemic. Sensors have been successfully integrated with smartphones and smart wearable devices, with the necessary capabilities to capture and process health data remotely. Sensors, especially biosensors, are increasingly becoming indispensable resources for monitoring daily life activities in the medical field for improved clinical diagnostics and monitoring biological molecules. Among other functionalities, wearable sensors have been used for remote monitoring of patients in healthcare, which can have a great impact on geriatric nursing care and community health nursing care.{18}

E.gs

• Skin electrodes to monitor heart rate
• Piezoelectric sensor to monitor respirations

Robotics

To facilitate distant patient engagement, healthcare workers can utilize interactive tele-presence machines to observe and listen. This interaction is driven by integrated recording lenses, acoustic outputs, and audio capturing units. While certain units operate via direct synchronization with tablets or smartphones, more advanced models utilize self-directed navigation to bypass environmental barriers.{19}

Integrating machine intelligence significantly enhances the functionality of remote-controlled machinery. For instance, voice-processing software sharpens verbal comprehension, which is vital for human-machine interaction. More broadly, AI empowers machines to decode and mimic human speech patterns, while enabling complex spatial navigation and adaptive learning protocols over prolonged periods. Some robots are smart enough to point out specific health conditions from their patient’s voice or movements.

Robots are very useful in pandemics to deliver patient care and administer medications in hazardous situations to minimise exposure of virus and other dangerous chemicals to healthcare workers, especially nurses who are with the patients 24 hours a day.{20}

Benefits

• Reduced caregiver workload
• Enhanced decision-making

Risk assessment

Automated sepsis risk assessment systems have been developed to assess the sepsis risk of inpatients by using data mining techniques so that nurses will be alerted to make efficient and effective nursing care plans, even automatic systems generate nursing diagnoses based on data , fall risk prediction, and guided decision trees to prevent infection e.g. catheter-associated urinary tract infections.

Fall risk prediction, for instance, involves regular assessment and fall precaution implementation. However, manual risk calculation is time-consuming and vulnerable to human error, leading to inaccurate predictions. AI offers three advantages over traditional methods:

• the ability to quickly consider large volumes of data in the risk prediction
• increased intervention specificity (accurately flagging patients most at-risk)
• Automated   adjustments in variable selection and calculation.

AI accurately identifies at-risk patients by considering more diverse patient information from the electronic health record and other information sources.

Voice assistants

AI assisted follow up system have been developed in developed countries. This system, called patients for follow up viva automatic speech telephony, to improve patient follow-up and recovery and lessens the burden of follow-up nurses. Voice assistants may have a future in electronic health record applications, collecting patient data in the home and delivering interventions to augment care. Imagine a scenario in which a nurse uses Alexa to remind older adults to take their medications and measure their blood pressure. Alexa then records patient data in the EHR for the nurse to review. For older adults and patients with certain disabilities, such as poor eyesight, these tools may be especially useful given their voice-based interaction. The benefit of voice assistants depends on nurse involvement in technology selection and its application in practice and patient care.

Speech recognition technologies

Speech recognition technologies can speed up and enhance nursing documentation, and machine learning has been used to develop a tool to aid nurses in using standardised technologies, by automatically suggesting the most relevant terms to be used based on the text written by the nurse.

Text mining

Text mining will require a large database, Text mining, where AI technologies are being used to mine millions of nursing notes to identify patients with fall history or drug and alcohol use disorders to support care planning and patient risk detection. Similarly, machine learning, specifically deep learning, has been experimented to predict pain sensation and physical deterioration for acute critical conditions.

 AI technologies will also help nurses integrate different types of relevant data (e.g., environmental, genomic, health data, socio-demographics), strengthening nurses’ capacity to provide multifaceted care. 

 Application of artificial intelligence in the community, outside the traditional setting of hospitals and clinics

• Tele health
• Remote monitoring

Tele health: Tele health or e health has gained recognition since covid times, tele health nurses have wide scope throughout the country, tele health is saving human lives and providing health care at door steps, it has been integrated in national health mission, and in health and wellness centres throughout the country with the help of e sanjeevni apps where a patient can receive specialist consultation viva mobile phone.

E g patient visits the health and wellness centre of any village, where nurses contact specialists and provide need-based interventions within no time.

  Remote monitoring

Various wearable sensors are used in remote monitoring of patients E.g., cardiac monitoring such as HR and rhythm sensors, including the Apple Watch, rhythm and Huawei devices

The Apple Watch is FDA-approved to detect and alert hearth irregular rhythms.{21}

Challenges of artificial intelligence in the nursing profession

• To educate the educators in nursing colleges for better implementation of AI technologies to augment care from basic courses.
• Development of modular wards
• Integration of computer technology with Nursing basic education
• Integration of artificial intelligence tools with culture to apply it in clinical practice to promote its acceptability among patients
• Generation of a large database to use in machine learning and to develop algorithms that automatically guide prompt decision making to provide care.

Limitations of artificial intelligence in the nursing profession

• It lacks human touch
• It lacks human creativity
• Its increased use will diminish human abilities
• It leads to dependence of humans on machines
• It needs huge costs in development, maintenance and repair

Conclusion

Artificial intelligence is destined to transform clinical nursing practice, community health nursing practice and nursing education.

 It will also transform the health care delivery system and will ease nursing quality care delivery and nurses’ workload burdens.

Artificial intelligence will also develop algorithms related to patient care based on a nursing database that will help in prompt decision-making and will save human lives.

Nurses must contribute to the advancement of artificial intelligence to ensure development that advances the nursing role and focuses on providing client-centred care.

List of declaration’s

• Number of authors 

    Single author; NUSRAT MANZOOR (zargarnusrat53@gmail.com)

• Author’s contribution

Nusrat manzoor is a nursing officer with research interest in AI, digital health technologies and clinical nursing. she conceived the review topic, conducted the literature search, analysed and synthesised the review article and drafted and revised the manuscript, the author read and approved the final manuscript

• type of review

Narrative review article

• funding information

No funding

• conflict of interest

No conflict of interest

• acknowledgements

I am thankful to my parents for their support always

• Ethical approval and consent to participate

Not applicable as this review article is based exclusively on published literature and did not involve human participants, human data or human issue

• Consent for publication/consent to participate

Not applicable

• Competing interest

No competing interest

Reference

1.  Journals.IWW.com
2.  Reimaging the possible in the Indian health care ecosystem with emerging technologies (pwc.in)
3.   Ajani R, Chatterjee A, Talwai A, Zhang J. How a pharma company applied machine learning to patient data. Harvard Business Review. October 25, 2018. hbr.org/2018/10/how-a-pharma-company-applied-machine-learning-to-patient-data
4. Cary MP Jr, Zhuang F, Draelos RL, et al. Machine learning algorithms to predict mortality and allocate palliative care for older patients with hip fracture. J Am Med Dir Assoc. 2021;22(2):291-6. doi:10.1016/j.jamda.2020.09.025
5.  
6. By: By Brian J. Douthit, PhD, RN-BC; Ryan J. Shaw, PhD, RN; Kay S. Lytle, DNP, RN-BC, NEA-BC, CPHIMS, FHIMSS; Rachel L. Richesson, PhD, MPH; and Michael P. Cary, Jr., PhD, R January 11 2022
7. Clancy, Thomas R. PhD, MBA, RN, FAAN. Artificial Intelligence and Nursing: The Future Is Now. JONA: The Journal of Nursing Administration 50(3):p 125-127, March 2020. | DOI: 10.1097/NNA.0000000000000855
8. Robert N. How artificial intelligence is changing nursing. Nurs Manage. 2019 Sep;50(9):30-39. doi: 10.1097/01.NUMA.0000578988.56622.21. PMID: 31425440; PMCID: PMC7597764.

•   Bresnick J. Artificial intelligence in healthcare spending to hit $36B. Health IT Analytics. 2018. https://healthitanalytics.com/news/artificial-intelligence-in-healthcare-spending-to-hit-36b. [Google Scholar]
•  Federal Register. Executive order No. 13859 of February 11, 2019: maintaining American leadership in artificial intelligence. www.federalregister.gov/documents/2019/02/14/2019-02544/maintaining-american-leadership-in-artificial-intelligence.
•   Menzies T. 21st-century AI: proud, not smug. IEEE Intell Syst. 2003;18(3):18–24. [Google Scholar]
•   Castellanos S. What exactly is artificial intelligence. The Wall Street Journal. 2018. www.wsj.com/articles/what-exactly-is-artificial-intelligence-1544120887. [Google Scholar]
• Buchanan C, Howitt M, Wilson R, Booth R, Risling T, Bamford M Predicted Influences of Artificial Intelligence on Nursing Education: Scoping Review JMIR Nursing 2021;4(1):e23933 URL: https://nursing.jmir.org/2021/1/e23933 DOI: 10.2196/23933

13. Seibert K, Domhoff D, Bruch D, Schulte-Althoff M, Fürstenau D, Biessmann F Wolf-Ostermann K Application Scenarios for Artificial Intelligence in Nursing Care: Rapid Review J Med Internet Res 2021;23(11):e26522 URL: https://www.jmir.org/2021/11/e26522 DOI: 10.2196/26522

1. 14  .Robert, Nancy PhD, MBA-DSS, BSN. How artificial intelligence is changing nursing. Nursing Management (Springhouse) 50(9):p 30-39, September 2019. | DOI 10.1097/01.NUMA.0000578988.56622.21

 15. Buchanan C, Howitt ML, Wilson R, Booth RG, Risling T, Bamford M. Predicted Influences of Artificial Intelligence on Nursing Education: Scoping Review. JMIR Nurs. 2021 Jan 28;4(1):e23933. doi: 10.2196/23933. PMID: 34345794; PMCID: PMC83

16.Abbasgholizadeh-Rahimi, S., Granikov, V., & Pluye, P. (2020). Current works and future directions on application of machine learning in primary care. In Proceedings of the 11th Augmented Human International Conference (pp. 1–Google Scholar

1. AI for Good Foundation. (2015). AI for good foundation. AI for Good Foundation. Retrieved from https://ai4good.org/Google Scholar
2. Benjamin, R. (2019). Race after technology: Abolitionist tools for the new Jim code. Social Forces, 98(4), 1–3.
3. Overview of artificial intelligence in healthcare (ai4bharat.org)
4. Tikkanen,R and M.K Abrams 2020 US Health care team from a global perspective 2019 higher speeding worst outcomes
5. Yu, KH., Beam, A.L. & Kohane, I.S. Artificial intelligence in healthcare. Nat Biomed Eng 2, 719–731 (2018). https://doi.org/10.1038/s41551-018-0305-z 12 december2017 Introduction:
6. Artificial intelligence.  (AI)
7. Artificial intelligence: AI is commonly characterized as an innovation that empowers digital devices or automated machinery to process information, logically deduce conclusions, comprehend surroundings, interact, and execute judgments at or above human capabilities {3} or it can also be defined as the integration of science and engineering to develop computer based soft wares to aid health care. The phrase “artificial intelligence” was originally introduced by computer scientist John McCarthy during the mid-1950s
8. (Lippincott cott Williams and Wilkins)
9. Modern individuals interact with machine intelligence routinely via ubiquitous items like smartphones, internet-connected televisions, and biometric tracking wearables {4}
10. Classification of Machine Intelligence
11. Automated technology progresses through three distinct evolutionary phases:
12. Specialized Machine Intelligence
13. Human-Level Machine Intelligence
14. Hyper evolved Machine Intelligence
15. Specialized machine intelligence operates within a restricted domain, utilizing computing power to execute highly specific objectives. This phase is frequently designated as “weak AI.” where in synthetic systems possess the cognitive power to process concepts and execute judgments independently, an evolutionary step known as “strong AI.”
16. Hyper-evolved machine intelligence represents the ultimate phase of automation, where computational systems operate and solve problems at a level that fundamentally eclipses human intellectual capacity
17. Advantages of artificial intelligence
18. AI   improves decision-making power that will save human lives.
19. AI   aids in solving complex problems in health care.
20. AI performs high-level computations.
21. AI   has increased accuracy and power.
22. Artificial intelligence in nursing
23. The implementation of AI within clinical nursing involves utilizing cutting-edge systems to elevate patient outcomes, accelerate clinical judgments, and provide medical intervention in perilous settings while safeguarding staff from unnecessary risks Nursing is emerging day by day; addition of artificial intelligence will augment nursing care.{6}
24. (WHO)
25. Fundamentally, machine intelligence describes a computer’s capacity to autonomously transform raw metrics into actionable insights that direct clinical actions its use will save human lives, reduce nurses’ workload and enable prompt action within the golden hour.
26. Need of artificial intelligence in the nursing profession
27. Its application will save nurses time, energy, and resources
28. It will lessen the burden on hospitals’ inpatient departments and outpatient department thus lessening the workload of nurses
29. Its application will provide specialist-based care in the rural population
30. Its application will provide need-based care
31. Its application will also save clients time and unnecessary walks to hospitals for minor ailments.{7}
32. Principles of Artificial intelligence in the Nursing profession
33. Protecting human autonomy
34. Promoting human well-being and safety and the public interest
35. Ensuring transparency, explainability intelligentibility
36. Fostering responsibility and accountability
37. Ensuring inclusiveness and equity
38. Promotion of Artificial Intelligence that is responsive
39. and sustainable
40. Clinical artificial intelligence tools in the nursing profession {8}
41. Monitoring patients
42. Improving medication adherence
43. Recording digital notes
44. Automatic laborious work
45. Monitoring patients:
46. Monitoring patients is one of the important nursing work domains. Artificial intelligence is likely to have the greatest influence in patient monitoring e.g., nurses can use AI analysis of vital signs for cardiovascular and respiratory monitoring of patients admitted in intensive care units {9}
47. Patient monitoring is very important. According to a report of 2015, hundreds of thousands of patients fall each year, of which to 30 to 50 per cent of patients have suffered injuries due to falls, which can increase the hospital stay and can even result to death. Artificial intelligence tools like sensors, to analyses movements of patients in patient care rooms or wards, can alert nurses when a fall is predicted
48. During covid 19 pandemics, the FDA has granted permission to use a software (CLEWICU) which predicts whether the patient will develop dangerously low blood pressure or respiratory failure. {10}
49.  Improving medication adherence
50. Artificial intelligence can be tremendously helpful in improving patients’ medication adherence with the help of machine learning. Some of the solutions that have shown results in this field are {11}
51. Chabot
52. Apps
53. Smart packaging
54. Smart pills
55. Clever caps
56. E.g.,
57. Federal health regulators have cleared the inaugural pharmaceutical product featuring an integrated electronic tracking mechanism (The US Food and Drug Administration)
58. This specialized antipsychotic medication utilizes an internal, edible micro-sensor that logs exact consumption data. Upon dissolution, the internal sensor signals a small patch worn on the skin, which relays the metrics to a smartphone app for patient tracking. Concurrently, clinical teams can monitor compliance metrics remotely via a secure online platform. e., g
59. (Abilify My Cite) (aripiprazole tablet with sensor) This tablet has an ingestible sensor embedded in the pill that records whether the medication was taken or not. It works by sending a message from the pill sensor to a wearable patch. This patch transmits the information to a mobile application so that the patients can track the ingestion of medication. The healthcare workers can also access this information through a web portal, so it will be helpful for nurses to track medication adherence of discharged or admitted patients. {12}
60.  Recording digital clinical notes
61. Documentation in health care is very important, and it needs a huge amount of time to document each and every thing related to patients. Nurses suffer a huge workload of documentations {13}
62. To ease nurses’ documentation workload, voice-to-text algorithms and linguistic software can streamline the entry of clinical documentation directly into electronic health records (EHR)
63. Streamlining Routine Physical Duties
64. A substantial portion of shifts is consumed by transiting between wards, patient bedsides, and centralized desks. Within surgical suites, staff must constantly travel to retrieve sterilized instruments. Artificial intelligence can automate such tasks, allowing nurses to spend more time with the patients. e.g., in the developed nations, many hospitals have employed robots for delivering.{14}
65. Applications of artificial intelligence in clinical nursing practice:
66. Clinical decision-making support
67. Sensor-based technologies
68. Mobile health
69. Robotics
70. Risk assessment
71. Voice assistants
72. Text mining
73. Speech recognition technologies {15}
74. Clinical decision-based support
75. AI will aid nurses to make decisions regarding patient care at a glance as electronic health record alarms and alerts, clinical practice guidelines, order sheets and dashboards will help nurses in prompt decision making in a clinical setting.{16}
76.  Clinical decision support can be integrated with mobile health apps that can provide various actionable options and actions to be taken. When coupled with AI, clinical decision support can offer predictions and suggestions with accuracy and specificity beyond human capacity.
77. Sensor-based technologies {17}
78. Advanced monitoring devices have revolutionized clinical environments. These utilities convert physiological metrics into readable electronic signals, helping frontline clinicians capture vital signs such as pulse frequency and systemic metrics such as heart rate, blood sugar level, stress rate, oxygen saturation rate, temperature, weight, and blood pressure, which are usually captured with sensory smart devices and transmitted as electrical pulses for further processing. Sensors continue to transform health systems globally and unlock new opportunities to provide care virtually, especially during the pandemic. Sensors have been successfully integrated with smartphones and smart wearable devices, with the necessary capabilities to capture and process health data remotely. Sensors, especially biosensors, are increasingly becoming indispensable resources for monitoring daily life activities in the medical field for improved clinical diagnostics and monitoring biological molecules. Among other functionalities, wearable sensors have been used for remote monitoring of patients in healthcare, which can have a great impact on geriatric nursing care and community health nursing care.{18}
79. E.gs
80. Skin electrodes to monitor heart rate
81. Piezoelectric sensor to monitor respirations
82. Robotics
83. To facilitate distant patient engagement, healthcare workers can utilize interactive tele-presence machines to observe and listen. This interaction is driven by integrated recording lenses, acoustic outputs, and audio capturing units. While certain units operate via direct synchronization with tablets or smartphones, more advanced models utilize self-directed navigation to bypass environmental barriers.{19}
84. Integrating machine intelligence significantly enhances the functionality of remote-controlled machinery. For instance, voice-processing software sharpens verbal comprehension, which is vital for human-machine interaction. More broadly, AI empowers machines to decode and mimic human speech patterns, while enabling complex spatial navigation and adaptive learning protocols over prolonged periods. Some robots are smart enough to point out specific health conditions from their patient’s voice or movements.
85. Robots are very useful in pandemics to deliver patient care and administer medications in hazardous situations to minimise exposure of virus and other dangerous chemicals to healthcare workers, especially nurses who are with the patients 24 hours a day.{20}
86. Benefits
87. Reduced caregiver workload
88. Enhanced decision-making
89. Risk assessment
90. Automated sepsis risk assessment systems have been developed to assess the sepsis risk of inpatients by using data mining techniques so that nurses will be alerted to make efficient and effective nursing care plans, even automatic systems generate nursing diagnoses based on data , fall risk prediction, and guided decision trees to prevent infection e.g. catheter-associated urinary tract infections.
91. Fall risk prediction, for instance, involves regular assessment and fall precaution implementation. However, manual risk calculation is time-consuming and vulnerable to human error, leading to inaccurate predictions. AI offers three advantages over traditional methods:
92. the ability to quickly consider large volumes of data in the risk prediction
93. increased intervention specificity (accurately flagging patients most at-risk)
94. Automated   adjustments in variable selection and calculation.
95. AI accurately identifies at-risk patients by considering more diverse patient information from the electronic health record and other information sources.
96. Voice assistants
97. AI assisted follow up system have been developed in developed countries. This system, called patients for follow up viva automatic speech telephony, to improve patient follow-up and recovery and lessens the burden of follow-up nurses. Voice assistants may have a future in electronic health record applications, collecting patient data in the home and delivering interventions to augment care. Imagine a scenario in which a nurse uses Alexa to remind older adults to take their medications and measure their blood pressure. Alexa then records patient data in the EHR for the nurse to review. For older adults and patients with certain disabilities, such as poor eyesight, these tools may be especially useful given their voice-based interaction. The benefit of voice assistants depends on nurse involvement in technology selection and its application in practice and patient care.
98. Speech recognition technologies
99. Speech recognition technologies can speed up and enhance nursing documentation, and machine learning has been used to develop a tool to aid nurses in using standardised technologies, by automatically suggesting the most relevant terms to be used based on the text written by the nurse.
100. Text mining
101. Text mining will require a large database, Text mining, where AI technologies are being used to mine millions of nursing notes to identify patients with fall history or drug and alcohol use disorders to support care planning and patient risk detection. Similarly, machine learning, specifically deep learning, has been experimented to predict pain sensation and physical deterioration for acute critical conditions.
102.  AI technologies will also help nurses integrate different types of relevant data (e.g., environmental, genomic, health data, socio-demographics), strengthening nurses’ capacity to provide multifaceted care. 
103.  Application of artificial intelligence in the community, outside the traditional setting of hospitals and clinics
104. Tele health
105. Remote monitoring
106. Tele health: Tele health or e health has gained recognition since covid times, tele health nurses have wide scope throughout the country, tele health is saving human lives and providing health care at door steps, it has been integrated in national health mission, and in health and wellness centres throughout the country with the help of e sanjeevni apps where a patient can receive specialist consultation viva mobile phone.
107. E g patient visits the health and wellness centre of any village, where nurses contact specialists and provide need-based interventions within no time.
108.   Remote monitoring
109. Various wearable sensors are used in remote monitoring of patients E.g., cardiac monitoring such as HR and rhythm sensors, including the Apple Watch, rhythm and Huawei devices
110. The Apple Watch is FDA-approved to detect and alert hearth irregular rhythms.{21}
111. Challenges of artificial intelligence in the nursing profession
112. To educate the educators in nursing colleges for better implementation of AI technologies to augment care from basic courses.
113. Development of modular wards
114. Integration of computer technology with Nursing basic education
115. Integration of artificial intelligence tools with culture to apply it in clinical practice to promote its acceptability among patients
116. Generation of a large database to use in machine learning and to develop algorithms that automatically guide prompt decision making to provide care.
117. Limitations of artificial intelligence in the nursing profession
118. It lacks human touch
119. It lacks human creativity
120. Its increased use will diminish human abilities
121. It leads to dependence of humans on machines
122. It needs huge costs in development, maintenance and repair
123. Conclusion
124. Artificial intelligence is destined to transform clinical nursing practice, community health nursing practice and nursing education.
125.  It will also transform the health care delivery system and will ease nursing quality care delivery and nurses’ workload burdens.
126. Artificial intelligence will also develop algorithms related to patient care based on a nursing database that will help in prompt decision-making and will save human lives.
127. Nurses must contribute to the advancement of artificial intelligence to ensure development that advances the nursing role and focuses on providing client-centred care.
128. List of declaration’s
129. Number of authors 
130.     Single author: NUSRAT MANZOOR (zargarnusrat53@gmail.com)
131. Author’s contribution
132. Nusrat manzoor is a nursing officer with research interest in AI, digital health technologies and clinical nursing. she conceived the review topic, conducted the literature search, analysed and synthesised the review article and drafted and revised the manuscript, the author read and approved the final manuscript
133. type of review
134. Narrative review article
135. funding information
136. No funding
137. conflict of interest
138. No conflict of interest
139. acknowledgements
140. I am thankful to my parents for their support always
141. Ethical approval and consent to participate
142. Not applicable as this review article is based exclusively on published literature and did not involve human participants, human data or human issue
143. Consent for publication/consent to participate
144. Not applicable
145. Competing interest
146. No competing interest
147. Reference
148.  Journals.IWW.com
149.  Reimaging the possible in the Indian health care ecosystem with emerging technologies (pwc.in)
150.   Ajani R, Chatterjee A, Talwai A, Zhang J. How a pharma company applied machine learning to patient data. Harvard Business Review. October 25, 2018. hbr.org/2018/10/how-a-pharma-company-applied-machine-learning-to-patient-data
151. Cary MP Jr, Zhuang F, Draelos RL, et al. Machine learning algorithms to predict mortality and allocate palliative care for older patients with hip fracture. J Am Med Dir Assoc. 2021;22(2):291-6. doi:10.1016/j.jamda.2020.09.025
152.  
153. By: By Brian J. Douthit, PhD, RN-BC; Ryan J. Shaw, PhD, RN; Kay S. Lytle, DNP, RN-BC, NEA-BC, CPHIMS, FHIMSS; Rachel L. Richesson, PhD, MPH; and Michael P. Cary, Jr., PhD, R January 11 2022
154. Clancy, Thomas R. PhD, MBA, RN, FAAN. Artificial Intelligence and Nursing: The Future Is Now. JONA: The Journal of Nursing Administration 50(3):p 125-127, March 2020. | DOI: 10.1097/NNA.0000000000000855
155. Robert N. How artificial intelligence is changing nursing. Nurs Manage. 2019 Sep;50(9):30-39. doi: 10.1097/01.NUMA.0000578988.56622.21. PMID: 31425440; PMCID: PMC7597764.
156.   Bresnick J. Artificial intelligence in healthcare spending to hit $36B. Health IT Analytics. 2018. https://healthitanalytics.com/news/artificial-intelligence-in-healthcare-spending-to-hit-36b. [Google Scholar]
157.  Federal Register. Executive order No. 13859 of February 11, 2019: maintaining American leadership in artificial intelligence. www.federalregister.gov/documents/2019/02/14/2019-02544/maintaining-american-leadership-in-artificial-intelligence.
158.   Menzies T. 21st-century AI: proud, not smug. IEEE Intell Syst. 2003;18(3):18–24. [Google Scholar]
159.   Castellanos S. What exactly is artificial intelligence. The Wall Street Journal. 2018. www.wsj.com/articles/what-exactly-is-artificial-intelligence-1544120887. [Google Scholar]
160. Buchanan C, Howitt M, Wilson R, Booth R, Risling T, Bamford M Predicted Influences of Artificial Intelligence on Nursing Education: Scoping Review JMIR Nursing 2021;4(1):e23933 URL: https://nursing.jmir.org/2021/1/e23933 DOI: 10.2196/23933
161. 13. Seibert K, Domhoff D, Bruch D, Schulte-Althoff M, Fürstenau D, Biessmann F Wolf-Ostermann K Application Scenarios for Artificial Intelligence in Nursing Care: Rapid Review J Med Internet Res 2021;23(11):e26522 URL: https://www.jmir.org/2021/11/e26522 DOI: 10.2196/26522
162. 14  .Robert, Nancy PhD, MBA-DSS, BSN. How artificial intelligence is changing nursing. Nursing Management (Springhouse) 50(9):p 30-39, September 2019. | DOI 10.1097/01.NUMA.0000578988.56622.21
163.  15. Buchanan C, Howitt ML, Wilson R, Booth RG, Risling T, Bamford M. Predicted Influences of Artificial Intelligence on Nursing Education: Scoping Review. JMIR Nurs. 2021 Jan 28;4(1):e23933. doi: 10.2196/23933. PMID: 34345794; PMCID: PMC83
164. 16.Abbasgholizadeh-Rahimi, S., Granikov, V., & Pluye, P. (2020). Current works and future directions on application of machine learning in primary care. In Proceedings of the 11th Augmented Human International Conference (pp. 1–Google Scholar
165. AI for Good Foundation. (2015). AI for good foundation. AI for Good Foundation. Retrieved from https://ai4good.org/Google Scholar
166. Benjamin, R. (2019). Race after technology: Abolitionist tools for the new Jim code. Social Forces, 98(4), 1–3.
167. Overview of artificial intelligence in healthcare (ai4bharat.org)
168. Tikkanen,R and M.K Abrams 2020 US Health care team from a global perspective 2019 higher speeding worst outcomes
169. Yu, KH., Beam, A.L. & Kohane, I.S. Artificial intelligence in healthcare. Nat Biomed Eng 2, 719–731 (2018). https://doi.org/10.1038/s41551-018-0305-z 12 december2017