How Do You Make Use of Artificial Intelligence in Healthcare?

1. What Is Artificial Intelligence?

Artificial intelligence (AI) is the whole of the technology that lets machines gain the ability to learn, think, decide and solve problems in a way resembling human intelligence. At its foundation lie algorithms that can learn from large data sets, recognise patterns and make predictions about the future.

Today artificial intelligence is not only an extension of software systems; it has become the centre of digital transformation across every sector, including health, finance, manufacturing and marketing. In the health sector in particular, the enormous volume of data — millions of patient records, laboratory results, imaging data and sensor outputs — has reached a scale that cannot be analysed by human effort. By finding the relationships within that data, artificial intelligence increases diagnostic accuracy, speeds up processes and reduces human error.

Artificial Intelligence's Core Components

1. Data:
   Data is every artificial intelligence system's fuel. The cleaner, more accurate and more comprehensive the data it is fed, the greater the model's predictive power.
2. Algorithms:
   The mathematical structures that process the data; classification, prediction or optimisation models, for example. These algorithms determine the model's "way of thinking".
3. Machine learning:
   The method that lets a computer learn through experience. The system learns from past data and makes predictions on new data.
4. Deep learning:
   Multi-layered algorithms inspired by the human brain's neural networks. They deliver great success in complex tasks such as imaging and speech recognition in particular.
5. Natural language processing (NLP):
   The process of drawing meaning by analysing text data such as doctors' notes, discharge reports or call centre conversations.

Why Artificial Intelligence Matters in Healthcare

The health sector is by its nature a field holding rich data and vital decisions. Even seconds can be critical in a patient's diagnosis. That is where artificial intelligence comes in:

• It shortens diagnosis time: it delivers early detection in imaging systems.
• It reduces errors: it alerts the doctor through clinical decision support systems.
• It increases efficiency: it prevents wasted time and resources in hospital operations.
• It improves the experience and raises patient satisfaction: it makes faster, personalised service possible.

Artificial intelligence is no longer the future — it is a cornerstone of today's health systems. Used with the right data infrastructure and an ethical approach, it increases both clinical success and business efficiency together.

2. What Types of Artificial Intelligence Can Be Used in Healthcare?

Artificial intelligence is not a single technology; it is a combination of different algorithms and learning methods. In the health sector each type offers its own benefit. Below you can find the most common types of artificial intelligence and examples of their use in healthcare.

Machine learning

Machine learning lets systems learn from past data and make predictions about the future.
Where it is used:

• Disease risk scores and predicting complications
• Calculating the likelihood of not attending an appointment (no-show)
• Early detection models from clinical data
• Operational forecasts (patient volume, stock planning)

Example: models predicting diabetes patients' future risk level from their blood sugar, activity and nutrition data.

Deep learning

Deep learning analyses complex data with neural network architectures. It has created a revolution in medical imaging in particular.
Where it is used:

• Automatic lesion detection in radiology, pathology and dermatology images
• OCT and retina analysis in eye disease
• Automatic classification of images such as MRI, CT and X-ray

Example: a deep learning-based system can detect tumours in brain MRIs within seconds.

Natural language processing (NLP)

NLP lets artificial intelligence understand and interpret human language.
Where it is used:

• Automatic summarising of doctors' notes and discharge reports
• Analysing call centre conversations
• Extracting data from clinical research texts
• Chatbots answering patients' questions

Example: NLP-supported systems can identify reports mentioning "lung nodule" among thousands of patient records within seconds.

Computer vision

Computer vision lets computers draw meaning from visual data.
Where it is used:

• Automatic analysis in radiology, dentistry, dermatology and ophthalmology
• Surgical planning and 3D modelling
• Detecting abnormalities in biopsy and microscope images

Example: in dentistry, computer vision can automatically optimise a clear aligner plan.

Generative AI / LLM

Generative artificial intelligence covers the advanced models that can produce text, images or data (ChatGPT, Claude and Gemini, for example).
Where it is used:

• Patient information texts and content production
• Summarising clinical notes, standardising reports
• Digital marketing content (blogs, emails, social media)
• 24/7 pre-information through chatbot integrations

Example: an LLM-based virtual assistant can give patients personal information about preparing for surgery.

Expert systems (rule-based AI)

Expert systems are artificial intelligence systems working within particular rules and medical protocols.
Where it is used:

• Clinical decision support systems
• Drug interaction warnings
• Risk assessment and scoring systems

Example: it produces rule-based warnings such as "if the patient is taking blood thinners, drug X is not recommended."

Technologies working together

Modern hospitals generally use several of these technologies together.
A radiology system detects a lesion with computer vision and deep learning models; an NLP module summarises the report; and CRM integration ties the result to the advertising data through an offline conversion system.
Organisations thereby gain not only clinical accuracy but a measure of real ROI (return on investment).

3. Clinical Uses (Diagnosis – Treatment – Follow-Up)

Artificial intelligence now plays an active role at every stage of clinical processes. It increases diagnostic accuracy, speeds up treatment planning and makes patients' follow-up easier.
Below you can find artificial intelligence's most effective uses in healthcare by specialism.

Artificial intelligence for radiology: fast, accurate diagnosis in images

Radiology is one of the clinical fields where artificial intelligence is most widespread and most successful.
By analysing thousands of X-ray, MRI and CT images, deep learning algorithms can detect findings such as tumours, fractures, vascular blockages or lesions within seconds.

Benefits:

• Up to 40% faster reporting
• An increase in early diagnosis rates
• A reduction in human error
• Prioritising critical cases (triage)

Example: an artificial intelligence model can detect the likelihood of pneumonia or a nodule on chest X-rays and give the radiologist an automatic alert.

Artificial intelligence for pathology: cell analysis in digital microscopy

Pathology draws on artificial intelligence in analysing high-resolution digital slides.
Deep learning-based systems examine cancer cells' morphology and automate grading and classification.

Benefits:

• More consistent diagnostic results
• A reduction in the need for a second opinion
• Shorter reporting times

Artificial intelligence for dermatology: early detection in skin lesions

Computer imaging models can analyse moles or lesions on the skin's surface and detect melanoma risk at an early stage.
With smart mobile apps and camera-supported systems, this analysis can now be applied on the patient's side too.

Benefits:

• High accuracy in distinguishing malignant from benign
• A reduction in unnecessary biopsies
• Remote diagnosis and teledermatology applications

Artificial intelligence in eye disease: detecting retinopathy and glaucoma

In ophthalmology, artificial intelligence has been groundbreaking in retina and optic nerve analysis.
By examining OCT and fundus images with deep learning models it can detect signs of diabetic retinopathy, macular degeneration or glaucoma at an early stage.

Benefits:

• An increase in early detection rates
• A reduction in the risk of sight loss
• A fall in screening costs

Artificial intelligence in dentistry: detecting plaque and decay on panoramic X-rays

Dentistry is now fully digitalised.
Artificial intelligence systems help clinicians by detecting conditions such as decay, plaque or bone loss on panoramic or CBCT (3D) images.

Benefits:

• Automatic creation of treatment plans
• Clear aligner treatment optimisation
• Informing patients with visual reports

Artificial intelligence for cardiology: ECG and risk analysis

In cardiology, artificial intelligence can analyse ECG, echocardiography and vital data and predict conditions such as arrhythmia, heart failure or stroke risk in advance.

Benefits:

• The ability to intervene early
• Forecasting sudden cardiac arrest or rhythm disorder
• Personalising the treatment process

Artificial intelligence for oncology: personalised treatment approaches

In cancer treatment, artificial intelligence can combine the patient's genetic data, tumour type and past treatment results to build personalised treatment protocols.

Benefits:

• An increase in treatment response rates
• Preventing unnecessary drug use
• More accurate protocol selection through clinical decision support systems

Artificial intelligence in follow-up and early warning systems

To monitor patients after treatment and prevent complications, artificial intelligence analyses data coming from sensors or wearable devices.
When the system sees an abnormality in the patient's parameters it can send an automatic alert to the clinician or the patient.

Examples of use:

• Warnings of sepsis or heart attack risk in intensive care
• Detecting glucose fluctuations in diabetes patients
• Tracking exercise during rehabilitation

Data-driven clinical decisions and the ROI effect

Artificial intelligence delivers significant gains in terms of efficiency and cost as well as clinical accuracy.

• 30–50% faster reporting
• A fall in clinical error rates
• An increase in patient satisfaction and the revenue cycle

All that data proves artificial intelligence is not only a diagnostic tool but also a tool for corporate growth and ROI optimisation.

4. Artificial Intelligence in Patient Experience, Marketing and CRM Integration

In the health sector artificial intelligence is transforming not only diagnosis and treatment but the whole journey, from the patient's first contact with the clinic to their satisfaction after treatment.
For modern healthcare organisations, success is now measured not only by making the right diagnosis but by reaching the right patient at the right moment and making the relationship sustainable.

That is where artificial intelligence makes a difference, bringing together the trio of patient experience management, marketing automation and CRM integration.

Personalised patient communication and experience

Thanks to AI-supported chatbots, virtual assistants and WhatsApp integrations, patients can get support 24/7.
Understanding incoming messages with natural language processing (NLP), the systems direct each patient individually.

Examples of use:

• Smart appointment booking through the website and WhatsApp
• Automatic answering of frequently asked questions
• Interactive information through voice assistants
• Personalised reminders before surgery or treatment

Benefits:

• A serious reduction in the call centre's load
• Fast, personal and consistent communication
• An increase in patient satisfaction

AI-supported healthcare marketing

Digital marketing in healthcare is no longer only "running ads" — it means a data-driven patient acquisition process.
Machine learning-based systems analyse ad performance and determine which campaigns deliver higher conversion.

Examples of use:

• Audience segmentation: grouping by age, location, interest and past engagement
• AI-based ad optimisation: prioritising the content delivering high ROAS
• SEO and content production: AI-supported blog and information articles
• Image production: social media and banner designs with artificial intelligence

Benefits:

• A fall in patient acquisition cost (CPL/CPA)
• Accurate measurement of ROI by campaign
• Real-time performance tracking

Offline conversion tracking: measuring digital's real impact

In healthcare, conversion is completed not at the click but with the appointment or treatment that takes place at the clinic.

What is offline conversion? What is its benefit? You can find more detailed information about offline conversion setup in that article.

Offline conversion tracking reveals real ROI by matching the engagement coming from digital advertising with CRM systems.

How it works:

1. The patient sees the ad → fills in a form / writes on WhatsApp / calls
2. It is recorded automatically in the CRM system
3. When the treatment takes place the result is passed to the ad platform
4. Which campaign genuinely won patients is thereby measured

Benefits:

• Directing the budget to the channels that deliver
• Reducing CPL/CPA rates
• Campaign optimisation resting on data

CRM integration: making every process automatic and measurable

Artificial intelligence strengthens CRM systems (Monday, Zoho, HubSpot and so on) and makes the whole patient journey traceable end to end.
Every touchpoint — the ad, the form, the call, the appointment, the treatment — is gathered into a single data chain.

Examples of use:

• Automatic appointment assignment and status updates
• Personalised email / SMS sending by patient segment
• Measuring satisfaction after treatment and analysing feedback
• Patient acquisition, follow-up and revenue reports in a single panel

Benefits:

• Manual data entry disappearing
• MQL (marketing qualified lead) and SQL (sales qualified lead) tracking becoming clear
• Marketing, sales and patient relations managed in one place

As an agency, DijitalPi is a direct partner agency of Monday, Zoho and HubSpot. You can get detailed information about the CRM solutions that suit your business.

6. Artificial Intelligence in Healthcare Marketing and Digital Communication

Artificial intelligence is creating transformation not only in healthcare organisations' operational processes but in patient acquisition and digital communication strategy too.
A successful health brand now advances within a triangle of visibility, trust and measurable performance. One of the most powerful tools delivering that balance is the AI-supported digital marketing ecosystem.

Smart targeting: the right message, the right audience

Artificial intelligence algorithms analyse user behaviour and interests and split each campaign into micro-segments.
An eye hospital's ad can thereby be shown only to "users aged 25–45 interested in laser eye treatment".

Where it is used:

• AI targeting in Google, Meta and TikTok campaigns
• Behavioural segmentation (by form, click and visit data)
• Geographic targeting (city, district, device type)
• Dynamic remarketing

Benefits:

• Unnecessary impressions and wasted budget are prevented
• Conversion rates (CVR) increase
• Patient acquisition cost (CPL/CPA) falls

Artificial intelligence in content production and SEO

Generative artificial intelligence is now at the centre of content production in healthcare.
LLM-based systems can produce blog posts, email content, descriptions and information texts around targeted keywords.

Where it is used:

• Blog and SEO content (for example "the recovery process after laser eye treatment")
• Website copy, email campaigns
• Social media posts and patient information messages
• Image production (banners, social media designs, 3D simulations)

Benefits:

• Up to 80% faster content production
• Visibility at the top in search engines
• Consistency in the brand language

Ad optimisation and performance tracking

Machine learning algorithms analyse ad campaigns' performance continuously.
After every click they calculate which keyword or image brings better conversion and offer automatic optimisation recommendations.

Where it is used:

• Google Ads, Meta Ads and YouTube campaign optimisation
• Keyword, copy and image performance analysis
• AI-supported bid strategies
• Real-time ROI monitoring panels

Benefits:

• Data-driven campaign management
• An increase in return on ad spend (ROAS)
• A reduction in manual optimisation time

Digital reputation and sentiment analysis

Artificial intelligence can measure brand perception by analysing patient reviews and social media posts.
With sentiment analysis, positive and negative comments are classified and summary reports presented to management.

Where it is used:

• Google My Business review analysis
• Social media sentiment analysis
• Satisfaction scoring (NPS)
• A crisis management alert system

Benefits:

• An increase in brand credibility
• Real-time patient satisfaction tracking
• Rapid response to negative experiences

5. Artificial Intelligence in Hospital Management and Operations

Artificial intelligence makes a difference not only in clinical processes but in hospital management, operational planning and financial performance tracking too.
For today's healthcare organisations, "digital transformation" means making the right decision at the right time, based on the right data.

AI-supported management systems optimise the hospital's whole operation and thereby both reduce costs and make resource use as efficient as possible.

Artificial intelligence in appointment, resource and staff planning

Machine learning-based algorithms analyse past appointment data and predict patient volume and no-show rates.
The system can thereby forecast on which days and at which hours demand will rise for which clinic or doctor.

Examples of use:

• Dynamic appointment planning (staff distribution according to busy hours)
• Optimising operating theatre, laboratory or bed capacity
• Automatic recommendations in shift planning

Benefits:

• A reduction in waiting times
• Efficiency in resource use

Artificial intelligence in finance and revenue cycle management

One of healthcare organisations' most important difficulties is managing the revenue cycle transparently and without error.
Artificial intelligence audits the accuracy of invoices, insurance transactions and service coding and thereby minimises revenue loss.

Examples of use:

• Automatic detection of invoice verification and coding errors
• Models predicting insurance denial rates
• Smart notification systems for shortening collection times

Benefits:

• Improved cash flow
• A reduction in financial errors
• Revenue growth and sustainable profitability

Artificial intelligence in stock, procurement and logistics

AI-supported forecasting models optimise medical supplies, drugs and consumables according to consumption trends.
These systems prevent holding unnecessary stock while also reducing the risk of running out of critical products.

Examples of use:

• Forecasting demand for supplies
• Automatic purchasing recommendations
• Supplier performance analysis

Benefits:

• A reduction in stock-out rates
• Cost savings
• Operational continuity

Quality, accreditation and performance monitoring

Artificial intelligence tracks hospitals' quality indicators (KPIs) automatically, detects deviations and produces reports.
Thanks to these systems, managers can improve processes with real-time alerts.

Examples of use:

• Monitoring patient waiting times and satisfaction scores
• Analysing clinical quality metrics such as infection rate and length of stay
• Automatic data collection for accreditation documents

Benefits:

• Ease of management through decision support systems
• A culture of continuous improvement taking root

Artificial intelligence in human resources management and training

Artificial intelligence can analyse employee performance data and draw up competence maps, ensuring the right staff are assigned to the right roles.
With micro-learning systems, automatic training content can also be offered in the areas staff need.

Examples of use:

• Shift optimisation and predicting absence
• Performance analytics and measuring motivation
• AI-supported training modules ("virtual assistant onboarding", for example)

8. Data Security, Data Protection Law and Ethical Principles

Health data is one of the most sensitive kinds of personal data.
A patient's name, diagnosis, treatment history or genetic information matters greatly not only in clinical processes but in terms of ethical responsibility and legal obligations.
When artificial intelligence systems are developed, protecting, anonymising and processing that data fairly should be the core priority.

Why data security matters in healthcare

Artificial intelligence applications need large amounts of data in order to produce accurate results. But every piece of data brings privacy risk with it.
The following principles should therefore be observed in data management:

• Anonymisation and masking:
  Information that could reveal the patient's identity (name, national ID number, contact details) should be separated out of the system.
• Data access control:
  Nobody other than authorised users should be able to reach a patient's data.
  Role-based access (RBAC) and log management play a critical role here.
• Data storage and encryption:
  Data should be stored and transferred using methods compliant with international security standards (AES-256, TLS 1.3 and so on).
• Server location and compliance:
  Under Türkiye's data protection law (KVKK), health data must be held on local servers; transfer abroad is subject to specific permissions.

Compliance with KVKK and international regulation

In Türkiye, processing health data falls into the special category of data under Personal Data Protection Law no. 6698 (KVKK).
Globally, GDPR (EU), HIPAA (US) and the ISO 27701 / 27001 standards should also be taken as references.

Core legal requirements:

• Personal health data cannot be processed without explicit consent.
• Data can only be used for the stated purpose.
• If it is to be shared, it should be transferred in "anonymised" form.
• The system should support users' right to delete or access their data.

At DijitalPi we bring the data flows in every artificial intelligence infrastructure we use into line with KVKK and GDPR,
and apply the principles of data minimisation and logging in API and integration processes.

Ethical artificial intelligence principles

Using artificial intelligence in medicine requires not only technical but ethical responsibility.
Because an algorithm's decision can directly affect a person's health, it must be "fair, transparent and explainable".

Ethical principles:

• Fairness: the model being cleared of biases such as race, gender or age.
• Explainability: being able to explain why the artificial intelligence gave that result.
• Accountability: final responsibility for decisions resting with a human (the doctor, the manager).
• Transparency: informing the patient about how and why their data is used.
• Traceability: model outputs being recorded and auditable retrospectively.

A safe AI ecosystem: technology + regulation + people

Artificial intelligence systems are made safe not only by technical security but by organisational policy and human supervision.
Hospitals should therefore establish this triple balance for data governance:

1. Technological security: encryption, access management, monitoring systems.
2. Legal compliance: integration of the KVKK, GDPR and HIPAA standards.
3. Human supervision: human control in decision-making through clinical and ethics committees.

9. Starting an Artificial Intelligence Project: A Roadmap for Hospitals

Every digital transformation project starts with an idea, but reaching success requires a clear plan.
For hospitals, technology investment genuinely working is possible not only by setting the system up but by managing it with the right data, the right goal and the right people.
The steps below are a practical roadmap healthcare organisations can use when planning modern data projects.

1. Clarifying the need and the goal

First, you need to define clearly what you want to change.
When the problem definition is clear, the solution's impact is clear too.

• Is improvement aimed at clinical processes, or at operational efficiency?
• By which criteria will success be assessed?
• Which department or team owns the process?

2. Preparing the data and ensuring quality

A good result is born of clean, reliable data.
In healthcare organisations, information is generally scattered across hospital information systems, CRM, laboratory, PACS or call centre systems.
Bringing that data together, standardising it and anonymising it is the foundation of the process.

• Missing and incorrect records are cleaned.
• Data is de-identified in line with the data protection law.
• A single source of truth is created.

Once the data flows in an orderly way, the later steps speed up by themselves.

3. Starting with a pilot

Every project should start with a small trial.
A narrow but high-impact area is chosen — appointment forecasting, volume planning or image analysis, for example.
The aim is to test the practice, not the theory.

At the end of the pilot period the system's accuracy rate, cost, processing time and user feedback are analysed.
This stage is the safest way of seeing whether the technology genuinely works.

4. Integration and real use

When the pilot gives a positive result, the system is integrated into the hospital's existing structure.
The data flow is connected to the hospital information system, CRM, laboratory or advertising accounts.
Clinical and operational teams can thereby see the same data at the same time.

Well-done integration makes decision-making easier.
Information such as appointment volume, conversion rate and revenue distribution can be monitored in real time on management dashboards.

5. Involving the teams in the process

Technology alone does not bring success.
The doctors, nurses, call centre staff and managers who use the system are the most important part of this process.
With user-friendly interfaces, short training sessions and feedback loops, everyone becomes part of the system.

At the point where a model decides, a human still has the last word — that balance builds trust.

6. Measuring performance and seeing the impact

Once the application starts running, the results obtained are monitored regularly.
Questions such as how efficiently the process is running, how costs are changing and how patient satisfaction is affected are answered.

At this stage DijitalPi combines CRM data and offline conversion records to make the project's real financial impact visible.
How not only the system but the investment is performing thereby becomes clear.

7. A culture of continuous improvement

No system works perfectly forever in the state it was first set up.
Over time new data arrives, needs change and expectations grow.
Regular monitoring, data updating and optimisation processes should therefore be made permanent.

Once that culture takes root, every new piece of data offers the organisation an opportunity to learn.

10. Successful Examples From Türkiye and Around the World

In different parts of the world, healthcare organisations now use artificial intelligence not as pilot trials but as a natural part of their daily operations.
The successes seen in imaging, diagnosis, patient follow-up and marketing show that this transformation produces concrete results both medically and financially.

US – Mayo Clinic: automation in imaging and diagnosis

Mayo Clinic scans thousands of MRI and CT images in its radiology departments with deep learning-based systems.
Thanks to these systems:

• Image assessment time fell by 40%.
• The rate of incorrect reporting fell.
• The time doctors could give per patient increased.

This approach made human resources more efficient as well as delivering clinical accuracy.

UK – NHS (National Health Service): patient follow-up and early warning systems

The UK's NHS uses machine learning systems in chronic disease management and intensive care monitoring.
Early warning algorithms built with real-time data can identify sepsis or heart failure risk in advance.
These systems delivered a fall of up to 15% in hospital readmission rates.

Japan – Fujitsu & Tokyo Medical University: artificial intelligence in eye disease

Computer vision models used in retina screening can detect diabetic retinopathy at an early stage.
Screening time fell to just 5 seconds per person.
This application spread early detection in regions where regular eye screening is not possible.

Europe – Novartis & PathAI collaboration: speed and consistency in pathology analysis

Large research centres in Europe use the PathAI infrastructure to analyse pathology slides.
The system classifies cancer cells within seconds and provides specialists with a second opinion.
Diagnostic accuracy has reached levels of 93%.

Türkiye – measurability in clinical marketing (a DijitalPi application)

DijitalPi is one of the first agencies in Türkiye to integrate offline conversion measurement into healthcare marketing.

With this system:

• Appointments coming from ad clicks began to be tracked through the CRM and advertising panels.
• Patients who converted into treatment were matched with the ad campaigns.
• ROI and patient acquisition cost (CPA) came to be calculated automatically.

As a result of campaign optimisation carried out with this method at a cosmetic clinic:

• The conversion rate rose 42%,
• CPL fell 35%,
• Campaign ROI tripled.

Türkiye – using artificial intelligence for patient experience in healthcare
(a DijitalPi application)

Data collection and analysis infrastructure

Data is the foundation of understanding patient experience.
DijitalPi gathers all the patient data coming from the website, WhatsApp, the call centre and CRM systems under a single roof.
That data is anonymised, standardised and processed for analysis.

Among the data collected:

• Appointment frequency, cancellation rate and procedure type
• The patient's communication channel (web, WhatsApp, social media)
• Conversation content and sentiment analysis
• Post-treatment satisfaction scores (NPS)

This multi-channel data structure lets organisations build a 360° experience map for every patient.

Behaviour and sentiment analysis

Patient reviews and call transcripts are analysed with natural language processing (NLP) models.
The system draws the patient's satisfaction level, concerns and expectations from spoken or written messages.
Managers can monitor that analysis in real time on a dashboard.

This means:

• The processes drawing the most complaints are identified,
• The specialisms with low satisfaction rates are spotted quickly,
• The areas needing training or process improvement become clear.

Sources

1. Junaid Bajwa et al., "Artificial intelligence in healthcare: transforming the practice of medicine", Future Healthc J., 2021. PMC
2. "A Review of the Role of Artificial Intelligence in Healthcare", PMC – NIH. PMC
3. Jenny Cordina, Eduardo Coronado, Penelope Williams & Sarah Greenberg, "Harnessing AI to reshape consumer experiences in healthcare", McKinsey, November 2024. McKinsey & Company
4. "AI in healthcare: The future of patient care and health management", Mayo Clinic Press. Mayo Clinic McPress
5. "Benefits and Risks of AI in Health Care: Narrative Review", IJMR, 2024. i-JMR
6. "The Role Of AI In Enhancing The Patient Experience", Lumen blog, August 2024. Lumen Blog
7. "What Artificial Intelligence Means for Health Care", JAMA Network. JAMA Network