Clinicians and healthcare professionals need to familiarize themselves with AI, including its applications and appropriate implementation. Here I am explaining about AI in the context of the disease life cycle.
4. Why Tech
● 70% agreed, tech- positive transformation on
healthcare
● 63% consultations to be remote in 10 years
● 56% - clinical decision support tools use AI in
10 years’ time
https://www.elsevier.com/connect/clinician-of-the-future
5. AI in Clinical Research
1. Preventive Analytics & Predictive Models
2. Precision Diagnosis
3. Personalized Therapy
4. Personalized Dosing
17. AI/ML in Drug development,
Need?
“ Evolution is not a force but a process “
• High attrition rate
• Increased expenditure
• Increase volume of data
• Increase global regulatory requirement
• Challenge in timely processing
18. Role of AI in Drug-Discovery
• Better compounds going into clinical trials
• Better target understanding
• Better conductance of trials
• Better Post Marketing surveillance
22. Drug Repurposing
• Drug repositioning, drug retasking, drug reprofiling, drug rescuing, drug recycling,
drug redirection, and therapeutic switching
• Process of identifying new therapeutic use(s)
for old/existing/available drugs
• Highly efficient, time saving, low-cost and
minimum risk of failure, increases the
success rate
23. 4b. Clinical Trials
• Half of time and investment
• 86% of all trials do not meet enrolment
timelines
• 1/3rd of all Phase III trials fail owing to
enrolment problems
• Patient recruitment takes up 1/3rd of duration
• A 32% failure rate because of patient
recruitment problems
24. AI models used to enhance
patient cohort selection
• Automatically analyze EMR and clinical
trial eligibility databases, find matches
between specific patients and recruiting
trials, and recommend these matches to
doctors and patients
• Predict the risk of dropout for a specific
patient
25. AI in Clinical Research
1. Preventive Models and Predictive
Analytics
2. Precision Diagnosis
3. Personalized Therapy
4. Personalized Dosing
26. 4c. Pharmacovigilance
• Insertion of structured and unstructured
content:
• NLP and ML to extract ICSR information
• AI for decision-making: AI may play an
important role in predicting the new ADR
27. AI/ML in PV, Need?
“ Evolution is not a force but a process “
• Increase volume of data
• Increase global regulatory requirement
• Increased workload
• Increased expenditure
• Challenge in timely processing
33. Advantages
• Improve the quality and accuracy
• Cost-effective
• Timely manner
• Can handle diverse types data formats
• Transparent data sharing with regulators,
prescribers
• Prediction of new ADR