Darsons ICT & Machine Learning Learning Pathway

Pharm-D Professional Years I–V | Darsons Institute of Science & Technology, Gujranwala

Program theme: Digital Skills → Data Literacy → Machine Learning → Pharmaceutical Applications → AI-Enabled Innovation

The proposed pathway integrates Information and Communication Technology (ICT), data analysis, computational thinking, and machine learning into all five professional years of the Pharm-D program. Students progress from basic digital competence in Year I to supervised, research-oriented pharmaceutical AI projects in Year V.

The aim is not to turn every pharmacy student into a software engineer. It is to develop pharmacists who can use digital tools confidently, interpret data critically, understand machine learning, evaluate AI-generated information, and apply technology responsibly in pharmaceutical practice and research.

1. Five-year progression at a glance

Year I — Digital Foundations

Learn digital tools

Build computer literacy, online research skills, academic documentation, spreadsheets, presentations, digital safety, and introductory AI literacy.

Capstone: Digital Pharmacy Learning Portfolio

Year II — Data & Computational Thinking

Understand data

Learn spreadsheet analytics, basic statistics, data visualization, data quality, and introductory programming logic.

Capstone: Pharmaceutical Data Analysis Report

Year III — Machine Learning Fundamentals

Build simple models

Explore supervised and unsupervised learning, model evaluation, data preparation, and introductory pharmaceutical applications.

Capstone: Supervised Educational ML Project

Year IV — Applied Pharmaceutical AI

Apply to pharmacy

Explore clinical and industrial pharmacy data, pharmacovigilance, quality assurance, research analytics, and decision-support limitations.

Capstone: Pharmaceutical AI Case Study

Year V — Research, Innovation & Responsible AI

Design and evaluate

Develop a supervised capstone, evaluate evidence and model limitations, communicate findings, and consider ethics and implementation.

Capstone: Final-Year Digital Pharmacy Innovation Project

2. Detailed year-wise curriculum

The following is a proposed curriculum framework for institutional planning. Each year can be delivered through a dedicated module, integrated classroom activities, laboratory sessions, and project work alongside the existing Pharm-D subjects.

Year I — Digital Foundations for Pharmacy

Recommended duration: 12–16 guided weeks across the academic year

Module

Core learning content

Practical activity

1. Digital Literacy

Computer operations, file management, cloud storage, digital collaboration

Organize a digital academic portfolio

2. Academic Productivity

Word processing, presentations, spreadsheets, document formatting

Prepare a formatted pharmaceutical science assignment

3. Online Research Skills

Search strategies, scholarly databases, source credibility, citation basics

Find and evaluate five credible sources on a medicine

4. Spreadsheet Fundamentals

Data entry, formulas, sorting, filtering, charts

Create a medicine information or laboratory data sheet

5. Introduction to AI

AI concepts, generative AI, prompts, strengths and limitations

Compare an AI-generated explanation with textbooks or reliable references

6. Digital Safety & Ethics

Privacy, passwords, plagiarism, copyright, patient confidentiality

Identify risks in sample digital pharmacy scenarios

Learning outcomes

By the end of Year I, students should be able to:

• Use common digital tools for academic and professional tasks.
• Locate, assess, organize, and cite credible scientific information.
• Create basic spreadsheets, charts, presentations, and digital records.
• Explain introductory AI concepts and identify common AI errors.
• Apply basic privacy, cybersecurity, academic integrity, and confidentiality principles.

Assessment plan

• Digital skills practical test — 25%
• Online research and referencing assignment — 20%
• Spreadsheet task — 20%
• AI verification and digital ethics exercise — 15%
• Digital Pharmacy Learning Portfolio — 20%

Year II — Data Literacy, Statistics & Computational Thinking

Recommended duration: 14–18 guided weeks

Module

Core learning content

Practical activity

1. Pharmaceutical Data Management

Data types, variables, coding, data dictionaries, data cleaning

Clean a sample medicine inventory dataset

2. Spreadsheet Analytics

Logical functions, lookups, pivot tables, conditional formatting

Analyze stock levels and expiry dates in simulated inventory data

3. Statistics for Data Analysis

Mean, median, standard deviation, distributions, correlation

Summarize and interpret a sample laboratory dataset

4. Data Visualization

Bar charts, line charts, scatter plots, dashboards

Create a dashboard of simulated medicine-use data

5. Computational Thinking

Decomposition, patterns, algorithms, flowcharts, logic

Design a flowchart for checking a sample prescription

6. Introduction to Programming

Variables, conditions, loops, functions, simple data structures

Write or adapt a beginner-level script to summarize data

7. Data Quality & Governance

Missing values, bias, anonymization, data provenance

Identify errors and privacy risks in a sample dataset

Learning outcomes

Students should be able to:

• Prepare, clean, summarize, and visualize structured data.
• Select suitable descriptive statistics for basic pharmaceutical questions.
• Explain how data quality and sampling affect conclusions.
• Design simple algorithms and understand introductory programming logic.
• Recognize privacy risks, biased data, and misleading graphs.

Assessment plan

• Data cleaning practical — 20%
• Statistics and interpretation assignment — 20%
• Dashboard or visualization project — 25%
• Computational thinking/programming task — 15%
• Data governance and ethics viva — 20%

Year II capstone: Pharmaceutical Data Analysis Report using a synthetic or properly de-identified dataset, with a research question, visualizations, interpretation, limitations, and references.

Year III — Machine Learning Fundamentals

Recommended duration: 16–20 guided weeks

Module

Core learning content

Practical activity

1. ML Concepts

Features, labels, datasets, training, validation, testing

Map a pharmacy question to a possible ML task

2. Data Preparation

Missing data, encoding, scaling, train/test split, leakage

Prepare a small, synthetic dataset for analysis

3. Supervised Learning

Linear/logistic regression, decision trees, classification

Train a simple model on a simulated dataset

4. Unsupervised Learning

Clustering, similarity, exploratory pattern identification

Explore patterns in a synthetic medicine-use dataset

5. Model Evaluation

Accuracy, precision, recall, F1 score, confusion matrix, MAE/RMSE where appropriate

Compare model results and explain errors

6. Responsible ML

Bias, overfitting, interpretability, uncertainty, reproducibility

Review a model card or critique a sample AI output

7. Reproducible Workflows

Notebooks, documentation, versioning basics, reporting

Produce a documented analysis notebook

Learning outcomes

Students should be able to:

• Distinguish machine learning from conventional programming and generative AI.
• Explain the purpose of features, labels, training data, and test data.
• Prepare a basic dataset and train or run a simple educational model.
• Choose and interpret appropriate evaluation metrics.
• Identify overfitting, data leakage, bias, uncertainty, and limitations.
• Present results without claiming that an experimental model is clinically validated.

Assessment plan

• ML concepts quiz — 15%
• Data preparation practical — 20%
• Model-building or guided notebook exercise — 25%
• Model evaluation and critique — 20%
• Reproducible mini-project and presentation — 20%

Year III capstone: Supervised Educational ML Project. Students document the question, dataset, method, evaluation, errors, limitations, and ethical considerations. Use simulated or public educational datasets, not identifiable patient data.

Year IV — Applied AI in Pharmaceutical Sciences

Recommended duration: 16–20 guided weeks, integrated with relevant professional subjects

Module

Core learning content

Practical activity

1. AI in Drug Discovery

Virtual screening concepts, molecular representations, prediction limitations

Critically review an educational drug-discovery workflow

2. Formulation & Quality

Experimental data, process variables, prediction and optimization concepts

Analyze a simulated formulation or quality-control dataset

3. Pharmacovigilance Analytics

Adverse event data, signal detection concepts, causality limitations

Explore a synthetic adverse-event dataset

4. Clinical & Medication Data

Data quality, medication-use patterns, clinical decision-support concepts

Analyze fictional medication-use cases

5. Research Analytics

Study design, variable selection, confounding, reproducibility

Critique a published AI-related pharmaceutical study

6. Decision Support & Human Oversight

Clinical workflow, explainability, uncertainty, validation

Review a simulated decision-support scenario and identify where pharmacist judgment is required

7. AI Governance

Privacy, consent, security, bias, accountability, applicable regulations

Prepare a risk checklist for a proposed pharmacy AI application

Learning outcomes

Students should be able to:

• Explain potential applications of AI in pharmaceutical discovery, formulation, quality, and medication-related research.
• Critically evaluate the methodology and evidence behind a pharmaceutical AI study.
• Interpret model performance in the context of a defined use case.
• Identify when model outputs could be misleading or unsafe.
• Recommend appropriate validation, documentation, privacy controls, and professional oversight.
• Distinguish research prototypes from approved or clinically validated tools.

Assessment plan

• Pharmaceutical AI literature review — 20%
• Applied dataset or case-study analysis — 25%
• Critical appraisal of a published study — 20%
• AI risk and ethics assessment — 15%
• Group presentation and individual viva — 20%

Year IV capstone: Pharmaceutical AI Case Study. Each group evaluates a defined use case and submits a report covering the problem, evidence, data requirements, method, risks, limitations, and proposed validation.

Year V — Research, Innovation & Responsible AI

Recommended duration: 16–20 guided weeks or integrated into the final-year research schedule

Module

Core learning content

Practical activity

1. Research Problem Design

Research questions, objectives, feasibility, literature review

Develop a proposal for a pharmacy-related digital problem

2. Advanced Data Analysis

Appropriate model selection, evaluation, sensitivity analysis

Reassess a dataset and compare suitable analytical methods

3. AI-Assisted Research

Literature discovery, structured extraction, drafting support, source verification

Audit AI-assisted research notes against original sources

4. Prototype Development

Requirements, workflow design, interface mock-ups, testing

Create a non-clinical prototype or proof of concept

5. Validation & Reproducibility

Robustness, generalizability, external validation concepts, reporting

Test a prototype with predefined scenarios and document failure cases

6. Ethics & Implementation

Governance, privacy, stakeholder needs, implementation barriers

Develop a risk register and implementation plan

7. Communication & Commercialization

Poster, technical report, pitch, intellectual property awareness

Present the project to faculty and invited reviewers

Learning outcomes

By the end of Year V, students should be able to:

• Design a feasible, evidence-based digital pharmacy research project.
• Select and justify an appropriate analytical approach.
• Critically assess performance, uncertainty, bias, and generalizability.
• Document methods and results sufficiently for review and reproducibility.
• Communicate findings to scientific and non-technical audiences.
• Propose responsible implementation steps without overstating clinical readiness.

Assessment plan

• Research proposal — 15%
• Technical work, analysis, or prototype — 25%
• Validation, reproducibility, and risk report — 20%
• Final dissertation/report or project document — 20%
• Poster/oral presentation and viva — 20%

Year V capstone: Digital Pharmacy Innovation Project. Students may develop a data dashboard, educational tool, inventory analytics prototype, literature-analysis workflow, or a supervised research model. Any patient-facing or clinical decision-support application requires appropriate institutional oversight and validation; student prototypes must not be used to make real patient-care decisions.

3. Recommended teaching and practical delivery model

A consistent delivery structure will help Darsons integrate this pathway with the existing Pharm-D curriculum without overloading students.

Concept session

Understand the topic, terminology, examples, and relevance to pharmacy.

30%

Guided practical

Work with digital tools, datasets, spreadsheets, notebooks, or simulations.

40%

Project and reflection

Solve a pharmacy-related problem, present results, and evaluate limitations.

30%

These percentages are a suggested distribution of learning activities, not the formal assessment weightings listed for each year.

Suggested weekly timetable

• One 60-minute concept session
• One 90-minute supervised practical session
• One 30-minute independent learning or reflection activity

Total: approximately 3 hours per week. Institutions may adapt this schedule according to faculty availability, credit-hour requirements, and the approved Pharm-D curriculum.

4. Core practical projects across five years

Use this progression to ensure that every student's portfolio demonstrates growth from basic ICT to applied pharmaceutical innovation.

Year I — Digital Pharmacy Portfolio

Compile verified pharmaceutical references, a formatted report, a spreadsheet, a presentation, and an AI fact-checking exercise.

Evidence: Portfolio files and practical demonstration.

Year II — Smart Inventory Dashboard

Analyze simulated medicine stock, expiry dates, reorder levels, and trends using spreadsheets and charts.

Evidence: Dashboard, data dictionary, and interpretation report.

Year III — Introductory ML Model

Build or run a guided model using synthetic data, compare metrics, and document errors and limitations.

Evidence: Notebook, model evaluation, and viva.

Year IV — Pharmaceutical AI Case Study

Evaluate a proposed AI application in quality control, drug discovery, pharmacovigilance, or medication-use research.

Evidence: Literature review, case analysis, and risk assessment.

Year V — Digital Pharmacy Innovation

Develop and evaluate a research prototype or analytical tool, with a documented methodology, testing plan, and implementation considerations.

Evidence: Final report, demonstration, poster, and oral defense.

5. Standard assessment rubric

Use a common rubric across all professional years while increasing the expected complexity and independence at each stage.

Assessment criterion

Weight

Conceptual understanding

15%

Practical digital/technical skills

25%

Data quality and analytical reasoning

20%

Pharmaceutical relevance and interpretation

15%

Ethics, privacy, and responsible AI

10%

Documentation, communication, and presentation

15%

Total

100%

Progression standard: Year I emphasizes correct tool use; Year II emphasizes accurate data handling; Year III emphasizes sound model evaluation; Year IV emphasizes pharmaceutical interpretation; Year V emphasizes independent, reproducible, and responsible project work.

6. Suggested software and learning resources

Area

Suggested tools or resources

Digital productivity

Microsoft Office or LibreOffice

Data analysis

Excel or LibreOffice Calc; Google Sheets where appropriate

Programming

Python, Jupyter Notebook, Google Colab

Visualization

Spreadsheet charts, Matplotlib, or other approved visualization tools

Machine learning

scikit-learn and beginner-level educational notebooks

Scientific research

PubMed, Google Scholar, and other available scholarly databases

Version control and documentation

Git/GitHub or an institution-approved alternative

Responsible AI

Institutional AI-use policy, privacy guidance, and source-verification checklists

Tool selection should depend on availability, internet access, student device capability, software licensing, and faculty expertise. Students should not be required to purchase expensive software to complete core learning outcomes.

7. Faculty and institutional implementation

To implement the pathway effectively at Darsons, establish the following:

1. Program coordinator: Oversees the five-year pathway, annual learning outcomes, assessments, and curriculum alignment.
2. ICT/AI instructor: Teaches digital literacy, data analysis, programming fundamentals, and introductory machine learning.
3. Pharmacy subject faculty: Ensure that exercises are scientifically relevant to pharmaceutics, pharmacology, clinical pharmacy, pharmaceutical chemistry, and research.
4. Practical laboratory: Provides suitable computers, approved software, datasets, and secure storage for student work.
5. Project review panel: Reviews final-year projects for scientific validity, feasibility, ethics, and appropriate claims.
6. Digital safety policy: Defines permitted AI use, disclosure of AI assistance, plagiarism rules, data privacy, and procedures for handling sensitive information.

Recommended progression checkpoints

• End of Year I: Can use digital tools and verify online scientific information.
• End of Year II: Can clean, summarize, and visualize data.
• End of Year III: Can explain, run, and evaluate a basic ML workflow.
• End of Year IV: Can critically assess a pharmaceutical AI use case.
• End of Year V: Can present a documented, responsible, evidence-based digital pharmacy project.

8. Final institutional outcome

By the completion of the five-year pathway, every Pharm-D graduate should have a portfolio demonstrating digital competence, data literacy, introductory machine learning knowledge, pharmaceutical application, and responsible technology use.

This pathway is designed as a proposed Darsons academic framework. Before formal launch, align it with the university-approved Pharm-D curriculum, available teaching capacity, assessment regulations, and applicable institutional requirements. Clinical AI tools should not be represented as validated or used in patient care solely because they have been studied or demonstrated by students.