WorksheetsOptimization and Algorithms in Healthcare Worksheet
Total questions: 25
Worksheet time: 15mins
A hospital experiences unpredictable emergency admissions every night. Which optimization technique would MOST effectively adapt to changing patient load while avoiding getting trapped in local minima?
Simple Linear Regression
Simulated Annealing
Fixed-rule-based scheduling
Manual allocation by staff
In ambulance routing, traffic changes rapidly. Which algorithm is MOST suitable because it updates each agent’s path based on both personal and shared experience?
Genetic Algorithm
Particle Swarm Optimization
Ant Colony Optimization
Gradient Descent
A hospital wants to minimize drug expiry while ensuring sufficient stock. Demand fluctuates seasonally. Which approach BEST handles uncertainties and provides near-optimal solutions?
Brute force enumeration
Spreadsheet fixed reorder formula
Metaheuristic optimization
Manual estimation by pharmacist
A large hospital needs to schedule nurses while considering fatigue, night shift fairness, emergency backup, and personal preferences. Which type of model is MOST suitable?
Single deterministic scheduling equation
Hybrid model combining GA + ML predictions
Simple FCFS (first come first served)
Manual shift rotation
A smart hospital plans to implement AI-based decision support that predicts ICU demand and starts reallocating resources automatically. Which future trend does this BEST represent?
Paper-based reporting
Static planning with monthly meetings
Data-driven optimization with predictive analytics
Increasing number of manual staff approvals
Genetic algorithms are primarily inspired by:
Newton’s laws
Mendelian genetics and natural selection
Boolean algebra
Electrical circuits
In Genetic Algorithms, crossover is used to:
The probability of randomly altering genes in GA is called:
Learning rate
Mutation rate
Fitness score
Convergence rate
Particle Swarm Optimization is inspired by:
Cellular division
Bird flocking and fish schooling
Brain neurons
Ant colonies
In PSO, the term personal best refers to:
Best solution found by entire swarm
Best solution found by a single particle
Random solution allocation
Initial guess
Simulated Annealing is inspired by:
Thermodynamics cooling processes
Insect behavior
Genetic mutation
Neural networks
Simulated annealing avoids local minima using:
Mutation
Temperature-controlled probability
Fitness scaling
Elitism
Ant Colony Optimization mimics:
Pathfinding using pheromone trails
Binary decision trees
Medical diagnosis
Chemical reactions
In ACO, pheromone evaporation helps to:
Intensify local search
Prevent premature convergence
Reduce algorithm speed
Hybrid Optimization models:
Use only deterministic algorithms
Combine two or more optimization techniques
Do not work for healthcare
Ignore global minima
Nurse scheduling optimization deals mainly with:
Predicting patient survival
Assigning nurses to shifts respecting constraints
Diagnosing diseases
Telemedicine system coding
Ambulance routing optimization is similar to:
Sorting algorithms
Traveling Salesman Problem
Histogram equalization
Noise filtering
Operating room allocation focuses on minimizing:
DNA sequencing errors
Waiting time and idle time
Body temperature fluctuations
Color segmentation
Bed management in hospitals improves:
Network speed
Resource utilization
Air conditioning
Internet connectivity
Patient flow optimization primarily targets:
Improving website traffic
Minimizing bottlenecks and waiting time
Maximizing retail sales
Battery usage
Drug inventory management ensures:
High power consumption
Medicine availability with minimal expiry losses
Unlimited stock purchase
Random distribution
Emergency response optimization can rely on:
Clustering of disease images
Predictive demand and routing algorithms
Handwritten character recognition
Signal modulation
Medical equipment scheduling optimization reduces:
Revenue
Idle diagnostic machines and delays
Bed count
Patient records
AI-based decision support systems assist doctors in:
Real-time monitoring and analytics
Laundry scheduling
Hospital canteen menu
Light switching
Future smart hospital trends include:
Manual record keeping
Paper-based management
Real-time data-driven optimization
Random staffing patterns
