Machine Learning Fundamentals — MCQs
Based on the provided image, which of the following is the correct diagnosis?
What is the classification of intelligence corresponding to an IQ score of 90-109?
Classification system of bone tumors is -
Which of the following bone lesions is characterized by the 'fallen fragment sign,' a radiological feature seen in lytic bone lesions with fluid-filled cavities?
What is the most likely diagnosis based on the chest radiographs shown below?
What does this CT chest image show?
A research team develops an AI algorithm using 100,000 CT scans from multiple institutions. The algorithm shows excellent performance (AUC 0.96) but requires extensive computational resources. To deploy it in resource-limited settings, they propose model compression techniques. Evaluate the potential trade-offs and propose the most balanced approach.
A radiology department is evaluating two AI algorithms for fracture detection. Algorithm A has AUC-ROC of 0.95, while Algorithm B has AUC-ROC of 0.92 but provides explainable results showing which image regions influenced its decision. Considering clinical implementation and medicolegal aspects, which statement best evaluates the choice?
A deep learning algorithm for detecting pneumonia on chest X-rays performs excellently on the validation set but poorly on external testing. Analysis reveals the algorithm learned to recognize the hospital logo and text on images from ICU patients (who more likely had pneumonia). What type of bias does this represent?
An AI model for detecting breast cancer on mammography shows sensitivity of 95% and specificity of 85% in a screening population with 1% disease prevalence. A study claims the AI outperforms radiologists who have 90% sensitivity and 90% specificity. Analyze why this comparison may be misleading.
Machine Learning Fundamentals Indian Medical PG Practice Questions and MCQs
Question 1: Based on the provided image, which of the following is the correct diagnosis?
- A. Uterus didelphys
- B. Bicornuate Uterus
- C. Unicornuate Uterus (Correct Answer)
- D. Septate uterus
Explanation: ***Unicornuate Uterus*** - The image distinctly shows **only one fallopian tube and one rudimentary uterine horn** on the right side, indicating a unicornuate uterus. - This malformation results from the **incomplete development of one Müllerian duct**, leading to a single, banana-shaped uterine cavity. *Uterus didelphys* - This condition involves **two completely separate uteri**, each with its own cervix and vagina. - The image does not show evidence of two distinct uterine bodies or cervices. *Bicornuate Uterus* - A bicornuate uterus is characterized by **two uterine horns that fuse caudally**, creating a heart-shaped appearance with a shared cervix. - The image clearly lacks the characteristic heart shape and shows only one functional horn. *Septate uterus* - A septate uterus has a **fibrous or muscular septum** dividing the uterine cavity, while the external uterine contour remains normal. - The image does not show a septum or a normal external uterine contour with an internal division; instead, it presents with a single underdeveloped horn.
Question 2: What is the classification of intelligence corresponding to an IQ score of 90-109?
- A. Below average
- B. Average (Correct Answer)
- C. Slightly below average
- D. Above average
Explanation: ***Average*** - An **IQ score** range of **90-109** is traditionally classified as **Average** intelligence. - This range represents the **mean** and surrounding **standard deviation** of IQ scores in the general population. *Below average* - This classification usually corresponds to IQ scores in the range of **70-79** or **80-89**, depending on the specific scale. - It does not represent the central tendency of the population's intelligence. *Slightly below average* - This category typically corresponds to IQ scores in the range of **80-89**. - It falls just below the average range but is not as low as the "below average" classification. *Above average* - This classification is typically assigned to IQ scores that are in the range of **110-119** or higher. - It signifies cognitive abilities that are greater than the majority of the population.
Question 3: Classification system of bone tumors is -
- A. Enneking (Correct Answer)
- B. Edmonton
- C. TNM
- D. Manchester
Explanation: ***Enneking*** - The **Enneking staging system** is widely used for primary **bone tumors**, particularly sarcomas. - It classifies tumors based on their histological grade, local extension, and presence of metastases, which guides surgical planning and prognosis. *Edmonton* - The **Edmonton classification** is primarily used for **periprosthetic fractures** around hip and knee replacements. - It does not classify primary bone tumors but rather describes fracture patterns related to prosthetic implants. *TNM* - The **TNM (Tumor, Node, Metastasis)** classification is a general staging system used for many types of cancer, but it's not the primary system for bone tumors. - While applicable for some bone cancers, the **Enneking system** provides a more specific functional and anatomical assessment for limb-sparing surgery in bone sarcomas. *Manchester* - The **Manchester staging system** is primarily used for **lymphoma**, particularly Hodgkin lymphoma. - It describes the extent of lymph node involvement and extralymphatic disease, completely unrelated to bone tumors.
Question 4: Which of the following bone lesions is characterized by the 'fallen fragment sign,' a radiological feature seen in lytic bone lesions with fluid-filled cavities?
- A. Adamantinoma
- B. Aneurysmal bone cyst
- C. Simple bone cyst (Correct Answer)
- D. Osteosarcoma
Explanation: ***Simple bone cyst*** - The **'fallen fragment sign'** is a **pathognomonic radiological feature** of simple bone cysts (unicameral bone cysts). - This sign occurs when a **pathological fracture** through the cyst allows a fragment of cortical bone to fall into the fluid-filled cavity and settle dependently at the bottom, visible on upright radiographs. - Simple bone cysts are benign, fluid-filled lesions commonly affecting the **proximal humerus and proximal femur** in children and adolescents. *Aneurysmal bone cyst* - This is a **benign, blood-filled, expansile lesion** with multiple septated compartments. - Characteristic radiological feature is **fluid-fluid levels** on MRI or CT due to blood products of different densities. - Does NOT typically demonstrate the 'fallen fragment sign' - the multi-loculated nature prevents free-floating bone fragments. *Adamantinoma* - This rare **malignant bone tumor** primarily affects the **tibia** and presents as a lytic lesion, often with sclerotic borders. - It is a solid tumor that does not form simple fluid-filled cavities or demonstrate the 'fallen fragment sign.' *Osteosarcoma* - This is a **highly malignant bone tumor** characterized by osteoid production and bone destruction. - Often presents with periosteal reaction like a **'sunburst' pattern or Codman's triangle**. - It is a solid, aggressive tumor that does not form fluid-filled cavities that would exhibit a 'fallen fragment sign.'
Question 5: What is the most likely diagnosis based on the chest radiographs shown below?
- A. Lung abscess
- B. Lobar emphysema
- C. Segmental collapse (Correct Answer)
- D. Bronchiectasis
Explanation: ***Segmental collapse*** - The frontal image shows a **wedge-shaped opacity** in the right upper lobe, and the lateral view reveals a **triangular area of increased density** consistent with collapsed lung tissue. - This pattern, particularly the triangular density on the lateral view and volume loss indicated by the position of the **minor fissure (white arrow)**, points towards segmental collapse. *Lung abscess* - A lung abscess typically presents as a **cavity with an air-fluid level**, which is not depicted in these images. - The lesion shown is mostly **solid and dense**, unlike the characteristic appearance of an abscess. *Lobar emphysema* - Lobar emphysema involves **overinflation of a lung lobe**, characterized by increased lucency and vascular attenuation, which is the opposite of the findings here. - There is no evidence of **air trapping** or **hyperinflation** in the images provided. *Bronchiectasis* - Bronchiectasis is characterized by **permanent abnormal dilation of the bronchi**, often seen as "tram tracks" or "ring" opacities on imaging. - The images do not show these specific findings; instead, they indicate a loss of lung volume.
Question 6: What does this CT chest image show?
- A. Consolidation
- B. Pneumothorax
- C. Pleural effusion
- D. Segmental collapse (Correct Answer)
Explanation: ***Segmental collapse*** - The CT image shows loss of lung volume in a specific segment, indicated by the **crowding of bronchi and vessels in the affected area**, which is suggestive of atelectasis or collapse. - The black arrow points to the collapsed segment, which appears as a **densified, airless region within the lung parenchyma**, consistent with segmental collapse. *Consolidation* - **Consolidation** typically presents as an area of increased opacification due to alveolar filling with exudate or fluid, but without significant loss of lung volume. - Unlike collapse, consolidation generally **retains the lung architecture** and does not show crowding of vessels and bronchi. *Pneumothorax* - A **pneumothorax** is characterized by the presence of air in the pleural space, which would appear as a dark, air-filled space between the lung and the chest wall. - This typically leads to a **collapsed lung that is displaced medially** and no longer touches the chest wall, which is not seen here. *Pleural effusion* - **Pleural effusion** is the accumulation of fluid in the pleural space, presenting as a homogenous, gravity-dependent opacity that obscures lung parenchyma. - It would typically cause **blunting of the costophrenic angles** and a meniscus sign, which are not the primary findings indicated by the arrow.
Question 7: A research team develops an AI algorithm using 100,000 CT scans from multiple institutions. The algorithm shows excellent performance (AUC 0.96) but requires extensive computational resources. To deploy it in resource-limited settings, they propose model compression techniques. Evaluate the potential trade-offs and propose the most balanced approach.
- A. Model compression always maintains performance while reducing size
- B. Use knowledge distillation to train a smaller model that mimics the larger model while accepting minimal performance decrease (Correct Answer)
- C. Avoid compression as any performance loss is unacceptable in medical AI
- D. Random pruning of neural network connections is sufficient
Explanation: ***Use knowledge distillation to train a smaller model that mimics the larger model while accepting minimal performance decrease*** - **Knowledge distillation** allows a "student" model to learn the complex features of a "teacher" model, significantly reducing **computational footprint** while preserving high **diagnostic accuracy**. - This approach is the most balanced for **resource-limited settings**, as it optimizes the trade-off between **model size** and the high **AUC** required for clinical safety. *Model compression always maintains performance while reducing size* - This is incorrect because compression techniques like **quantization** or **pruning** often result in some degree of **information loss** or degradation in metric sensitivity. - The goal of compression is to minimize this loss, but it is not a guaranteed consequence of the process. *Avoid compression as any performance loss is unacceptable in medical AI* - While accuracy is critical, failing to compress the model makes it unusable in **edge devices** or areas with low **processing power**, hindering medical access. - Medical AI deployment requires a pragmatic balance between **idealistic performance** and **practical utility** in real-world clinical environments. *Random pruning of neural network connections is sufficient* - **Random pruning** is suboptimal and lacks the strategic precision needed to maintain the **AUC 0.96** performance level required for radiology. - Effective model optimization requires **structured pruning** or **weight-based selection** to ensure critical diagnostic features are not inadvertently deleted.
Question 8: A radiology department is evaluating two AI algorithms for fracture detection. Algorithm A has AUC-ROC of 0.95, while Algorithm B has AUC-ROC of 0.92 but provides explainable results showing which image regions influenced its decision. Considering clinical implementation and medicolegal aspects, which statement best evaluates the choice?
- A. Algorithm A should always be chosen due to superior performance metrics
- B. Algorithm B may be preferred despite lower AUC due to interpretability and accountability (Correct Answer)
- C. AUC-ROC is the only relevant metric for clinical decision making
- D. The difference in AUC is clinically insignificant so both are equivalent
Explanation: ***Algorithm B may be preferred despite lower AUC due to interpretability and accountability*** - **Explainable AI (XAI)** is critical in medicine because it allows clinicians to verify the **reasoning process**, ensuring the algorithm isn't relying on irrelevant artifacts. - High **interpretability** facilitates **medicolegal accountability** and builds trust, which are often prioritized over marginal gains in statistical performance metrics like **AUC-ROC**. *Algorithm A should always be chosen due to superior performance metrics* - Relying solely on **performance metrics** ignores the "black box" problem, where a model may have high accuracy but fail unexpectedly in **real-world clinical scenarios**. - Without **spatial localization** or explanation, clinicians cannot easily distinguish between a true positive and a **spurious correlation** detected by the AI. *AUC-ROC is the only relevant metric for clinical decision making* - **AUC-ROC** measures general discriminatory power but does not account for **clinical utility**, workflow integration, or the safety implications of **false negatives**. - Other metrics such as **Positive Predictive Value (PPV)** and **Explainability** are equally vital for determining if a tool is safe and effective for bedside use. *The difference in AUC is clinically insignificant so both are equivalent* - A difference between **0.95 and 0.92** can be statistically and clinically significant depending on the **prevalence** of the condition and the volume of images processed. - Labeling them as **equivalent** overlooks the qualitative advantage of **explainability**, which fundamentally changes how the radiologist interacts with the software.
Question 9: A deep learning algorithm for detecting pneumonia on chest X-rays performs excellently on the validation set but poorly on external testing. Analysis reveals the algorithm learned to recognize the hospital logo and text on images from ICU patients (who more likely had pneumonia). What type of bias does this represent?
- A. Selection bias
- B. Confounding bias (Correct Answer)
- C. Information bias
- D. Spectrum bias
Explanation: ***Confounding bias*** - In machine learning, this occurs when an algorithm learns a **spurious correlation** between a feature (like a hospital logo) and the outcome (pneumonia) because that feature is non-causally associated with the disease. - The **hospital logo** acts as a **confounding variable** that provides a shortcut for the model, leading to high internal accuracy but poor **generalizability** to external datasets without that logo. *Selection bias* - This involves errors in the **recruitment or retention** of study participants, leading to a sample that does not accurately represent the target population. - While the ICU population represents a specific subset, the core issue here is the algorithm identifying **irrelevant visual markers**, not just the patient selection process. *Information bias* - This refers to errors in how data is **measured, collected, or recorded**, such as recall bias or measurement error. - In this scenario, the images themselves were recorded correctly, but the model's **interpretation logic** was flawed due to external markers rather than an error in the data collection tool. *Spectrum bias* - This occurs when the study population does not reflect the **full range** of disease severity seen in clinical practice, often using only very sick patients and healthy controls. - While using ICU patients could contribute to this, the specific problem of identifying **hospital-specific text or logos** is a hallmark of confounding, not just a narrow disease spectrum.
Question 10: An AI model for detecting breast cancer on mammography shows sensitivity of 95% and specificity of 85% in a screening population with 1% disease prevalence. A study claims the AI outperforms radiologists who have 90% sensitivity and 90% specificity. Analyze why this comparison may be misleading.
- A. The AI has lower positive predictive value despite higher sensitivity (Correct Answer)
- B. The AI has higher negative predictive value in all cases
- C. Specificity is more important than sensitivity in screening
- D. The prevalence is too high for meaningful comparison
Explanation: ***The AI has lower positive predictive value despite higher sensitivity*** - In a low **prevalence** environment (1%), even a small drop in **specificity** leads to a significant increase in **false positives**, which markedly reduces the **Positive Predictive Value (PPV)**. - Despite a sensitivity of 95%, the AI's lower specificity (85% vs 90%) results in more unnecessary follow-up procedures and **recall rates** compared to the radiologist. *The AI has higher negative predictive value in all cases* - While higher sensitivity generally improves **Negative Predictive Value (NPV)**, the NPV is already exceedingly high for both (approx. 99.9%) due to the low **prevalence** of the disease. - A marginal gain in NPV does not necessarily justify a substantial increase in **false alarms** caused by lower specificity. *Specificity is more important than sensitivity in screening* - Neither metric is universally "more important"; the ideal screening tool requires a **balance** to ensure high **sensitivity** (catching cases) without overwhelming the system with **false positives**. - However, in this specific clinical context, the radiologist's higher **specificity** maintains a better diagnostic yield (PPV) than the AI model. *The prevalence is too high for meaningful comparison* - A **prevalence** of 1% is actually typical for **screening mammography** populations; it is not considered too high for statistical analysis. - The comparison is misleading due to the **trade-off** between sensitivity and specificity, not because the prevalence rate is an outlier.
Want unlimited practice?
Get full access to all questions, explanations, and performance tracking.
Start For Free