Machine Learning in Healthcare Flashcards

A convolutional neural network (CNN) trained to detect pneumonia on chest X-rays performs well on training data but poorly on external hospital data. This is best described as:

Answer: Dataset shift or distribution shift

Dataset shift occurs when the statistical distribution of training data differs from deployment data, causing performance degradation on external cohorts.

In survival analysis applied to patient outcomes, the Kaplan-Meier estimator is used to:

Answer: Estimate the probability of surviving past a given time point

The Kaplan-Meier estimator produces a non-parametric survival curve showing the probability of event-free survival over time, accounting for censored observations.

Which type of ML model is most commonly used for structured EHR tabular data in clinical risk scoring?

Answer: Gradient Boosted Trees (e.g., XGBoost)

Gradient boosted tree models like XGBoost consistently outperform deep learning on structured tabular EHR data and offer built-in feature importance.

A healthcare ML model that denies prior authorization more frequently for a specific racial group is exhibiting:

Answer: Algorithmic bias causing disparate impact

Algorithmic bias causes disparate impact when a model's outputs disproportionately disadvantage a protected group, often due to biased training data.

When building a sepsis early-warning model, the AUROC metric measures:

Answer: The model's ability to discriminate sepsis from non-sepsis across all decision thresholds

AUROC (Area Under the ROC Curve) quantifies overall discriminative ability across all classification thresholds, with 1.0 being perfect discrimination.

Which regularization technique is commonly used in neural networks to prevent overfitting by randomly deactivating neurons during training?

Answer: Dropout

Dropout randomly sets a fraction of neuron activations to zero during each training step, forcing the network to learn redundant representations and reducing overfitting.

In clinical decision support, a model's 'calibration' refers to:

Answer: How well predicted probabilities match actual observed event rates

A well-calibrated model produces predicted probabilities that closely match the true frequency of outcomes (e.g., a 70% predicted risk should occur ~70% of the time).