diff --git a/laborious/activities/model_metrics.py b/laborious/activities/model_metrics.py
index cb44805..b9b1841 100644
--- a/laborious/activities/model_metrics.py
+++ b/laborious/activities/model_metrics.py
@@ -6,7 +6,6 @@ with workflow.unsafe.imports_passed_through():
     import warnings
     from typing import Any
 
-    import numpy as np
     import pandas as pd
     from pandas import DataFrame, Index, Series, to_datetime
     from sientia_do.notifications.handlers import CoreNotificationHandler as NotificationHandler
@@ -16,6 +15,7 @@ with workflow.unsafe.imports_passed_through():
     from sientia_do.observability.sientia_monitoring import SientiaMonitoring
     from sientia_do.temporal.constants import DATETIME_FORMAT_WITH_TZ
     from sientia_model.analytics.drift_analysis import DriftAnalysis, DriftInsufficientDataError
+    from sientia_model.metrics.regression import RegressionMetrics
 
     from laborious import metrics
     from laborious.utils.dataframe_debug import build_dataframe_debug_message
@@ -365,62 +365,62 @@ class ModelMetrics(SientiaMonitoring):
     @activity.defn(name='calculate_simple_metrics')
     def calculate_simple_metrics(self, input_data: dict[str, Any]) -> list[dict]:
         """
-        Calculate simple metrics for a model. Metrics available are:
-            - rmse
-            - mse
-            - mae
-            - r2
-            - accuracy
-            - precision
-            - recall
-            - f1
+        Calculate simple regression metrics for a model using RegressionMetrics.
+
         Args:
-            input_data (dict[str, Any]): Input data containing:
+            input_data: Input data containing:
                 - metadata (dict): Workflow execution metadata
                 - model_id (str): ID of the MLFlow model
-                - target_data (pd.DataFrame): Target data for calculating metrics, containing target and prediction columns
-                - metrics (list[str]): List of metrics to calculate
+                - target_data (list[dict]): Target data with target, prediction, timestamp columns
+                - metrics (list[str]): Metric names to calculate
+                - interval_minutes (int): Window interval in minutes
+                - model_type (str | None): Model algorithm type (for r2 lock)
         Returns:
-            dict[Hashable, Any]: Dictionary containing the calculated metrics
+            list[dict]: Records with metric, value, model_id, timestamp, data_size, interval_minutes
         """
-
         metadata = input_data['metadata']
         model_id = input_data['model_id']
         target_data = DataFrame(input_data['target_data'])
-        metric_names = input_data['metrics']
+        metric_names = list(input_data['metrics'])
         interval_minutes = input_data['interval_minutes']
+        model_type = input_data.get('model_type')
 
         data_size = target_data.shape[0]
 
-        output_data = []
+        # Filter r2 when model_type is known and unsupported
+        if (
+            model_type
+            and 'r2' in metric_names
+            and not RegressionMetrics.is_r2_supported(model_type)
+        ):
+            metric_names = [m for m in metric_names if m != 'r2']
+            self.warning(
+                f'r2 excluded for model {model_id}: not supported for model_type={model_type}',
+                metadata,
+            )
+            self.send_notification(
+                metadata=metadata,
+                notification_id='SIMPLE_METRICS_R2_UNSUPPORTED',
+                message=f'r2 excluded: not a valid metric for model_type={model_type}',
+                block='model_metrics',
+                level=NotificationLevel.WARNING,
+            )
 
-        diff = target_data['target'] - target_data['prediction']
-        diff_squared = diff**2
+        if not metric_names:
+            self.info(f'No metrics to calculate for model {model_id} after filtering', metadata)
+            return []
 
         self.info(f'Calculating simple metrics for model {model_id}: {metric_names}', metadata)
 
-        for metric in metric_names:
-            if metric == 'rmse':
-                output_data.append({'metric': 'rmse', 'value': np.sqrt(np.mean(diff_squared))})
-            elif metric == 'mse':
-                output_data.append({'metric': 'mse', 'value': np.mean(diff_squared)})
-            elif metric == 'mae':
-                output_data.append({'metric': 'mae', 'value': np.mean(np.abs(diff))})
-            elif metric == 'r2':
-                y_true = target_data['target']
-                y_mean = np.mean(y_true)
+        # Build Series with DatetimeIndex for RegressionMetrics
+        timestamps = pd.to_datetime(target_data['timestamp'])
+        real_data = Series(target_data['target'].values, index=timestamps, dtype=float)
+        predictions = Series(target_data['prediction'].values, index=timestamps, dtype=float)
 
-                ss_res = np.sum(diff_squared)
-                ss_tot = np.sum((y_true - y_mean) ** 2)
-
-                # Evita divisão por zero
-                if ss_tot == 0:
-                    r2_score = 0.0
-                else:
-                    r2_score = 1 - (ss_res / ss_tot)
-
-                output_data.append({'metric': 'r2', 'value': r2_score})
+        regression = RegressionMetrics(real_data, predictions)
+        output_data = regression.calculate(metric_names)
 
+        # Wrap with metadata columns matching the existing output schema
         data = DataFrame(output_data)
         data['model_id'] = model_id
         data['timestamp'] = target_data['timestamp'].max()