<p>Systolic blood pressure (SBP) and heart rate (HR) are critical for proactive clinical decision-making, particularly in intensive care environments. Early identification of abnormalities in these vital signs helps patients receive appropriate treatment and reduce associated health degradation. This study presents FCMS-iDMM, a fog/cloud-based real-time forecasting system that simultaneously predicts future SBP and HR values using deep learning models integrated with big data streaming platforms. The research involves two main phases: offline model and online forecasting pipeline optimization. During the offline model development, we explore the single-task and multi-task modeling. Different optimization steps have been explored. The single task includes forecasting HR and SBP in multi-step heads using Temporal Convolutional Networks (TCN), Long Short-Term Memory (LSTM), and Gated Recurrent Unit (GRU). Multi-task comprises forecasting HR and SBP in diverse multi-step heads as puerperal employing TCN, sequence-to-sequence (seq2seq), and Autoencoder models using LSTM and GRU. Extensive results are accomplished by the Medical Information Mart for Intensive Care III (MIMIC III) to assess the performance of the proposed multi-task DL model. Multi-task learning (MTL) models based on Temporal Convolutional Networks (TCNs) achieved superior performance. In forecasting 8&#xa0;min, TCN recorded the best performance compared to other models with 1.5428 RMSE, 1.0871 MAE, and 1.269 MAPE for HR and 4.1446 RMSE, 2.4323 MAE and 2.5237 MAPE for SBP in multi-task. Simulated sensors, Apache Kafka, and Apache Spark are used to develop the real-time HR and SBP online forecasting pipeline. Experimental validation using the MIMIC-III database confirmed that multi-task models outperform single-task approaches across multiple forecasting horizons. The proposed system offers a scalable and efficient solution for real-time monitoring of vital signs, paving the way for predictive, patient-centered healthcare systems.</p>