Objective <p>To evaluate the effectiveness and user satisfaction of an online cell morphology self-study and self-test platform designed to enhance the blood smear morphology diagnostic skills of hospital laboratory technicians.</p> Methods <p>We developed an online platform incorporating machine learning algorithms for automated recognition and classification of blood cell morphology. The platform allows users to assess cell types and provides real-time feedback. We conducted a multi-center study involving 1,034 registered users from various hospitals. User satisfaction was assessed using a 5-point Likert scale survey. The platform’s effectiveness was evaluated by comparing users’ diagnostic accuracy before and after using the platform for three months. We also compared the platform’s performance with other automated morphology recognition systems.</p> Results <p>User satisfaction was high, with mean scores of 4.5/5 for the platform’s usefulness in recognizing morphological features, 4.4/5 for assisting in case diagnosis, 4.6/5 for serving as an educational tool, and 4.5/5 for facilitating morphology reporting. Users’ diagnostic accuracy significantly improved from 65.3 to 89.6% after using the platform (<i>p</i> &lt; 0.001). The platform’s cell recognition accuracy (92.1%) was comparable to other state-of-the-art automated systems.</p> Conclusion <p>The online cell morphology self-study and self-test platform is an effective tool for enhancing blood smear diagnostic skills of hospital laboratory technicians, with high user satisfaction and performance comparable to other automated systems. Widespread adoption of this platform could improve the quality of blood smear morphology assessment in clinical practice.</p> Clinical trial number <p>Not applicable.</p>