Previously, doctors interpreted diseases and their outcomes according to their experience in diagnosis. However, with the rapid increase in technology and population, the task of examining the patient becomes cumbersome and sometimes human efforts produce inconsistent results. Several research is being done for healthcare in terms of improving visualization and accuracy by using machine learning models. The current research targets to explore quantum computing as a different way of processing information compared to classical computer systems such as the use of quantum bits (qubits) along with superposition and entanglement for extending the computation capabilities at an unprecedented level of thinking in the healthcare domain. Quantum computing systems provide exponential benefits in terms of high-speed processing, faster and easier diagnostic assistance, unimaginable reduction in processing throughput, and many more. An extensive comparative analysis of existing approaches has been made which benchmarks the need for quantum healthcare computing. The objective of this work is to interpret whether Quantum computers prove to be more trusted when it comes to patient diagnosis, and faster analysis leading to cost optimization. In order to accelerate patient diagnosis, different approaches have been presented. The authors have proposed a precision-based granular approach for patient diagnosis that incorporates diagnosing the disease with enhanced precision and granularity. It involves reporting symptoms by the patient, encountering by healthcare expert on multiple factors, precise examination, granular health status (understanding past and present medical history), followed by a precise intervention by understanding biomolecular simulations. The algorithm has been presented to describe the flow process for patient diagnosis modeling using quantum computing. It involves qubits initialization, pairing the values, assigning probabilistic values, cross-validation, and quantum circuit formation. Precision-based granular approach has been implemented for a scenario (consisting of medical parameters such as oxygen and heart rate level, with the functionality of diagnosing oxygen level and heart range which lies as either normal or not normal (high/low)). Precision-based granular approach deals specifically with the individual ‘biomolecular simulation by understanding variations in the individual body whereas the umbrella-based approach does not deal with specifically to individual mechanisms. Granular level of encounter is not possible in umbrella-based treatment. Python Jupyter notebook and IBM Composer tool is used for the implementation of results. Bloch sphere and computational state graph are obtained as an output for better visualization and understanding. Falcon r5.11H processor is used with the version of 1.0.24 of IBM Composer to simulate the experiment. The methodology using precision based granular approach provides timely encounter of disease along with umbrella diagnosis and precise treatment. The time is taken and frequency of qubits have been presented with promising results. The diagnosis process and optimizing cost efficiency can aid in an early detection of the disease.
Read full abstract