SPECTRA Project aims at designing a Decision Support System (DSS) based on AI techniques and the use of cutting-edge Technologies for the early diagnosis of TRS patients. 

The innovative aspect of the Project is to combine typical screening procedures used in standard clinical practice, with ICT-based assessment techniques based on Machine Learning algorithms.

SPECTRA will conduct a field study involving real patients from the Unit for Treatment-Resistant Psychosis, University "Federico II" of Naples. After being categorized as TRS or nonTRS, eligible patients will enter the study. 

The SPECTRA staff will collect historical clinical patient data, such as:

•  Magnetic Resonance Images, 

• questionnaire scores, 

• demographic data, 

• geographical and feeding data 

• real-time data collected during the patient’s screening.

Real time physical data will be acquired by:

•  IoT sensors (ECG, temperature, EEG, etc,), 

• video 

• speech. 

Thus, standard data and data acquired by using ICT technologies will be adopted for training a Machine Learning/Deep Learning model for detecting TRS patients. However, one of the main problems with the adoption of AI solutions for supporting decisions in healthcare is that clinicians lack trust in the black-box operation. 

Another project's main objective is to define interaction models suitable for supporting clinicians during the TRS diagnosis by exploiting eXplainable Artificial Intelligence (XAI) methods, which will explain how AI black-box models generate predictions. 

XAI techniques will be used to provide clinicians with more precise details about the peculiarities of some subdimensions of SZ in TRS patients, supporting them in choosing a more appropriate alternative pharmacological treatment. As a secondary outcome, a TSR-nonTRS dataset will be created that will be useful for the scientific community for experimenting with Machine Learning approaches to the diagnosis of TRS in people suffering from schizophrenia.

TRS DIAGNOSIS AND SUPPORTING ML TOOLS

SPECTRA project aims at improving these results by integrating standard data with bio-signals, emotional, cognitive and socials signals of TRS/nonTRS patients gathered through wearable sensors to observe whether these objective measures can represent valuable predictors of disorganization dimension and in turn allows a DSS system based on advanced ML models to perform an early and accurate prediction of TRS state

EXPLAINABLE AI IN HEALTHCARE

SPECTRA will propose an XAI-based DDS able to explain to clinicians the reasons for a particular diagnosis suggestion by increasing the interpretability of the results. XAI techniques can be used to enhance the trust of clinicians in new technologies and ICT-tools, by contemporary increasing transparency and legibility of the system, which could suggest new insights to the clinicians that in turn could be improved by the clinicians' feedback. This will result in a more understandable and accurate supporting system.