Parkinson’s Detection: Emotional Intelligence Perspective

: Parkinson’s disease is a neurological ailment affecting millions of individuals throughout the world. Early detection and accurate diagnosis of Parkinson’s disease (PD) are crucial for effective treatment and management of the disease. In recent years, there has been growing interest in using Emotional Intelligence-based approaches to detect PD, as changes in emotional processing are a common symptom of the disease. Emotion recognition using various techniques of emotional intelligence can aid in early detection, management, and monitoring of the disease. This paper presents a comprehensive review of the research on PD detection. Also, the taxonomy approaches to PD detection using different biomarkers and Emotional Intelligence (EI) are discussed. In this paper, it also reviews recent studies on the use of Emotional intelligence techniques for PD detection and proposes future directions for research in this area. Overall, the review suggests that using Emotional Intelligence approaches has a high potential for enhancing the accuracy and reliability of PD detection and monitoring, and can have significant implications for improving the quality of life of PD patients.


Introduction
Parkinson's disease (PD) is a neurodegenerative disorder that affects movement and coordination. It is caused by the degeneration of dopamine-producing neurons in a specific part of the brain called the substantia nigra. The decline in dopamine levels leads to symptoms such as tremors, stiffness, slow movement, and difficulty with balance and coordination [1].The exact cause of Parkinson's disease is unknown, but it is believed to be a combination of genetic and environmental factors may be responsible for this condition [2][3] [4]. Age is also a significant risk factor, as the majority of cases occur in individuals over the age of 60 [5]. PD is diagnosed by a careful review of symptoms, physical examination, and medical history. There is no specific test for Parkinson's disease, but imaging tests such as CT scans or MRI may be used to rule out other conditions [6]. Treatment for Parkinson's disease is primarily focused on managing symptoms and improving quality of life. This may involve medications to increase dopamine levels, physical therapy to improve mobility and balance, and lifestyle changes such as exercise and diet modifications. Living with Parkinson's disease can be challenging, and individuals may experience a range of physical, emotional, and social effects. Parkinson's disease can have a significant influence on Emotional Intelligence, and individuals with the condition may experience changes in mood and Emotional regulation, difficulties with social interactions and communication, and changes in executive functioning. These changes can result in decreased varied by nation, and rising to 1-3% among the elderly. According to the Parkinson's Disease Foundation, around 1 million People are affected by the disorder. In the United States, the incidence of Parkinson's disease is around 20 cases per 100,000 people per year (60,000 occurrences each year), with an average onset age of around 60 years. Parkinson's disease is estimated to afflict 1% of persons aged 60 and above, increasing to 1% to 3% of those aged 80 and up [13]. It is important to emphasise, however, that these figures do not include undiagnosed cases. Because Parkinson's disease is so complicated, there is presently no viable treatment. The illness is thought to be caused by the death of 70-80% of dopaminergic neurons in the substantial nigra (SNs) portion of the brain, as seen in fig. Dopamine is a neurochemical generated in the substantia nigra, an important brain region, and it influences a number of central nervous system activities, including movement control, executive functions of cognition, and limbic emotional activity.  relatives in your family, however, your chances of having the condition are low [15]. (IV) Toxins exposure: Continuous exposure to herbicides (chemicals used to kill or control particular types of pests) and pesticides (chemicals used to kill or repel pests of various kinds, including insects and plants on occasion) may increase your risk of Parkinson's disease [16].

Parkinson's Disease Detection
Parkinson's disease has no particular test. A neurologist (a doctor who specialises in nervous system ailments) diagnoses Parkinson's disease based on your signs and symptoms, medical history, and a neurological and physical examination. Because Parkinson's disease is commonly misdiagnosed in its early stages, we use a number of reliable genetic biomarkers and non-invasive approaches to identify it. Differentiating Parkinson's disease from other diseases, tracking its course, or suggesting a beneficial response to a therapy intervention. The identification of biomarkers, which are perceptible and measurable changes in the body that may be used to predict, diagnose, and track disease activity and developmentis the holy grail of invasive Parkinson's disease research. A variety of strategies can be used to discover biomarkers, including Diagnostic markers [17], Progression markers [18], Pharmacokinetic marker [19]. In addition, researchers have developed a number of non-invasive approaches for determining the severity of Parkinson's disease, including acoustic analysis of voice sounds, physiological signals, wearable sensors, and gait analysis. The identification of Parkinson's disease progression through acoustic analysis of speech waves has caught the interest of numerous academics [20].

Progression markers
Progression marker is further divided into following types: (I) TCS: Transcranial B-Mode Sonography (TCS) assesses the blood flow velocity of brain arteries by measuring the frequency of ultrasound waves and their reflections. This low-cost and reliable method indicates increased echogenicity of the substantia nigra (SN) in Parkinson's disease (PD) brains compared to the control group, which may be due to heightened iron and gliosis levels in PD patients' SN. Patients with other parkinsonian illnesses, on the other hand, are more frequently hyperechogenic [21].(II) MRI: The most extensively utilised diagnostic paradigm for early identification of Parkinson's Disease is the examination of magnetic resonance imaging (MRI) images of the brain. The MRI scans provide anatomical information about the brain's subcortical structure, which are subsequently evaluated for aneurysms, allowing for early identification of a specific form of sickness. Magnetic Resonance Imaging (MRI) in Parkinson's disease patients can detect changes in brain structure caused by dopamine depletion. can reveal changes in brain structure induced by dopamine depletion [22].(III) PET Scan: Positron emission tomography (PET) scanning is a medical imaging technique that produces pictures of the inside of the body using a small quantity of radioactive material and a particular camera. PET scans are utilised in the setting of Parkinson's disease (PD) to visualise the activity of specific areas of the brain and to aid in the diagnosis of PD. PET scans can assist determine the existence of dopamine-producing cells in the brain in Parkinson's disease, which is important for the diagnosis of PD as a degeneration of dopamineproducing cells is a hallmark of the disease. By measuring the activity of these cells, PET scans can help differentiate PD from other conditions with similar symptoms, such as essential tremor or multiple system atrophy. Studies have shown that PET scans are effective in detecting the presence of dopamine-producing cells in the brains of individuals with PD [23].(IV) SPECT Scan: Dopaminergic imaging, a neuroimaging technique that uses single photon emission computed tomography (SPECT) with I-Ioflupane, is widely used in the early stages of Parkinson's disease [24].Functional neuroimaging using the SPECT approach is beneficial in individuals exhibiting early indications of parkinsonism [25].

Non-invasive methods
Non-invasive methods is further divided into following types (I) Voice signal: Voice analysis is a technique that uses computational methods to analyse speech and voice patterns for the detection of Parkinson's disease (PD). It involves recording and analysing speech and voice parameters, such as pitch, volume, and rhythm, to identify any deviations from normal speech patterns that may indicate PD. Studies have shown that individuals with PD often exhibit distinctive speech and voice changes, such as reduced volume and monotony, and altered prosody, which can be detected through voice analysis. These changes can be used to distinguish between individuals with PD and healthy controls, and may provide an early warning of the onset of the disease [26]- [28].(II) Wearable sensors: Wearable sensors are devices that can be attached to the body and used to monitor various physiological signals, such as movement, heart rate, and body temperature. In recent years, wearable sensors have been increasingly used in the field of Parkinson's disease (PD) research and management. Wearable sensors in Parkinson's disease enable for continuous, real-time monitoring of motor and nonmotor symptoms such bradykinesia, tremors, and gait abnormalities. This information can be used to track disease progression, evaluate the efficacy of treatments, and monitor the response to therapy [29].(III) Gait analysis: Gait analysis is a technique used to assess and evaluate an individual's walking patterns and movements. In the realm of Parkinson's disease research (PD), gait analysis is used to assess the effects of PD on an individual's gait, as well as to evaluate the efficacy of treatments for PD. Gait analysis in PD can be performed using various techniques, including laboratory-based gait analysis, in-clinic gait analysis, and community-based gait analysis. Laboratory-based gait analysis typically involves the use of high-tech equipment, such as motion capture systems and force plates, to measure various gait characteristics, such as stride velocity, stride length and step length. In-clinic gait analysis typically involves a clinician observing and assessing an individual's gait during a physical examination. Community-based gait analysis involves the use of wearable sensors, such as accelerometers, to measure gait parameters in a realworld setting [30].

4.
Emotional Intelligence Emotional intelligence (EI) is the ability to identify, express, and feel emotions, as well as control them, harness them for constructive goals, and successfully handle the emotions of others. It has been stated that emotional intelligence talents are a better predictor of life success than IQ [31]. Emotional intelligence is commonly defined by four characteristics: (I) Self-awareness -Understanding how one's emotions, emotional triggers, strengths, weaknesses, goals, values, and objectives influence one's thoughts and behaviour is referred to as self-awareness. You understand how your emotions impact your thoughts and actions. You are confident in your abilities while still being mindful of your flaws [31]. (II) Self-management-The ability to control one's emotions, based on self-awareness, is referred to as selfmanagement. Even people with high EQs have bad moods, impulsive behaviours, and negative emotions like tension and rage on occasion. The capacity to regulate your emotions rather than allowing them to rule you is referred to as self-management [32]. (III) Social awareness -You're sympathetic. You can recognise emotional cues, understand people' desires and concerns, feel at ease in social situations, and understand power dynamics in a team or organisation. (IV) Relationship management -Relationship management is all about interpersonal skills, which include the capacity to win co-workers' genuine trust, rapport, and respect. It's about more than simply a trust fall during a team building activity; it's about trusting and being trusted as a member of a team. You know how to build and maintain strong relationships, communicate clearly, encourage and influence others, work effectively with others, and handle conflict [33].

4.1.
How Parkinson's disease can affect Emotional Intelligence: Parkinson's disease (PD) is a neurodegenerative disorder that primarily affects motor function, but it can also impact emotional and social functioning. Emotional intelligence (EI) is a set of skills that enable individuals to recognize, understand, and regulate their own emotions, as well as the emotions of others. In this response, I will discuss in detail how Parkinson's disease can affect emotional intelligence. (I)Recognition of emotions: The ability to recognize emotions is an important component of emotional intelligence. People with PD may have difficulty recognizing emotions due to changes in the brain that affect emotional processing. These changes can make it difficult to identify and differentiate between different emotions, especially those that are subtle or complex [34]. (II)Understanding of emotions: Understanding emotions involves being able to comprehend the reasons behind an emotional response. Individuals with PD may struggle with this aspect of emotional intelligence due to changes in the brain that impact cognitive function. These changes can make it difficult to interpret social cues and understand the motivations behind other people's emotions. (III)Regulation of emotions: Regulating emotions involves the ability to manage and control one's own emotions in different situations. People with PD may experience difficulty regulating their emotions due to changes in the brain that impact the production of neurotransmitters such as dopamine. This can lead to increased emotional instability, impulsivity, and anxiety, which can affect their ability to make decisions and cope with stress [35]. (IV)Communication of emotions: Effective communication of emotions is an important component of emotional intelligence. People with PD may experience difficulty communicating their emotions due to changes in the brain that impact speech and language function. This can lead to difficulty expressing emotions clearly, which can result in frustration and social isolation [36]. (V)Empathy: It involves the ability to understand and share the emotions of others. People with PD may experience difficulty with empathy due to changes in the brain that impact emotional processing and social cognition. This can make it difficult to recognize and respond to the emotional needs of others, which can lead to social isolation and interpersonal difficulties. Therefore, Parkinson's disease can impact emotional intelligence in a variety of ways, including changes in emotional recognition, understanding, regulation, communication, and empathy. However, the impact of PD on emotional intelligence can vary depending on the individual and the stage of the disease. People with PD may benefit from interventions that focus on improving emotional regulation, communication skills, and social support to help mitigate the impact of PD on emotional intelligence and improve their overall quality of life [37].

Models of Emotional Intelligence
The three key theorists in Emotional Intelligence research are Bar-On, Mayer and Salovey, and Daniel Goleman. Emotional intelligence, according to Reuven Bar-On, a well-known researcher and the inventor of the term "emotion quotient," is concerned with understanding oneself and others, relating to people, and adapting to and coping with one's immediate surroundings in order to be more successful in dealing with environmental demands. (Bar-On, 1997). acquire emotional input and successfully navigate social settings. The definition of EI proposed by Salovey and Mayer aims to fit EI inside the parameters of the accepted standards for a new intelligence. They changed their original definition of emotional intelligence (EI) to "the ability to recognise emotion, integrate emotion to facilitate cognition, comprehend emotion, and control emotion to promote personal growth" as a result of their ongoing study. Their concept of EI, however, changed as a result of their further study to "the capacity to reason about emotions, and of emotions, to increase thinking. It encompasses the skills needed to effectively identify emotions, access and produce emotions to support cognition, comprehend emotions and emotional knowledge, and control emotions in a thoughtful manner to foster both emotional and intellectual development [39].(III) Mixed model: Both Goleman's (1995) and Bar-(1997) On's mixed models of emotional intelligence incorporate the value of competency (capacity) as well as general disposition (trait). The concept of a hybrid model is both wide and sound. The difficulty with the mixed model is that it is redundant with personality traits. The mixed model does not just measure emotional intelligence since it focuses on adaptive functioning such as social skills, stress management, and drive.

5.
Related works Literature review of PD Detection techniques using AI techniques: Pir Masoom Shah et al. have devised a technique for detecting Parkinson disease that makes use of a brain MRI scan and CNN for enhanced performance [40]. Matthew P. Adams1 et al. aimed to analyse and anticipate a patient's motor function as measured by part III of the universal Parkinson's disease rating scale (UPDRS) using a convolutional neural network that used the entire DAT image without feature extraction (CNN). [41]. Khatamino et al. proposed an 88% accuracy deep learning CNN-based approach for medical diagnosis based on spiral drawings of Parkinson's disease patients [42]. Dan Long et al. used SVM to classify early PD and HC. In their investigation, they used multimodal MR imaging on each PD and HC patient. Their model has an accuracy of 86.96% [43].Xinjie Shi et al. presented a method for identifying PD and normal patients using hybrid convolutional recurrent neural networks, which is useful in clinical practise [44].Shivangi et.al. suggested a way for distinguishing between Parkinson's disease and normal individuals using hybrid convolutional recurrent neural networks that is beneficial in clinical practise [45]. Ramzi M. Sadek et al. proposed using physical symptoms to detect Parkinson's disease patients as soon as feasible using an artificial neural network using back propagation approach. [46].Krishnagopal S et al. created a network-based technique called Trajectory Profile Clustering (TPC) to detect illness subtypes and past forecasts of disease development trends. It is an excellent method for finding and predicting subgroups in several longitudinal datasets as well as in individual individuals. This results in a 72% accuracy in predicting patients less than 4 years in advance [47]. O. Asmae et colleagues employed ANN and k-NN to discriminate between PD and healthy individuals. In the case of ANN, 70% of the data was utilised for training, 5% for validation, and 25% for testing. ANN claimed an accuracy of 96.7%. They used the RFE approach to perform feature selection (FS) on a dataset. [48].Hetav Modi et al suggested a PD recognition system based on a VGG16-based convolutional neural network (CNN). It extracts characteristics from the PET scan image dataset obtained from the PPMI source automatically. Specificity, accuracy, sensitivity, and precision of the suggested system are 97.5%, 84.6%, 71.6%, and 96.7%, respectively [49]. Literature review of PD detection techniques using EI: Shunans Zhao1 et al. proposed categorising emotional speech in Parkinson's disease patients, as well as categorising PD speech. Participants said short words with diverse emotional prosody, which were subsequently recognised using 209 separate audio characteristics and three algorithms (random forests, nave Bayes and support vector machines). When recognising emotions and PD vs. control, they attain accuracies of 65.5% and 73.33%, respectively [51].M. Capecci * , L. Ciabattoni et al. demonstrate a Machine-Learning Based Emotion Recognition System in Parkinson's disease patients. This system's development is built of each user executing an experimental protocol while a basic gadget (i.e., wristwatch) worn on the wrist collects data. To detect emotions during the experimental process, a ninepoint clinical scale and commercial emotion identification software were employed [52]. Anusri U et al. suggested a study that would use the facial emotions of Parkinson's disease patients and normal people to identify facial emotions such as sadness, happiness, rage, and depression. They attain their performance in terms of accuracy, sensitivity, and specificity by utilising the CNN architecture of Alex Net and Vgg 16 [53].Justyna Skiba ńska has revealed a unique approach to detecting Parkinson's disease based on facial feature expression. The XGBoost classifier beat the others, with 0.69 balanced accuracy. [54]. Konstantinos Sechidis et al. offer a study that uses machine learning approaches to explore the emotional content of speech in Parkinson's disease (PD) patients. It finds speech patterns that are predictive of PD patients' emotional states and compares the effectiveness of several machine learning algorithms in predicting these features. [55]. Muhammad Najam Dar et al. present a 1D-CRNN-ELM architecture that integrates a one-dimensional Convolutional Recurrent Neural Network (1D-CRNN) with an Extreme Learning Machine (ELM), which is resilient for emotion recognition in Parkinson's disease patients [56]. This section summarises the researcher's current work and provides a tabular comparison with the recommended systems. Nowadays, EI is critical to how we respond to what life throws at us. It is also a necessary component of compassion and recognising the deeper motivations behind others' behaviours. When coping with stressful events such as conflict, change, and barriers, EI is very helpful. Based on the literature review we propose the following taxonomy: A taxonomy of detection of Parkinson's disease using Emotional Intelligence is a categorization system that describes different techniques and approaches used in the field. Some of the possible categories in the taxonomy of detection of Parkinson's disease using Emotional Intelligence are: Figure 4. Taxonomy of PD Detection using Emotional Intelligence • Facial Expression Analysis: This involves using computer vision and machine learning techniques to analyse changes in facial expressions and movements, which are associated with Parkinson's disease. The data type used for Facial Expression Analysis in the detection of Parkinson's disease using Emotional Intelligence is image and video data. This can include still images or videos of the face, captured either in a controlled laboratory environment or in a real-world setting. The image and video data are then processed using computer vision algorithms, such as feature extraction, face detection and landmark detection, to extract relevant information about the facial expressions and movements. These features are then analysed for changes in their appearance, shape, and movement that are indicative of Parkinson's disease [53] .  [59].
• Electroencephalography (EEG): This involves measuring the electrical activity of the brain using electrodes placed on the scalp, and using machine learning techniques to analyse the EEG signals for patterns that are indicative of Parkinson's disease [60].The data type used in Electroencephalography (EEG) Analysis is EEG signals or brainwaves, which are recorded and analysed using electrodes placed on the scalp. The EEG signals are then pre-processed, such as removing noise and artifacts, and then fed into machine learning algorithms for further analysis [61]. The goal is to identify patterns in the EEG signals that are indicative of Parkinson's disease, and this requires selecting appropriate features, such as frequency and power, and using appropriate machine learning techniques, such as neural networks, support vector machines, and neural networks. Based on the EEG data, this analysis produces a diagnosis or prognosis of Parkinson's disease [60], [62]. Several approaches are utilised to examine EEG data in Electroencephalography (EEG) Analysis for Parkinson's disease identification., including (I)Power spectral density analysis: This method involves calculating the power spectral density of the EEG signals to identify changes in the frequency distribution of the signals, which are associated with Parkinson's disease [63].(II)Time-frequency analysis: This method involves analysing the time-frequency representation of the EEG signals to identify changes in the frequency content of the signals over time [64].(III)Independent Component Analysis (ICA): This method involves separating the EEG signals into independent components and analysing the properties of each component to identify patterns that are indicative of Parkinson's disease [65]. (IV) Other signal processing techniques: Other signal processing techniques, such as wavelet transformations, linear discriminant analysis (LDA), and principal component analysis (PCA), may also be used to analyse EEG recordings and find patterns related to Parkinson's disease [66].
• Physiological Signal Analysis: This involves analysing signals from the body, such as heart rate variability, skin conductance, and respiration rate, to detect changes in emotional. In the Physiological Signal Analysis category, several methods can be used to analyse the signals obtained from the body. One commonly used method is Heart Rate Variability (HRV) analysis, where the variation in time intervals between heart beats is analysed to understand the changes in autonomic nervous system activity [67]. Another method is Skin Conductance Analysis, which involves measuring the electrical conductance of the skin to detect changes in sweat gland activity, which is an indicator of emotional arousal. Respiration rate analysis is also used to measure changes in breathing patterns, which are often associated with changes in emotional states. Machine learning algorithms, such as random forests decision trees, and support vector machines, can be used to analyse these signals and classify them into different emotional states.
• Multi-modal analysis: Multi-modal analysis can use a combination of techniques such as feature extraction, feature selection, dimensionality reduction, and machine learning algorithms such as decision trees, support vector machines, random forests, and deep neural networks. These techniques help to combine the information from multiple sources, to increase the robustness of the model and improve its performance [68]. Additionally, hybrid models that use a combination of machine learning and rule-based systems can also be used in multi-modal analysis. The specific methods used would depend on the specific goals and requirements of the project, as well as the data available. For example, a study by Goldenberg et al. (2017) published in the journal "Movement Disorders" found that EI was related to several important outcomes in PD, including motor symptoms, cognitive function, and quality of life. These findings highlight the potential value of considering EI in the management of PD and demonstrate the potential of multimodal analysis to inform the development of more personalized treatment plans for individual patients [69] .
• Clinical outcomes-based analysis: This category involves the use of patient-reported outcomes, such as quality of life, depression, and anxiety scores, to assess the effectiveness of the emotional intelligencebased approach in detecting Parkinson's disease. Clinical outcomes-based analysis typically involves statistical methods such as regression analysis and classification algorithms to analyse the relationship between the patient-reported outcomes and Parkinson's disease status [70].The specific method used may vary depending on the research question, the type of data available, and the type of analysis desired. Some common methods used in this category include logistic regression, linear regression decision trees, and neural networks and support vector machines. The purpose is to evaluate the validity and reliability of the emotional intelligence-based method by using patient-reported outcomes to create accurate predictions regarding Parkinson's disease state [71].

6.
Open research challenges Research challenges for the detection of Parkinson's disease can include the following: (I) Inadequate or limited data availability. (II)Data quality and variability: The quality and variability of emotional intelligence data collected from individuals with Parkinson's disease can also present challenges in developing accurate models. This can include issues with measurement precision, as well as individual differences in emotional expressions. (III)Model interpretability: Interpreting the results of models trained on Emotional Intelligence data can be challenging, making it difficult to understand the underlying factors contributing to Parkinson's disease and to develop effective interventions.( IV)Ethical and privacy considerations: The collection and use of Emotional Intelligence data for the detection of Parkinson's disease also raises ethical and privacy concerns, such as the potential for discrimination based on emotional expressions and the security of sensitive personal data.(V)Variability in emotional expressions: Emotional expressions can be highly variable and can be influenced by many factors, such as mood, environment, and cultural background. This variability can make it difficult to accurately detect Parkinson's disease using emotional intelligence. (VI) Current Parkinson's disease detection methods, such as EEG and face recognition, have limits in terms of accuracy and scalability. This makes it difficult to create models that are both accurate and generally applicable.

Conclusion
Parkinson's disease can have a major influence on a person's Emotional Intelligence. The use of Emotional Intelligence techniques for Parkinson's disease detection has shown promising results, with the potential to complement or even surpass the accuracy of traditional biomarker-based approaches. Emotional intelligence-based approaches offer a non-invasive, cost-effective, and patient-centered approach to detecting PD, which may be especially useful in early-stage diagnosis and long-term monitoring of the disease. Further research is needed to validate and determine the efficacy of this approach. EI perspective has the potential to improve the accuracy of PD detection and enhance the quality of life for individuals with PD, and it represents an important area for future research in this field.