Volume 10, Issue 4, April – 2025 International Journal of Innovative Science and Research Technology

ISSN No:-2456-2165 https://doi.org/10.38124/ijisrt/25apr619

Smart Health Consulting System

Vahini.M1; Dr. E. Boopathi Kumar2
1
MSc(IT) Project Student,
2
Guest Faculty
1,2
Department of Information Technology, Bharathiar University, Coimbatore, India

Publication Date: 2025/04/25

Abstract: The project "Smart health consulting system" has been designed using Xml with Java as front end and SQLite
server as backend, which assist to prediction diseases and finds appropriate hospital with e-appointment system for the
users. Disease detection through symptoms may appear to be quite normal in day-to-day life, but serious when symptoms
grow complex and/or diverse. As this complexity or diversity grows, we human beings fail to correctly identify any specific
disease that results from the perceived symptoms. Different symptoms normally point towards different possibilities of
diseases, and also with varying intensities. The primary objective of the proposed system is to introduce a new mobile
application with self-automated disease prediction with a hospital recommendation process along with an appointment for
a doctor. The system facilitates the enhancement of the medical field service. The patient can identify the disease by
symptoms. At the beginning, users were required to register themselves using minor details. Once registered successfully,
users can log in by using their username and password. Users would then be able to choose their symptoms. Our system
used techniques applied for classifying effectively. Users can first choose their symptoms. Last but not least, our technique
will classify effectively whether the patient appears to be suffering from a disease or the patient appears to be normal
effectively. Then, the system will recommend suitable hospital and medical service to the patients or users based on the
symptoms effectively.

Keywords: Smart Health , Consulting System ,Artificial Intelligence (AI),Machine Learning (ML),Expert System, Diagnosis,
Medical Consultation , Health Monitoring , Knowledge Base , Inference Engine , Patient Data , Remote Healthcare , Decision
Support System (DSS), Natural Language Processing (NLP) Web-Based Application.

How to Cite: Vahini.M; Dr. E. Boopathi kumar (2025), Smart Health Consulting System. International Journal of Innovative
Science and Research Technology, 10(4), 1236-1242. https://doi.org/10.38124/ijisrt/25apr619

I. INTRODUCTION Smart Health Consulting System employs IoT and AI for

real-time monitoring of patients and remote consultation,
The Smart Health Consulting System links patients and lowering hospital visits. It increases access to health care,
physicians and facilitates first-time symptom evaluation, provides timely interventions, and has better patient
offering access and quality care[1].The Smart Health outcomes[7].The Smart Health Consulting System is an
Consulting System facilitates remote consultation of a artificial intelligence and mobile technology-based system of
physician, remote monitoring of health, and real-time expert real-time medical consultation and surveillance of health. It
guidance, offering access and quality of patient care[2].The increases the availability of health care, enhances preventive
Smart Health Consulting System uses smartphone-based medicine, and decreases reliance on hospital visits[8].The
remote consultation technology for medical conditions, Smart Health Consulting System employs AI to assist the user
symptom evaluation, and real-time health monitoring, in diagnosing and implement treatment for possible health
enhancing accessibility and control of chronic issues. It is cheaper and accessible medical care that decreases
diseases[3].Smart Health Consulting System allows real-time reliance on emergency physician visits[9].The Smart Health
patient monitoring and physician consultation remotely, Consulting System gives individuals the capacity to diagnose
enhancing emergency response and access to care[4].Smart illness, seek expert opinion, and receive treatment
Health Consulting System allows real-time monitoring of recommendations. It enhances access to medicine, lowers
health, remote consultation of doctors, and symptom analysis. hospitalization, and facilitates timely medical treatment[10].
It enhances the efficiency of healthcare by offering
individualized recommendations regarding treatment and II. LITERATURE SURVEY
emergency alerts[5].The Smart Health Consulting System
uses mobile technology and artificial intelligence to offer Pattanaik et al. (2022) suggested a Smart Health
real-time medical consultations and initial diagnoses. It Consulting Android app which allows users to find suitable
increases access and affordability, providing timely doctors according to the symptoms, make disease predictions
healthcare interventions, particularly in rural areas[6].The by using a Naïve Bayes classifier, schedule online

IJISRT25APR619 www.ijisrt.com 1236

Volume 10, Issue 4, April – 2025 International Journal of Innovative Science and Research Technology
ISSN No:-2456-2165 https://doi.org/10.38124/ijisrt/25apr619
appointments, send medication reminders, and give feedback more accurate prediction compared to sole-model
in order to make the system more efficient[1].Bodhe et al. utilization[3].Hybrid deep learning model of CNN and
(2014) suggested a mobile-based healthcare system based on LSTM. CNN extracts space features from input data and
Android OS which allows for diabetic patients to carry out LSTM extracts temporal patterns. The model is employed for
self-monitoring, send symptoms and physiological values to enhancing prediction accuracy for time-series data[4].CNN
a server-based expert system that interprets data, determines learns features, BiLSTM learns bidirectional temporal
the severity scores of diseases, and offers quick diagnosis and relationships, and attention highlights[5].Hybrid CNN-
e-prescriptions for patients with limited access[2].The LSTM model for time-series prediction. Spatial high-level
suggested system takes advantage of a deep learning-based features are learned by the CNN blocks, and
system combining Convolutional Neural Networks (CNN) temporalrelationships are learned by the LSTM blocks. They
and Long Short-Term Memory (LSTM) networks to detect collectively result in improved prediction accuracy on
plant diseases accurately and in real-time through leaf images sequential data[7].A hybrid deep model based on CNN and
(Author(s), Year)[3].The suggested system takes advantage GRU. A CNN is applied to provide local features and a GRU
of a Convolutional Neural Network (CNN) model that has is applied to provide temporal dependency on sequential data.
been trained on a varied set of leaf images in order to detect The model has been applied to improve performance over
and classify plant diseases automatically with high accuracy time-series prediction issues[8].A system for patient health
and less human involvement (Prajapati et al., 2017)[4].The monitoring based on IoT using sensors to acquire real-time
system proposed uses a hybrid deep learning model that patient information. The system sends information to a cloud
integrates Convolutional Neural Networks (CNN) and platform for remote alerting and monitoring. It is designed to
Support Vector Machines (SVM) for accurate classification provide timely medical intervention and enhance patient
of plant leaf diseases based on image processing methods care[8].An Android app with a backend database to store
(Singh & Misra, 2017)[5].The system proposed combines patient data, doctor's appointments, and prescriptions. It
image processing methods with a Convolutional Neural allows real-time interaction between healthcare providers and
Network (CNN)-based classifier to automatically identify patients. The system increases accessibility and efficiency in
and diagnose plant leaf diseases from images captured, the management of healthcare[9].A web-based system of
improving accuracy and minimizing manual labor (Patil & health counseling in which symptoms are entered in order to
Kumar, 2020)[6].The suggested system employs a deep generate possible diagnoses employing a rule-based expert
learning method with an application of pre-trained VGG16 system. It also offers appointment scheduling with doctors
Convolutional Neural Network to recognize and classify and health counseling. It also aims at providing simple health
different plant leaf diseases based on images, with the care and curbing hospital admissions for unnecessary
aspiration of offering a quick, automated, and accurate reasons[10].
diagnostic tool (Sharma & Jadon, 2020)[7].The system
utilizes Internet of Things (IoT) sensors coupled with an IV. PROPOSED MODULE
Android application for permanent monitoring of vital signs
in patients and presenting the same to physicians in real-time, The "Smart Health Consulting System" suggested module is
supporting enhanced remote care and emergency treatment to provide an electronic health assistant that combines user-
(Shaikh et al., 2017)[8].The system is a health care friendly design, efficient data handling, and intelligent
management application using an Android system meant to decision-making to improve the accessibility of healthcare
maintain patients' records, set appointments, and deliver and response time. It is programmed on XML with the front
instant medical reminders, thus automating doctor-patient end based on Java to offer a responsive and interactive mobile
communication (Kumar & Joseph, 2015)[9].The system app interface. The backend is powered by SQLite based on its
presented here provides an online intelligent health light and high-performance database capabilities for mobile
consulting platform in which patients are able to operating systems. The system is primarily intended to assist
communicate with physicians using a web interface, users in identifying potential illnesses based on the symptoms
facilitating effective symptom-based diagnosis and they experience and recommend suitable hospitals or medical
consultation without visiting them physically (Kumar et al., facilities and offering an e-appointment facility. The module
2018)[10]. begins with requesting the user to register by providing
simple personal information, which is stored securely in the
III. EXISTNG MODEL system. After registration, users are able to login using their
individual personal credentials. After login, the users can
The current model utilizes machine learning models like choose from a predefined set of symptoms, which are general
SVM and KNN with manually extracted features from plant manifestations of various diseases. The symptoms are then
leaf images for disease classification. It has the need for analyzed by an inbuilt classification algorithm that maps the
image preprocessing methods like segmentation and feature symptoms to potential diseases. This method is vital because
extraction[1].The current model utilizes image processing in the real world patients are never capable of detecting the
methods coupled with machine learning models like SVM severity or the specificity of the condition when symptoms
and ANN for plant disease classification. It relies on manual overlap or appear mild. The algorithm defeats the complexity
feature extraction like color, texture, and shape from leaf of many symptoms pointing to different conditions by
images[2].Hybrid of ARIMA and LSTM-based data
forecasting system. ARIMA processes linear parts and LSTM
processes nonlinearity trends. The hybrid model provides a

IJISRT25APR619 www.ijisrt.com 1237

Volume 10, Issue 4, April – 2025 International Journal of Innovative Science and Research Technology
ISSN No:-2456-2165 https://doi.org/10.38124/ijisrt/25apr619
The disease prediction engine decides whether the  Confirmation
patient is likely to be suffering from any disease or if the This module entirely for doctor they can log this mobile
symptoms are within normal limits. If a disease is predicted, app and can see request of user. Then they can provide
the system proceeds to the hospital recommendation process. confirmation and rejection service alert to user. User will
Hospitals are filtered and suggested based on the nature of receive appointment service confirmation or reject sms alert
disease, proximity to the user, and available specialists, in a proper manner.
thereby personalizing the experience. The feature of hospital
suggestion ensures that the users are led to the correct kind of  Chatbot Process
medical treatment without consuming time or resources. In The application also includes chatbot system, allowing
addition, patients are able to make appointments directly users to User can post any question using chatbot option
through the application, without waiting in long queues and based on user query Chabot will provide efficient automate
lines at hospitals. This is a digital approach that reduces the response to user.
burden on physical healthcare systems and speeds up the
process of the initial consultation. The system is also scalable, V. FLOW DIAGRAM
with integration with electronic health records and wearable
devices being feasible in future releases. The design is also DFD illustrate how data interact with a system. DFD are
inclusive with the view to helping users in rural and semi- very helpful in modeling many business function aspects
urban regions where immediate medical consultation is not since they break down a task into fundamental parts. This
easily accessible. Overall, the proposed module is a key pillar makes it easier for the analyst to comprehend the modelable
in making the transition from traditional healthcare delivery system that they are attempting to model. Data flow diagram
approaches to smart, AI-driven healthcare delivery centered represents a system by making use of external entities from
on early detection, user empowerment, and optimal medical where data flow towards a process in which transmission of
service accessibility. the data and produces output data which is moved to other
processes on external entities of files. Data can flow to
 Enrollment/Authentication process also as inputs. this is a sample healthcare appointment
This module is primarily mobile user based. With the system diagram. The users first log in/register and then
help of this module user and doctor can register in the proceed to their own dashboard. They can either book
registration form he has to fill with personal information like appointments (pick their preferred dates and times) or see
username, create password, mobile number, mail id. This will doctors directly via chat/video calls.Both these routes meet at
be stored in a different table. With the help of this password the medical history viewing feature, meaning after either
user can log on this mobile application. After successful login booking appointments or seeing doctors, users can see their
they can utilize app feature in effective manner. medical records. This health system end-to-end flow diagram
illustrates a patient experience across an end-to-end digital
 Doctor Profile Upload health platform. The process starts at the "Start" node,
This module completely based for doctor.First doctor pointing users to the "User Registration/Login" step where
can log in to this android application by using the correct they register or log in their account credentials. After
username and password. After logging in successfully can authentication, patients go to the "User Dashboard," the main
upload profile-related information such as Name, point for all system activities. From this point, the users are
specialization, experience, availability, fees, etc, these details able to choose either of two main paths: they can either "Book
are kept by separate table Appointment" and "Select Date/Time" for clinic visits, or
"Consult Doctor" via "Chat/Video Call" channels for
 Symptoms Upload and Diagnosis telemedicine consultations. Both paths merge at the "View
This module completely based for user.Firstly user r Medical History" module so that patients can view their
can login into this android application by entering the correct medical history irrespective of consultation type. This kind of
username and password. After login user can able to choose architecture supports continuity of care by maintaining full
their symptoms. According to user chosen symptoms medical records. The system facilitates flexibility in the
proposed mobile application apply pattern matching delivery of healthcare through central patient information. It
algorithm and categorize the disease efficiently optimizes user convenience with scheduled appointments and
virtual consultation at the point of need. The website must
 Appointment Booking connect with backend databases to maintain patient records,
This module entirely based for user. When ever user schedule appointments, and doctors' schedules. The stripped-
press doctor information button this system fetch doctor down design places the user first through logical transitions
details as per experience. Last complete doctor information between steps. The electronic healthcare solution in this case
show to user. After that user can choose doctor and request is a demonstration of how technology can render healthcare
pre booking these information includes Name, service type, services more accessible without undermining professional
timing, Place this request automatically goes to doctor for medical standards. The flow terminates at the "End" point,
conformation. which symbolizes the conclusion of a successful healthcare
interaction in this electronic environment. The system offers
an affordable means of healthcare management, with
scheduling features and virtual consultations, but yet access
to patient medical history.

IJISRT25APR619 www.ijisrt.com 1238

Volume 10, Issue 4, April – 2025 International Journal of Innovative Science and Research Technology
ISSN No:-2456-2165 https://doi.org/10.38124/ijisrt/25apr619

Fig 1 Level 0

Fig 2 Level 1

IJISRT25APR619 www.ijisrt.com 1239

Volume 10, Issue 4, April – 2025 International Journal of Innovative Science and Research Technology
ISSN No:-2456-2165 https://doi.org/10.38124/ijisrt/25apr619

Fig 3 Level 2

VI. RESULTS AND DISCUSSION predictions. It also successfully guided users to nearby or
appropriate hospitals and enabled appointment reservations.
The system was validated on the grounds of user Users were satisfied with the simplicity of the system during
satisfaction, response time, and diagnostic accuracy. Below is testing and that they could get basic medical knowledge
a summary of the test result of 50 users who utilized the Smart without having to visit hospitals in a hurry. Disease prediction
Health Consulting System. The Smart Health Consulting logic, being rule-based, was useful for common patterns of
System was effectively deployed as a mobile application symptoms. But it's seen that one can improve more on
where users are able to input symptoms and obtain possible accuracy if machine learning can be integrated later on. The
disease predictions and hospital recommendations. The project has potential to help rural and semi-rural areas poor in
system was tested with various symptom inputs to examine healthcare infrastructure by giving them a provisional
its responsiveness and accuracy. Tests confirmed that the diagnosis and hospital orientation
system correctly classified symptoms and made appropriate

Table 1 System Performance Evaluation

IJISRT25APR619 www.ijisrt.com 1240

Volume 10, Issue 4, April – 2025 International Journal of Innovative Science and Research Technology
ISSN No:-2456-2165 https://doi.org/10.38124/ijisrt/25apr619
60% of users rated the User Interface as Excellent, without any Poor scores.Diagnostic Accuracy was also well-
confirming that the system overall is intuitive and easy to use. liked: 65% of the users scored it Excellent, 25% Good, and
Another 30% gave it a Good rating, implying that design is 10% Fair. These ratings imply that users tend to have
good but possibly there could be some improvement in such confidence in the system to give sound health advice and
areas as visual layout and user flow. Just 10% said it with a suggestions Overall Satisfaction is the total impression of the
Fair response, with zero who said that it was Poor, reflecting items listed above. Here, 68% of the users gave the system an
in general positive acceptability. With respect to Response Excellent rating, 22% a Good rating, and 10% a Fair rating.
Time, the system performed marvelously, such that 70% The reason that in all these there is not even a single Poor
evaluated it as Excellent while 20% as Good. This is to note rating is an indication of the reliability and faith of the users
the timeliness and the system's responsiveness in providing in the system.
medical answers and consults. Only 10% scored it Fair, again

Fig 4 System Evaluation Results

The bar chart visually confirms the data provided in the Optimization Learning models that adapt through feedback
table. It is a comparative chart of user opinion on the basis of and history can make and customize diagnoses more accurate.
the four measurement parameters. The "Excellent" bar Emergency Alert System A warning feature that alerts
prevails in every category, which means that the vast majority emergency personnel or caregivers in the event of significant
of the users had an extremely good experience with the health findings made can give an added sense of safety.
system. The excellent experience ratings are also very high in Mobile Application System integration to a mobile app would
Response Time and Overall Satisfaction. The "Good" bars are allow the users to access the advice of health services on their
the second tallest in height in every group so that the system terms while on the go. The second significant growth area is
is adequate even when it is not better than hoped for all. The Artificial Intelligence and Natural Language Processing
"Fair" low and in every group uniformly report individual and integration, which would allow the system to better interpret
small-group user complaint problems. Of equal importance, sophisticated user inputs and also provide even more accurate
the absence of any "Poor" ratings graphically confirms the outputs. Furthermore, the integration of multilingual support
uniform performance and popularity of the system. graph would be a facilitation of overcoming language barriers and
finishes the table by summing up the good trends and relative the provision of equal access to healthcare services to those
performance of the system in a single look. It makes sure that from other linguistic backgrounds. The integration of
users are generally satisfied with the Smart Health Consulting wearables such as smartwatches and fitness bands can help
System, especially speed, accuracy, and satisfaction. facilitate continuous tracking of symptoms such as heart rate,
oxygenation levels, and sleeping patterns, which would assist
VII. FUTURE ENHANCEMENT in providing dynamic real-time recommendations regarding
health.
Integration with Wearable Devices Utilization of real-
time health information from fitness bands and smart watches VIII. CONCLUSION
would enhance the diagnostic performance as well as enable
permanent monitoring. Multilingual Support Support for The Smart Health Consulting System is evident to
multiple languages for the system would make the system facilitate medical consulting and diagnosis by using smart
more user-friendly for users across languages. Voice-Enabled technology. Being user-friendly, having quick response, and
Interaction Voice communication and voice output embedded reliable diagnostic results, the system generates a
in the system would help enhance convenience, especially for considerable amount of value to both medical professionals
blind patients or older patients. Machine Learning and patients. Test results confirm extremely high user

IJISRT25APR619 www.ijisrt.com 1241

Volume 10, Issue 4, April – 2025 International Journal of Innovative Science and Research Technology
ISSN No:-2456-2165 https://doi.org/10.38124/ijisrt/25apr619
satisfaction with the operation of the system for all the most Data for Sustainable Health Monitoring," Mobile
critical indicators by the vast majority of users. Overall, this Networks and Applications, vol. 21, no. 5, pp. 825–
model is the best reflection of the potential through which AI- 845, Oct. 2016
based health platforms are likely to improve access to timely [5] P. R. Deshmukh, D. M. Dhamdhere, and P. J.
and standardized health advice, especially for healthcare- Waghmare, "Disease Prediction System Using
underdeveloped regions. Through the application of Machine Learning," International Journal of
sophisticated technologies such as cloud computing, Scientific Research in Science and Technology, vol.
intelligent algorithms, and readable human interfaces, it can 8, no. 2, pp. 199–204, 2021.
improve availability, punctuality, and credibility of care. The [6] M. Chen, Y. Ma, J. Song, C. Lai, and B. Hu, "Smart
system addresses some of the traditional problems of Clothing: Connecting Human with Clouds and Big
conventional provision of health care, including long waiting Data for Sustainable Health Monitoring," Mobile
lists, rural access deficits, and shortages of health Networks and Applications, vol. 21, no. 5, pp. 825–
professionals. The system has the ability to empower users to 845, Oct. 2016.
manage their own health through on-demand consultation and [7] T. K. Das, A. S. Roy, and S. Paul, "IoT Based Health
symptomspecific advice. The architecture is adaptive and Monitoring System," International Journal of
flexible, thereby allowing it to scale with new technologies Research in Electronics and Computer Engineering,
and health care practices. Besides, its integration with vol. 6, no. 2, pp. 99–103, 2018.
wearable devices and electronic health records enables [8] Das, T. K., Roy, A. S., & Paul, S. (2018). IoT Based
holistic and continuous monitoring of well-being. Overall, the Health Monitoring System. International Journal of
Smart Health Consulting System is not only an answer to Research in Electronics and Computer Engineering,
current medical problems but also a futurist step towards a 6(2), 99–103.
coordinated, effective, and intelligent healthcare system in [9] Chen, M., Ma, Y., Song, J., Lai, C., & Hu, B. (2016).
the future.the suggested mobile application seeks to transform Smart Clothing: Connecting Human with Clouds and
the healthcare industry by leveraging emergent technologies Big Data for Sustainable Health Monitoring. Mobile
to mitigate the sophistication of disease diagnosis, doctor Networks and Applications, 21(5), 825–845.
appointment, and query resolution. Implementing a pattern [10] Deshmukh, P. R., Dhamdhere, D. M., & Waghmare,
matching algorithm as a pre-prediction algorithm for diseases P. J. (2021). Disease Prediction System Using
based on the complaint outlined by the user, the application Machine Learning. International Journal of Scientific
offers a novel and stand-alone solution for preliminary Research in Science and Technology, 8(2), 199–204
diagnosis assistance. The addition of a doctor appointment
system also improves user experience, allowing easy booking
of consultations with specialists according to the needs of the
patient. Implementing a chatbot offers the ability to provide
instant, automated responses to users' questions, providing
timely support to patients without the need for open human
contact. With such add-ons, the app can maintain minimized
manual effort on the part of healthcare providers and provide
a better, efficient, accessible, and user-based program for
patients. This cell phone application not only offers improved
quality health care service, but also erases the gap that exists
between patients and doctors, especially those people who
might not have easy access to hospital centers.

REFERENCES

[1] S. R. Bharamagoudar, R. B. Geeta and S. G. Totad,

"Web Based Student Information Management
System," International Journal of Advanced Research
in Computer and Communication Engineering, vol. 2,
no. 6, pp. 2349–2353, June 2013.
[2] T. K. Das, A. S. Roy and S. Paul, "IOT based health
monitoring system," International Journal of Research
in Electronics and Computer Engineering, vol. 6, no.
2, pp. 99–103, 2018.
[3] N. Z. Khan, A. Hussain, and R. Amin, "An Intelligent
Healthcare System for Detection and Classification of
Chronic Diseases using Machine Learning
Techniques," Journal of Healthcare Engineering, vol.
2020, Article ID 8883276, 2020.
[4] M. Chen, Y. Ma, J. Song, C. Lai, and B. Hu, "Smart
Clothing: Connecting Human with Clouds and Big

IJISRT25APR619 www.ijisrt.com 1242