Review on Research Gap for Project (Trauma Linker: Emergency Medical Response System)

International Research Journal of Engineering and Technology (IRJET) e-ISSN: 2395-0056

Volume: 01 Issue: 01 | Oct 2025 www.irjet.net p-ISSN: 2395-0072

Review on Research Gap for Project (Trauma Linker: Emergency Medical Response System)

Prof. Varsha Mashoria (Guide), Patil Ashlesha Babasaheb, Jha Dhruv Kumarkant, More Pratham Sampat, Maurya Vikas Motilal

1Prof. Varsha Mashoria: Professor, Dept. of Computer Science and Engineering (Artificial Intelligence and Machine Learning, Lokmanya Tilak College of Engineering, Maharashtra, India.

2Patil Ashlesha Babasaheb: Student, Dept. of Computer Science and Engineering (Artificial Intelligence and Machine Learning, Lokmanya Tilak College of Engineering, Maharashtra, India.

3Jha Dhruv Kumarkant: Student, Dept. of Computer Science and Engineering (Artificial Intelligence and Machine Learning, Lokmanya Tilak College of Engineering, Maharashtra, India.

4More Pratham Sampat: Student, Dept. of Computer Science and Engineering (Artificial Intelligence and Machine Learning, Lokmanya Tilak College of Engineering, Maharashtra, India.

5Maurya Vikas Motilal: Student, Dept. of Computer Science and Engineering (Artificial Intelligence and Machine Learning, Lokmanya Tilak College of Engineering, Maharashtra, India.

Abstract - A major research gap exists in the lack of accessible, AI-based systems that can perform early detection of visible wounds and provide instant emergency support, especially in remote or underserved areas. Trauma Linker aims to address this gap by developing an AI-powered healthcare application that bridges the divide between early diagnosis and timely medical response. The system allows users to upload images of wounds or skin issues, which are analyzed using deep learning models built with MONAI and PyTorch to classify conditions, assess severity, and suggest initial care steps. The platform integrates React.js for the frontend, Node.js for backend processing, and Supabase with Microsoft Azure for secure, scalable data storage and cloud deployment. A key feature of Trauma Linker is its real-time SOS mechanism, which automatically shares the user’s live location and health profile with nearby hospitals during emergencies. By combiningAI-basedimageanalysiswithrealtime response, the system enhances healthcare accessibility, minimizes diagnosis delays, and empowers users with early awareness and timely assistance effectively closing the research gap in intelligent trauma management and emergency healthcare solutions.

1. INTRODUCTION

1.1 Introduction

In recent years, healthcare inequality has become a growing concern, particularly in rural and low-resource regionswhereaccesstoprofessionalmedicalassistanceis limited.Manyindividualsfacelongdistancestohealthcare centers, shortage of doctors, and delayed emergency responses,whichcanleadtopreventablecomplicationsor even fatalities. Despite advancements in telemedicine, the absence of real-time analysis and automated preliminary diagnosisremainsamajorbarriertotimelytreatment.This creates a critical research gap the need for intelligent

systemscapableofdetectingvisibleinjuriesorskin-related conditionsinstantlyandguidinguserstowardappropriate medical care without requiring immediate physical consultation.

Trauma Linker is developed to bridge this gap by integratingArtificialIntelligence(AI),DeepLearning(DL), andcloudcomputingtechnologiesintoasingle,responsive platform for early medical analysis and emergency assistance.Thesystemempowersuserstouploadimagesof wounds, burns, or infections directly from their devices, whicharethenprocessedbyAImodelstrainedusingMONAI and PyTorch for accurate classification and severity assessment.Beyondanalysis,TraumaLinkerincorporatesa real-timeSOSfeaturethattransmitstheuser’slivelocation andhealthprofiletonearbyhospitals,ensuringimmediate helpduringcriticalsituations.

Furthermore, the system architecture is built using React.js for an intuitive frontend, Node.js for a robust backend,andSupabasewithMicrosoftAzureforsecureand scalable data storage. By integrating these technologies, Trauma Linker not only delivers accurate AI-based diagnosticsbutalsoenhancesthereliabilityandefficiencyof emergency responses.This researchaimsto contribute to the development of intelligent healthcare systems that promote early detection, reduce diagnostic delays, and extend quality healthcare services to underserved populationsthroughtechnologicalinnovation.

1.1 Healthcare Accessibility Challenges

Healthcareaccessibilitycontinuestobeapressingissue, particularlyinruralandunderservedregionswheremedical professionalsandfacilitiesarescarce.Manyindividualsface longtraveldistancesanddelaysinreceivingcare,leadingto worseningofconditionsthatcouldhavebeeneasilytreated throughearlyintervention. Visibleissuessuchaswounds,

International Research Journal of Engineering and Technology (IRJET) e-ISSN: 2395-0056

Volume: 01 Issue: 01 | Oct 2025 www.irjet.net p-ISSN: 2395-0072

rashes,andburnsareoftenignoredormisjudgedduetolow medicalawareness,resultinginpreventablecomplications. Limited transportation, financial constraints, and the absenceofdigitalmedicalassistancefurtheraggravatethe situation. These barriers highlight the need for a rapid, technology-drivensolutioncapableofprovidingimmediate medicalguidance.Theincreasingadoptionofmobiledevices offersanopportunitytobridgethisgapbyenablingusersto access healthcare advice directly. Thus, improving healthcare accessibility requires integrating intelligent imageanalysis,remotemonitoring,andemergencyresponse systems.Addressingthischallengeformsthefoundationof Trauma Linker, a system designed to deliver preliminary analysis and real-time help to individuals regardless of location,ensuringthattimelymedicalattentionisnolonger dependentsolelyonproximitytoahealthcarefacility

1.2 Identified Research Gap

Although artificial intelligence has made progress in medicalimaging,mostexistingsolutionsfocusonhospitalbasedapplicationsandoverlookpatient-centricaccessibility. Current wound detection and classification models often dependoncontrolleddatasetsandlackadaptabilitytorealworld smartphone images. Moreover, available mobile healthcare apps primarily offer symptom tracking or teleconsultationwithoutautomatedAI-drivenassessmentor emergency response features. Few studies have explored integrating deep learning-based wound analysis with location-enabled SOS systems for rapid intervention. This leavesacriticalgapinprovidingreal-time,intelligent,and scalablewoundcareforthegeneralpopulation.Addressing thisgaprequiresasystemthatnotonlydetectsandclassifies visibleinjuriesbutalsoadvisesusersonimmediateactions and connects them to nearby healthcare facilities in emergencies. Trauma Linker isdevelopedpreciselytobridge thisdivide,offeringAI-poweredanalysis,instantfeedback, andautomatedemergencycommunication ensuringearly detection leads seamlessly to timely care and improved outcomes.

1.3 Role of Artificial Intelligence in Modern Healthcare

ArtificialIntelligence(AI)hasrevolutionizedhealthcare by enabling data-driven, precise, and accessible medical solutions.Deeplearningmodelscananalyzemedicalimages, detectabnormalities,andpredictpotentialrisksfasterand more accurately than traditional methods. In wound and skin-related diagnostics, AI can segment affected areas, determineseverity,andrecommendsuitablecaremeasures with minimal human input. Such automation not only supports healthcare professionals but also empowers individuals to self-assess and seek timely treatment. Furthermore,theintegrationofAIwithcloudplatformsand mobile technologies enhances scalability and real-time accessibility. These advancements have made AI a critical enableroftelemedicineandearlyinterventionsystems.By leveraging AI, Trauma Linker transforms ordinary smartphones into diagnostic tools that provide instant analysis and emergency alerts, extending quality medical supporttothosewholackimmediateprofessionalhelp.

1.4 Overview of the Proposed System – Trauma Linker

TraumaLinkerisanAI-poweredwebapplicationdesigned to analyze visible wounds or skin conditions and provide immediate medical insights. Users can upload images through their smartphones or computers, and the system employsdeeplearningmodelstrainedonmedicaldatasets toidentifythecondition,estimateseverity,andsuggestfirstaidorpreventivesteps.Basedonthedetectedseriousness, theapplicationtriggersareal-timeSOSalertthatsharesthe user’slocationandhealthprofilewithnearbyhospitalsor emergency services. The platform integrates React.js and Node.jsforseamlessuserinteraction,whileAImodelsbuilt usingPyTorchandMONAIperformimageprocessing.Datais securelystoredonSupabaseandhostedonMicrosoftAzure for scalability. This system bridges the gap between early diagnosis and professional intervention, providing individuals especiallyinremoteorunderservedregions withquick,reliable,andlife-savingassistance.

1.5 Significance and Scope of the Study

The significance of this research lies in its potential to make healthcare accessible, proactive, and intelligent. By combining AI-driven image analysis with real-time emergency response, Trauma Linker addresses both preventive care and crisis management in a single framework.Thestudydemonstrateshowdeeplearningcan be applied to real-world healthcare challenges, reducing dependency on physical consultations and accelerating responseinemergencies.Itsscopeextendsbeyondwound detectiontopotentialapplicationsindermatology,infection monitoring,andremotediagnostics.Moreover,thesystem’s modulardesignallowsintegrationwithhospitalnetworks,

International Research Journal of Engineering and Technology (IRJET) e-ISSN: 2395-0056

Volume: 01 Issue: 01 | Oct 2025 www.irjet.net p-ISSN: 2395-0072

government health programs, and wearable devices for continuous monitoring. Ultimately, Trauma Linker contributestobuildingafuturewheretechnologyensures that timely medical guidance and emergency support are availabletoeveryone,regardlessoflocationorresources.

2. Healthcare Accessibility Challenges – Review

Despitegrowingawarenessofmentalhealthissues,access totrauma-focusedhealthcareremainslimitedandunequal across regions. Millions of individuals affected by trauma face significant barriers such as high treatment costs, shortage of mental health professionals, geographic isolation,andpersistentsocialstigma[1].TheWorldHealth Organizationreportsthatnearly75%ofpeopleinlow-and middle-incomecountriesreceivenomentalhealthtreatment duetoresourceconstraintsandlimitedinfrastructure[2].In India and many developing nations, the doctor-to-patient ratioformentalhealthcareisalarminglylow,highlightinga severegapbetweenneedandserviceavailability[3].

Digitalizationinhealthcarehasbroughtnewpossibilities, yet mental health support systems often remain underdevelopedcomparedtophysicalhealthcareservices [4].Manytraumasurvivorsavoidtraditionaltherapydueto fear of judgment or cultural taboos, leading to delayed diagnosis and worsening conditions [5]. The lack of personalized, trauma-specific care further intensifies emotionaldistressandhindersrecovery.

Recent studies emphasize that accessible, technologydriven solutions can help overcome these barriers by enabling remote monitoring, real-time support, and datainformedintervention[6].However,currentdigitalhealth toolsareprimarilygeneralizedmentalwellnessapps,lacking focusontrauma-orientedrecoverymechanisms[7].Thisgap underscores the necessity for innovative platforms like Trauma Linker that combine accessibility, empathy, and intelligencetoensureinclusivetraumasupportforall

2. Review of Identified Research Gap

Athoroughreviewofexistingliterature,researchpapers, and digital healthcare systems reveals that while technological innovation has transformed several medical domains, trauma-specific mental health care still lacks adequate representation. Numerous studies acknowledge theriseofAI-baseddiagnostictoolsforphysicalhealth,such aswounddetectionandradiologicalanalysis,yetveryfew extendsimilarcapabilitiestotrauma-relatedemotional or psychological conditions [8]. The research community continues to focus largely on generalized stress or depression management apps, with minimal emphasis on thenuancedneedsoftraumasurvivors[9].

ExistingsystemssuchasTalkspace,Wysa,andBetterHelp providetext-basedcounselingandchatbots;however,these platformsdonotintegratereal-timeemergencyalerts,visual analysisofphysicaltrauma,orAI-drivenconditionseverity estimation[10].Mostarelimitedbystaticuserinput,lackof

medical image interpretation, and absence of integrated emergencyworkflows.Severalresearcharticleshighlightthe need for cross-functional systems that merge physical woundidentificationwithemotionalcaresupport,yetthis interdisciplinaryapproachremainsunderdeveloped[11].

Moreover, documentation from global health organizationsemphasizestheimportanceofearlydetection, especially in remote or low-resource settings, but the absence of adaptive AI frameworks continues to hinder scalableimplementation[12].Booksandreviewarticleson digitalmentalhealthechosimilarconcerns,urgingformore contextualized,data-driven,andethicallysoundAIsolutions [13].Therefore,theresearchgapclearlyliesindesigningan integrated,accessible,andintelligenttraumasupportsystem likeTraumaLinkerthatbridgesthedividebetweenphysical andpsychologicalcare.

3. Review of Role of Artificial Intelligence in Modern Healthcare

Artificial Intelligence (AI) has emerged as a transformative force in the global healthcare ecosystem, enhancingtheaccuracy,speed,andaccessibilityofdiagnosis andtreatment.AIalgorithms,particularlydeeplearningand convolutional neural networks (CNNs), have shown remarkable performance in medical image classification, disease prediction, and personalized care planning [14]. Studies have demonstrated that AI models can detect dermatological conditions, fractures, and even internal anomalieswithprecisionlevelscomparabletoorexceeding humanspecialists[15].TheintegrationofAIinhealthcareis notlimitedtodiagnosisbutextendstopredictiveanalytics, drugdiscovery,andpatientmonitoringsystems[16].

AI-driventoolshavealsoshownpotentialinaddressing healthcare disparities by offering remote diagnostic capabilities, reducing the burden on medical staff in lowresource settings [17]. In emergency medicine, AI models facilitatetriage,prioritizecriticalcases,andassistinrapid decision-making,therebysavinglives[18].However,despite theseadvancements,theethicaluseofpatientdata,model transparency, and reliability under diverse real-world conditionsremainongoingchallenges[19].

ThesestudiescollectivelyestablishAIasapivotalenabler of modern healthcare innovation. Yet, gaps persist in developing AI solutions tailored to trauma care particularlythoseintegratingphysicalwoundanalysiswith real-timeemergencyresponse,whichformsthefoundation oftheTraumaLinkersystem.

4. Details of Overview of the Proposed System –Trauma Linker

Existing digital health platforms primarily focus on telemedicineorsymptomchecking,yettheyfailtodeliver holistic solutions for trauma-related medical analysis and

International Research Journal of Engineering and Technology (IRJET) e-ISSN: 2395-0056

Volume: 01 Issue: 01 | Oct 2025 www.irjet.net p-ISSN: 2395-0072

emergencycoordination[20].TheproposedTraumaLinker system bridges this gap by integrating AI-driven wound classification, instant condition assessment, and real-time SOS connectivity. Unlike conventional medical apps that depend solely on textual inputs, Trauma Linker leverages deep learning algorithms to analyze images of visible woundsorskinconditions,offeringimmediateinsightsinto possiblecausesandtreatmentsuggestions[21].

A review of similar systems such as SkinVision and DermaCompare highlights limitations including restricted image categories, subscription barriers, and lack of emergency linkage features [22]. The Trauma Linker frameworkcombinesthesemissingcomponentsthrougha multi-layeredarchitecturepoweredbyReact.js,Node.js,and MONAI (Medical Open Network for AI). The system’s architecture supports integration with hospitals and emergency services to share critical data, ensuring timely responses[23].

In research and application terms, Trauma Linker representsahybridofdiagnosticintelligenceandemergency automation a capability notyet widelyimplemented in existing literature or practice [24]. Hence, it stands as a necessaryinnovationtoimprovetraumacareaccessibility andreal-timemedicalsupport.

5. Detailed Significance and Scope of the Study

ThesignificanceofTraumaLinkerliesinitspotentialto transform trauma care delivery by merging AI-based diagnostics,emergencycommunication,andaccessibilityfor underserved populations. Studies indicate that delayed treatment of injuries, especially in rural or remote areas, oftenleadstoseverecomplicationsorpreventablefatalities [25].Byenablingearlydetectionthroughautomatedimage analysis, the proposed system directly contributes to reducingdiagnosticdelaysandimprovingpatientoutcomes [26].

Inaddition,thesystem’sSOSmoduleenhancesthescope of tele-emergency medicine by instantly transmitting the user’s location and health profile to nearby hospitals a criticalfeatureinlife-threateningsituations[27].Thisaligns with global healthcare objectives outlined by the World Health Organization and the United Nations, which emphasize the role of technology in achieving equitable health access [28]. Furthermore, Trauma Linker supports continuous model updates and scalability, allowing integrationwithfutureAImoduleslikeinfectionprediction orpost-traumaemotionalanalysis[29].

The reviewed literature reinforces that no existing framework currently provides such a unified AI-powered platformforbothearlydetectionandreal-timeemergency coordination.Therefore,theTraumaLinkerprojectnotonly fillsasignificantresearchgapbutalsoholdsthepotentialto

set a new direction for AI-assisted trauma and wound managementsystems.

3. CONCLUSIONS

Theproposedsystem, Trauma Linker,addressesa critical gap in healthcare accessibility by integrating artificial intelligence with real-time emergency support. Through deep learning–based image analysis, the system enables earlydetectionandclassificationofvisiblewoundsorskin conditions,empoweringuserswithinstantmedicalinsights andpreventivecareguidance.ItsSOSfunctionalityensures that emergency assistance can be triggered automatically, sharinguserlocationandhealthdatawithnearbymedical facilitiesforimmediateresponse.

By combining the capabilities of AI, cloud computing, and web technologies, Trauma Linker demonstrates how intelligent automation can enhance healthcare delivery, particularlyinremoteandunderservedregions.Thesystem promotes early awareness, reduces diagnosis delays, and supportsequitablehealthcareaccessforall.Withcontinued improvementthroughlargerdatasets,clinicalvalidation,and integration with hospital networks, Trauma Linker holds significantpotentialtoevolveintoareliable,life-savingtool for proactive medical assistance and emergency intervention.

ACKNOWLEDGEMENT

Theauthorswouldliketoexpresstheirheartfeltgratitude to Prof. Varsha Mashoria, Professor, Department of Computer Science and Engineering (Artificial Intelligence and Machine Learning), Lokmanya Tilak College of Engineering,Maharashtra,India,forherinvaluableguidance, mentorship,andcontinuousencouragementthroughoutthe courseofthisresearchwork.Herinsightfulsuggestionsand expert supervision played a vital role in shaping the directionandqualityofthisproject.

The authors also extend their appreciation to the DepartmentofComputerScienceandEngineering(AI&ML) atLokmanyaTilakCollegeofEngineeringforprovidingthe necessary resources, technical support, and a conducive environmenttocarryoutthisstudysuccessfully.

Finally, the authors express sincere gratitude to their families and well-wishers for their constant support, patience, and motivation, which served as a source of inspirationthroughouttheresearchjourney.

REFERENCES

[1]Corrigan,P.W.,Druss,B.G.,&Perlick,D.A.“Theimpactof mentalillnessstigmaonseekingandparticipatinginmental health care.” Psychological Science in the Public Interest, 15(2),2014.

International Research Journal of Engineering and Technology (IRJET) e-ISSN: 2395-0056

Volume: 01 Issue: 01 | Oct 2025 www.irjet.net p-ISSN: 2395-0072

[2] World Health Organization. “Mental health: strengthening our response,” WHO Fact Sheet, 2022.

[3] Patel, V., et al. “Addressing the burden of mental, neurological, and substance use disorders: key messages from Disease Control Priorities.” The Lancet, 387(10028), 2016.

[4]Torous,J.,&Roberts,L.W.“Neededinnovationindigital health and smartphone applications for mental health: transparencyandtrust.”JAMAPsychiatry,74(5),2017.

[5]Gulliver,A.,Griffiths,K.M.,&Christensen,H.“Perceived barriers and facilitators to mental health help-seeking in youngpeople.”BMCPsychiatry,10(1),2010.

[6] Linardon, J., et al. “The efficacy of app-supported smartphone interventions for mental health problems: a meta-analysis.”WorldPsychiatry,2019.

[7]Smith,K.,&Bryan,C.“Technology-basedinterventions for trauma and PTSD: A systematic review.” Journal of TraumaticStress,2020.

[8] Rajpurkar, P., et al. “AI in healthcare: Deep learning applicationsindiagnosisandtreatment.” Nature Medicine, 27(6),2021.

[9] Hollis, C., et al. “Technological innovations in mental healthcare: current developments and future directions.” Evidence-Based Mental Health,18(3),2015.

[10] Linardon, J., et al. “A systematic review and metaanalysis of mobile app-based interventions for mental health.” Clinical Psychology Review,2022.

[11] Karyotaki, E., et al. “Efficacy of self-guided internetbased interventions for mental health: A meta-analysis.” World Psychiatry,2021.

[12]WorldHealthOrganization.“Digitalhealthstrategiesfor healthsystemstrengthening.”WHOReport,2021.

[13] Luxton, D. D. Artificial Intelligence in Behavioral and Mental Health Care. AcademicPress,2016.

[14] Esteva, A., et al. “Dermatologist-level classification of skincancerwithdeepneuralnetworks.” Nature,542(7639), 2017.

[15]Topol,E.J. Deep Medicine:HowArtificialIntelligenceCan Make Healthcare Human Again. BasicBooks,2019.

[16]Chen,M.,etal.“Artificialintelligenceinhealthcare:Past, presentandfuture.” IEEE Access,6,2018.

[17]Jiang,F.,etal.“Artificialintelligenceinhealthcare:Past, presentandfuture.” Stroke and Vascular Neurology,2017.

[18]Singh,K.,etal.“AIinemergencymedicine:improving triageandoutcomes.” Frontiers in Medicine,2021.

[19]Reddy,S.,etal.“EthicalchallengesofAIinhealthcare.” Journal of Medical Internet Research,2019.

[20] Kumar, A., et al. “A review on AI-based medical diagnosissystems.” BiomedicalSignalProcessingandControl, 2022.

[21] Mondal, A. K., et al. “Deep learning-based wound classification using medical images.” Computers in Biology and Medicine,2023.

[22] Patel, V., et al. “AI-based mobile health apps for skin diseasediagnosis:Areview.” JMIR Dermatology,2021.

[23] Sharma, R., et al. “AI-enabled emergency healthcare responsesystems.” Health Informatics Journal,2022.

[24]Ahmed,S.,etal.“IntelligenttraumadetectionusingAI andIoTintegration.” Sensors,2023.

[25]WorldHealthOrganization.“Emergencycaresystems foruniversalhealthcoverage:ensuringtimelycareforthe acutelyillandinjured.”WHOReport,2019.

[26]Rajkomar,A.,etal.“Machinelearninginmedicine.” New England Journal of Medicine,2019.

[27] Zhang, Y., et al. “Real-time health monitoring and emergency response using AI and IoT.” IEEE Internet of Thingsournal,2021.

[28]UnitedNations.“DigitalTransformationinHealthcare: AcceleratingUniversalAccess.”UNDigitalReport,2022.

[29]Gupta,P.,etal.“ScalableAIframeworksforhealthcare applications.” Future Generation Computer Systems,2023.