Page 1270

www.rsisinternational.org

INTERNATIONAL JOURNAL OF LATEST TECHNOLOGY IN ENGINEERING,

MANAGEMENT & APPLIED SCIENCE (IJLTEMAS)

ISSN 2278-2540 | DOI: 10.51583/IJLTEMAS | Volume XV, Issue VI, June 2026

A Systematic Review of Machine Learning Approaches for Predicting

Heat-Related Skin Diseases under Climate Change

Sowmya S, Kavyashree Nagarajaiah

Research Scholar, SSAHE University Tumakuru, Karnataka, India.

Associate Professor, Department of MCA SSIT, SSAHE University, Tumakuru, Karnataka, India

DOI:

https://doi.org/10.51583/IJLTEMAS.2026.150600091

Received: 28 June 2026; Accepted: 03 July 2026; Published: 08 July 2026

ABSTRACT

Climate change has intensified the frequency, duration, and severity of extreme heat events, posing significant

risks to human health, particularly through the increasing burden of heat-related skin diseases. Elevated

temperatures, prolonged ultraviolet radiation exposure, air pollution, and changing environmental conditions

have contributed to the rising incidence of conditions such as heat rash, sunburn, skin infections, dermatitis, and

skin cancer, with children and older adults being especially vulnerable. Recent advances in machine learning

(ML) have enabled the development of predictive models for disease diagnosis and health risk assessment;

however, existing studies predominantly focus either on general heat-related health outcomes or on skin disease

classification using clinical images, with limited integration of climatic, environmental, and demographic factors

for forecasting heat-related skin disease risk under future climate scenarios. The survey presents a

comprehensive review of the current literature on climate-driven heat-related skin diseases and the application

of machine learning techniques for their prediction. The review examines major climatic and environmental

determinants, vulnerable population groups, commonly used datasets, feature selection methods, and predictive

algorithms, including Random Forest, Support Vector Machine, Decision Tree, Artificial Neural Networks,

Gradient Boosting, and Deep Learning models. It further compares model performance, interpretability, and

limitations. The survey highlights emerging research directions for developing robust and interpretable

predictive frameworks capable of forecasting future heat-related skin disease risks under climate change.

Keywords: Climate Change; Heat-Related Skin Diseases; Machine Learning; Predictive Modeling;

Environmental Determinants; Skin Disease Risk Assessment; Extreme Heat; Artificial Intelligence.

INTRODUCTION

The skin is the largest organ of the human body and serves as the primary protective barrier against

environmental hazards [1-2]. It performs several essential physiological functions, including regulating body

temperature, preventing dehydration, protecting against harmful ultraviolet (UV) radiation and infectious agents,

and facilitating sensory perception. Despite its protective role, the skin is continuously exposed to environmental

stressors such as excessive heat, solar radiation, humidity, and air pollutants, making it highly susceptible to a

variety of heat-related skin diseases. Common conditions include heat rash, sunburn, dermatitis, fungal

infections, bacterial infections, and, with prolonged exposure, an increased risk of skin cancer. Early detection

and accurate prediction of these diseases are essential for timely intervention, reducing disease severity, and

improving public health outcomes [3-6].

Climate change has emerged as one of the greatest global public health challenges of the twenty-first century.

Rising global temperatures have increased the frequency, intensity, and duration of extreme heat events and heat

waves across many regions of the world [7-10]. These climatic changes have resulted in significant health

consequences, including increased mortality, hospital admissions, and healthcare resource utilization. Although

cardiovascular, respiratory, and renal diseases have received considerable attention in heat-health research, heat-

related skin diseases remain comparatively underexplored despite being among the earliest and most visible

Page 1271

www.rsisinternational.org

INTERNATIONAL JOURNAL OF LATEST TECHNOLOGY IN ENGINEERING,

MANAGEMENT & APPLIED SCIENCE (IJLTEMAS)

ISSN 2278-2540 | DOI: 10.51583/IJLTEMAS | Volume XV, Issue VI, June 2026

health effects of prolonged heat exposure. Vulnerable populations, particularly children, older adults, outdoor

workers, and individuals with chronic illnesses or low socioeconomic status, are disproportionately affected due

to reduced thermoregulatory capacity and greater exposure to extreme environmental conditions.

The growing availability of environmental monitoring systems, electronic health records, satellite observations,

and climate datasets has created new opportunities for data-driven disease prediction. In recent years, artificial

intelligence (AI), particularly machine learning (ML), has demonstrated remarkable potential in healthcare by

identifying complex and non-linear relationships among large-scale datasets. ML algorithms such as Random

Forest, Support Vector Machine, Decision Tree, Gradient Boosting, Artificial Neural Networks, and Deep

Learning have been widely applied in disease diagnosis, medical image analysis, epidemiological forecasting,

and environmental health studies. Compared with traditional statistical approaches, these techniques can

efficiently analyze heterogeneous data, improve prediction accuracy, and support evidence-based decision-

making [11-14].

Several review studies have summarized the application of machine learning in dermatology, environmental

epidemiology, air pollution, vector-borne diseases, and heat-related health outcomes [15-18]. However, existing

reviews primarily focus on either image-based skin disease classification or general heat-related illnesses such

as heatstroke, mortality, and hospital admissions. Very limited attention has been given to integrating climatic

variables, environmental determinants, demographic characteristics, and future climate projections for predicting

heat-related skin disease risk. Furthermore, issues such as model interpretability, explainable artificial

intelligence, spatiotemporal analysis, climate scenario integration, and region-specific prediction remain

insufficiently investigated.

To address these gaps, this survey presents a comprehensive review of machine learning techniques for modeling

heat-related skin disease risk under climate change. The review examines the influence of climatic and

environmental determinants, identifies vulnerable population groups, summarizes commonly used datasets and

predictive algorithms, and compares their strengths and limitations. It also discusses model evaluation

techniques, interpretability methods, and emerging trends, including explainable AI and climate-informed

predictive modeling. Finally, the survey highlights current research challenges and future directions for

developing robust, interpretable, and climate-resilient machine learning frameworks that can support early

disease prediction, healthcare planning, and evidence-based public health interventions in the face of increasing

global temperatures.

LITERATURE REVIEW

Recent research demonstrates that climate change has emerged as one of the most significant environmental

challenges affecting human health, particularly through increasing heat stress, extreme weather events, and the

growing prevalence of skin and cardiovascular diseases. Lee and Kwon (2023; 2024) emphasized that rising

global temperatures and ultraviolet (UV) radiation adversely affect skin health, leading to increased risks of

dermatitis, psoriasis, melanoma, photoaging, and other dermatological disorders. Their systematic reviews

highlighted the growing role of artificial intelligence (AI)-based customized cosmetics and sustainable heat-

resistant ingredients, such as Hsian-Tsao, in improving skin protection and supporting climate-adaptive

healthcare. Similarly, Basha et al. (2022) investigated the relationship between climatic variables and

erythemato-squamous skin diseases, demonstrating that machine learning techniques can successfully identify

highly correlated weather parameters responsible for disease occurrence, thereby improving predictive

healthcare systems. Several review studies have focused on the application of machine learning in climate-

sensitive healthcare. Boudreault et al. (2025) conducted a comprehensive review of machine learning

applications for modelling extreme heat-related health outcomes and concluded that Random Forest remains the

most widely adopted algorithm, while future studies should incorporate deep learning models with high-

resolution spatiotemporal datasets. Likewise, Ssebyala et al. (2024) reviewed machine learning techniques for

predicting health risks from climate-sensitive extreme weather events and found that algorithms such as Logistic

Regression, Random Forest, Decision Trees, Support Vector Machines, and Bayesian approaches effectively

predicted mortality, heat-related illnesses, and post-traumatic stress disorders. However, the authors emphasized

the urgent need for standardized climate-health datasets to improve model generalizability.

Page 1272

www.rsisinternational.org

INTERNATIONAL JOURNAL OF LATEST TECHNOLOGY IN ENGINEERING,

MANAGEMENT & APPLIED SCIENCE (IJLTEMAS)

ISSN 2278-2540 | DOI: 10.51583/IJLTEMAS | Volume XV, Issue VI, June 2026

The integration of multimodal environmental and healthcare data has further enhanced disease prediction

capabilities. Tiwari et al. (2025) proposed a climate-aware healthcare framework integrating meteorological,

environmental, and clinical datasets for disease outbreak prediction, demonstrating that multimodal machine

learning significantly improves predictive performance compared with conventional approaches. Islam et al.

(2025) similarly highlighted the increasing frequency and intensity of heat waves due to climate change and

advocated the use of data-driven analytical frameworks for climate adaptation and heat stress mitigation.

Aldosary et al. (2025) extended this concept by applying ensemble machine learning techniques to forecast

climate risk and specific humidity in arid ecosystems, thereby improving heat hazard prediction and

environmental risk assessment. Recent clinical investigations have demonstrated the practical application of

machine learning in predicting heat-related health outcomes. Hirano et al. (2021) developed machine learning-

based mortality prediction models using multicentre heat illness registry data and reported that XGBoost

achieved superior predictive performance compared with conventional APACHE-II clinical scoring systems.

Similarly, Javari and Javari (2026) combined epidemiological modelling with machine learning techniques to

investigate cardiovascular hospitalizations associated with heat stress. Their study identified Heat Index, Wet

Bulb Globe Temperature (WBGT), and age as the most influential predictors, while XGBoost produced the

highest classification accuracy for prolonged hospitalization. Forbes et al. (2025) further compared traditional

thermo physiological models with machine learning algorithms for predicting rectal and skin temperatures

among older adults exposed to prolonged heat conditions. Their findings demonstrated that Ridge Regression

significantly outperformed conventional biophysical models, indicating the potential of machine learning for

personalized heat-risk monitoring.

Artificial intelligence has also transformed dermatological diagnosis through deep learning. Alzaeemi et al.

(2026) developed an InceptionV3-based convolutional neural network for pediatric skin disease classification,

achieving high diagnostic accuracy and demonstrating the effectiveness of transfer learning for early disease

detection. Similar advances in image-based classification have encouraged wider adoption of convolutional

neural networks for automated dermatological diagnosis, particularly in regions with limited specialist

availability. Collectively, the reviewed studies consistently demonstrate that climate change is increasingly

influencing public health through direct and indirect pathways, including heat stress, cardiovascular

complications, infectious diseases, and skin disorders. Machine learning and artificial intelligence have emerged

as powerful tools for analysing complex environmental and clinical datasets, enabling accurate prediction, early

diagnosis, and personalized healthcare interventions. Although significant progress has been achieved, several

studies identified limitations such as small datasets, limited geographical diversity, lack of standardized climate-

health databases, and insufficient integration of multimodal information. Future research should therefore focus

on developing large-scale, standardized datasets, incorporating advanced deep learning architectures,

explainable artificial intelligence techniques, and real-time environmental monitoring systems to improve

prediction accuracy and support climate-resilient healthcare systems.

Table 1: Summary of Existing Literature on Artificial Intelligence and Machine Learning Applications for

Climate-Related Health Prediction

Ref. No.

Authors

Dataset

Used

Objectives

Methods

RESULTS

Lee &

Kwon

(2024)

1308

records; 65

eligible

studies

Review AI-

tailored

cosmetics for

climate-

related skin

health

PRISMA

systematic

review

AI-supported

personalized

cosmetics improve

climate-adaptive

skin care.

Basha et al.

(2022)

Climate &

dermatology

dataset (49

attributes)

Predict

erythemato-

squamous

diseases

ML + Pearson

correlation

23 climate attributes

significantly

associated with

disease.

Page 1273

www.rsisinternational.org

INTERNATIONAL JOURNAL OF LATEST TECHNOLOGY IN ENGINEERING,

MANAGEMENT & APPLIED SCIENCE (IJLTEMAS)

ISSN 2278-2540 | DOI: 10.51583/IJLTEMAS | Volume XV, Issue VI, June 2026

Boudreault

et al. (2025)

25 ML

studies

Review ML

for extreme

heat health

impacts

Comprehensive

literature

review

Random Forest most

common;

recommends deep

learning.

Ssebyala et

al. (2024)

6096

records; 7

studies

Review ML

for climate-

sensitive

health risks

Scoping review

ML predicts

mortality, heat

illness and PTSD.

Tiwari et al.

(2025)

50 health &

weather

attributes

Disease

outbreak

prediction

XGBoost +

SHAP

99.2% accuracy

using multimodal

data.

Forbes et al.

(2025)

adults;162

sessions

Predict core &

skin

temperature

Ridge

Regression vs

biophysical

models

Ridge Regression

best (RMSE

0.27°C).

Islam et al.

(2025)

Historical

climate

datasets

Review

heatwave

prediction

ML, LSTM,

ARIMA,

SARIMA

Hybrid ML

improves heatwave

forecasting.

Javari &

Javari

(2026)

Hospital +

ERA5

climate data

Heat stress &

CVD

hospitalization

DLNM, RF,

XGBoost,

SHAP

Heat Index and

WBGT strongly

associated with

hospitalization.

Aldosary et

al. (2025)

Daily

climate data

(1982–

2023)

Forecast

humidity &

heat hazards

SVM, RF,

LightGBM,

XGBoost

LightGBM/XGBoost

achieved R²≈0.999.

Hirano et al.

(2021)

2393 heat

illness

patients

Mortality

prediction

LR, SVM, RF,

XGBoost

outperformed

APACHE-II.

Sousan et al.

(2026)

agricultural

workers

Evaluate

wearable heat

monitoring

RF, GBR,

regression

RF achieved

R²=0.96 for heat

strain prediction.

Wang et al.

(2022)

Climate

chamber

thermal

sensation

study

Predict

thermal

sensation

from skin

temperature

Correlation &

sensitivity

analysis

Chest skin

temperature best

predictor.

Tikarya et

al. (2023)

Review of

cattle skin

disease

datasets

Review CNN

for disease

detection

Deep learning

review

CNNs improve early

disease

identification.

Anderson et

al. (2023)

Perspective

review

Climate

change

impacts on

skin health

Narrative

review

Climate change

increases

dermatological risks.

Alzaeemi et

al. (2026)

520

pediatric

skin images

Website-based

skin disease

diagnosis

InceptionV3

CNN

~88% classification

accuracy.

Page 1274

www.rsisinternational.org

INTERNATIONAL JOURNAL OF LATEST TECHNOLOGY IN ENGINEERING,

MANAGEMENT & APPLIED SCIENCE (IJLTEMAS)

ISSN 2278-2540 | DOI: 10.51583/IJLTEMAS | Volume XV, Issue VI, June 2026

Wu et al.

(2022)

PLA/CeO₂

composite

experiments

Develop UV-

protective

film

Material

characterization

99.3% UV reduction

with improved

strength.

Lee &

Kwon

(2023)

107 selected

studies

Sustainable

skin

protection

Systematic

review

Hsian-Tsao

identified as

promising heat-

resistant ingredient.

METHODOLOGY

The survey paper was conducted using a systematic literature review approach to investigate recent advances in

machine learning (ML) and artificial intelligence (AI) for climate-related health prediction, heat stress

assessment, and skin disease diagnosis. Relevant peer-reviewed journal articles and review papers published

between 2021 and 2026 were selected from high-quality scientific databases based on their relevance to climate

change, heat-health modelling, dermatological disease prediction, and intelligent healthcare systems.

The reviewed studies primarily followed the Preferred Reporting Items for Systematic Reviews and Meta-

Analyses (PRISMA) framework or similar systematic review methodologies. Most studies searched multiple

scientific databases, including PubMed, Scopus, Web of Science, Embase, and MEDLINE, using combinations

of keywords such as machine learning, artificial intelligence, heat stress, climate change, heatwave, skin disease,

thermal sensation, prediction, and healthcare. Duplicate articles were removed, followed by title screening,

abstract screening, and full-text eligibility assessment according to predefined inclusion and exclusion criteria.

The selected studies covered diverse healthcare applications, including prediction of heat-related mortality and

morbidity, development of Heat Health Warning Systems (HHWS), classification of dermatological diseases

using deep learning, and identification of climate-sensitive diseases. Various environmental datasets consisting

of meteorological variables (air temperature, humidity, Wet Bulb Globe Temperature, Heat Index, apparent

temperature, solar radiation, and wind speed) were integrated with clinical and epidemiological datasets

containing hospital admissions, mortality records, physiological measurements, wearable sensor data, and skin

lesion images.

Machine learning techniques [36-41] employed across the reviewed studies included Random Forest (RF),

eXtreme Gradient Boosting (XGBoost), Support Vector Machine (SVM), Decision Tree (DT), Logistic

Regression (LR), Artificial Neural Networks (ANN), Convolutional Neural Networks (CNN), Gradient Boosting

Regression (GBR), Ridge Regression, Light Gradient Boosting Machine (LightGBM), Long Short-Term

Memory (LSTM), and ensemble learning methods. Recent studies also incorporated Explainable Artificial

Intelligence (XAI) techniques, particularly SHapley Additive exPlanations (SHAP), to improve model

interpretability and identify influential environmental and clinical variables.

The extracted information from each study included publication year, study objectives, datasets, machine

learning algorithms, environmental and clinical predictors, validation strategies, evaluation metrics, and major

findings. Comparative analysis was subsequently performed to identify common research trends, strengths,

limitations, and existing research gaps in climate-aware healthcare and intelligent skin disease prediction

systems.

DISCUSSION

The reviewed literature demonstrates that climate change has significantly increased the frequency and intensity

of heatwaves, thereby elevating the global burden of heat-related illnesses, cardiovascular disorders, respiratory

diseases, skin diseases, and mortality. Machine learning has emerged as a powerful computational tool capable

of modelling complex nonlinear relationships between environmental variables and human health outcomes,

enabling more accurate prediction than conventional statistical approaches.

Page 1275

www.rsisinternational.org

INTERNATIONAL JOURNAL OF LATEST TECHNOLOGY IN ENGINEERING,

MANAGEMENT & APPLIED SCIENCE (IJLTEMAS)

ISSN 2278-2540 | DOI: 10.51583/IJLTEMAS | Volume XV, Issue VI, June 2026

Among the reviewed algorithms, Random Forest and XGBoost were the most frequently adopted models

because of their robustness, ability to handle nonlinear relationships, resistance to overfitting, and superior

predictive performance. Deep learning models, particularly Convolutional Neural Networks, have shown

remarkable success in automated skin disease classification by learning discriminative image features directly

from dermatological images without manual feature engineering. Ensemble learning approaches, including

LightGBM and Gradient Boosting models, consistently demonstrated improved predictive accuracy for climate-

sensitive health outcomes.

Most studies integrated meteorological variables such as air temperature, relative humidity, Wet Bulb Globe

Temperature (WBGT), Heat Index, apparent temperature, and solar radiation with healthcare datasets. Several

investigations further incorporated demographic characteristics, physiological measurements obtained from

wearable sensors, hospital admission records, mortality databases, and medical histories to improve prediction

performance. Explainable Artificial Intelligence methods, particularly SHAP, were increasingly adopted to

improve transparency and identify the most influential predictors contributing to disease occurrence.

Although substantial progress has been achieved, several important limitations remain. Most studies relied on

geographically restricted datasets collected from developed countries, reducing model generalizability across

diverse climatic regions. Publicly available multimodal datasets integrating environmental, physiological, and

dermatological information remain scarce. Dataset imbalance, limited external validation, insufficient

consideration of socioeconomic determinants, and lack of standardized benchmark datasets continue to affect

the reproducibility and clinical deployment of machine learning models.

The literature also reveals that current Heat Health Warning Systems primarily depend on temperature thresholds

while overlooking individualized physiological responses, wearable sensor measurements, built-environment

characteristics, and real-time health monitoring. Future intelligent warning systems should integrate

environmental monitoring, wearable Internet of Things (IoT) devices, satellite observations, electronic health

records, and explainable deep learning frameworks to provide personalized early warning systems. Similarly,

future dermatological research should combine climate variables with skin image analysis to investigate climate-

induced skin diseases more comprehensively.

The reviewed studies indicate that integrating artificial intelligence, climate science, environmental monitoring,

and healthcare analytics provides a promising direction for developing intelligent decision-support systems

capable of improving early diagnosis, disease surveillance, personalized healthcare, and climate resilience.

Future research should prioritize large-scale multicenter datasets, explainable machine learning, multimodal data

fusion, federated learning, and real-time predictive systems to facilitate reliable and clinically applicable climate-

aware healthcare solutions.

CONCLUSION

This survey provides a comprehensive review of the current research on heat-related skin diseases and the

application of machine learning techniques for predicting disease risk under changing climatic conditions. The

findings demonstrate that climate change, characterized by rising temperatures, increasing heat waves, and

changing environmental conditions, has significantly increased the burden of heat-related skin diseases,

particularly among vulnerable populations such as children, older adults, and individuals with prolonged outdoor

exposure. Climatic variables including temperature, humidity, ultraviolet radiation, and air pollution, together

with demographic and socioeconomic factors, play a crucial role in influencing disease occurrence and

progression.

The review also highlights the growing adoption of machine learning techniques in healthcare and environmental

health research. Algorithms such as Random Forest, Support Vector Machine, Decision Tree, Gradient Boosting

Decision Tree, Convolutional Neural Networks, and Deep Learning models have demonstrated considerable

potential for disease prediction and risk assessment. Nevertheless, existing studies primarily focus either on skin

disease classification using medical images or on general heat-related health outcomes such as mortality,

Page 1276

www.rsisinternational.org

INTERNATIONAL JOURNAL OF LATEST TECHNOLOGY IN ENGINEERING,

MANAGEMENT & APPLIED SCIENCE (IJLTEMAS)

ISSN 2278-2540 | DOI: 10.51583/IJLTEMAS | Volume XV, Issue VI, June 2026

heatstroke, and hospital admissions. Limited research has addressed the integration of climatic, environmental,

and clinical data for predicting heat-related skin disease risk under future climate change scenarios.

Future research should focus on developing interpretable machine learning frameworks that combine climatic,

environmental, clinical, and socioeconomic data from multiple regions. The incorporation of advanced deep

learning techniques, explainable AI, climate projections, and geospatial analytics can improve prediction

accuracy while enhancing model transparency and generalizability. Such predictive frameworks will assist

healthcare professionals and policymakers in identifying high-risk populations, optimizing healthcare resource

allocation, strengthening heat action plans, and improving climate adaptation strategies. Overall, this survey

establishes a comprehensive knowledge base and identifies future research directions for developing robust

machine learning systems capable of forecasting heat-related skin disease risk and supporting climate-resilient

healthcare systems.

REFERENCES

1. Dirk Roosterman, Tobias Goerge, Stefan W. Schneider, Nigel W. Bunnett, and Martin Steinhoff,

“Neuronal Control of Skin Function: The Skin as a Neuroimmunoendocrine Organ”, Physiological

Reviews 2006 86:4, 1309-1379 10.1152/physrev.00026.2005

2. Oláh, A., Szöllősi, A.G., Bíró, T. (2012). The Channel Physiology of the Skin. In: Nilius, B., et al. Reviews

of Physiology, Biochemistry and Pharmacology, Vol. 163. Reviews of Physiology, Biochemistry and

Pharmacology, vol 163. Springer, Berlin, Heidelberg. https://doi.org/10.1007/112_2012_7

3. Goldust, M. and Grant-Kels, J.M. (2024), Using AI to help address skin health challenges caused by

climate change. Int J Dermatol, 63: e126-e127. https://doi.org/10.1111/ijd.17222

4. Karolina Mieczkowska, Thomas Stringer, John S. Barbieri, Mary Williams, Misha Rosenbach, Surveying

the attitudes of dermatologists regarding climate change, British Journal of Dermatology, Volume 186,

Issue 4, 1 April 2022, Pages 748–750, https://doi.org/10.1111/bjd.20900

5. Shen CZ, Zhao AT, Rotemberg V, Daneshjou R, Parker ER, Rosenbach M. Artificial intelligence in

dermatology: Clinical promise and environmental impact. J Invest Dermatol. 2026 Jun 10:S0022-

202X(26)01043-2. doi: 10.1016/j.jid.2026.03.039. Epub ahead of print. PMID: 42274450.

6. Chaisurin P, Tantranont K. Examining the Interplay Between Occupational Health Hazards and Health

Status Related to Risk Among Home-Based Workers in Thailand. Workplace Health Saf. 2026

Jul;74(7):364-373. doi: 10.1177/21650799261421553. Epub 2026 Mar 16. PMID: 41834727.

7. Maini Chen, Xiangyu Li, Anrong Dang, Yang Weng, Shi Qiu, Adapting to heatwaves: Optimizing urban

green spaces in Beijing to reduce heat health risks, Sustainable Cities and Society, Volume 130, 2025,

106600, ISSN 2210-6707,

https://doi.org/10.1016/j.scs.2025.106600.

8. Oka, K. (2023). Heat-Related Health Impacts of Climate Change and Adaptation Strategies in Japan. In:

Akhtar, R. (eds) Climate Change and Human Health Scenarios. Global Perspectives on Health Geography.

Springer, Cham. https://doi.org/10.1007/978-3-031-38878-1_5

9. Wabnitz, K.J.P., Leppmeier, L., Kuempfel, R. et al. Heat, health and inequalities in the WHO European

region – a scoping review with an intersectional lens. Int J Equity Health 25, 60 (2026).

https://doi.org/10.1186/s12939-026-02787-1

10. Gerardo Sanchez Martinez, Vladimir Kendrovski, Miguel Antonio Salazar, Francesca de’Donato, Melanie

Boeckmann, Heat-health action planning in the WHO European Region: Status and policy implications,

Environmental Research, Volume 214, Part 1, 2022, 113709, ISSN 0013-9351,

https://doi.org/10.1016/j.envres.2022.113709.

11. A. Rahman and M. G. Rabiul Alam, "Explainable AI based Maternal Health Risk Prediction using

Machine Learning and Deep Learning," 2023 IEEE World AI IoT Congress (AIIoT), Seattle, WA, USA,

2023, pp. 0013-0018, doi: 10.1109/AIIoT58121.2023.10174540.

12. Kute, S.S., Shreyas Madhav, A.V., Kumari, S. and Aswathy, S.U. (2022). Machine Learning–Based

Disease Diagnosis and Prediction for E-Healthcare System. In Advanced Analytics and Deep Learning

Models (eds A. Mire, S. Malik and A.K. Tyagi).

https://doi.org/10.1002/9781119792437.ch6.

13. Moulaei, K., Afshari, L., Moulaei, R. et al. Explainable artificial intelligence for stroke prediction through

comparison of deep learning and machine learning models. Sci Rep 14, 31392 (2024).

https://doi.org/10.1038/s41598-024-82931-5

Page 1277

www.rsisinternational.org

INTERNATIONAL JOURNAL OF LATEST TECHNOLOGY IN ENGINEERING,

MANAGEMENT & APPLIED SCIENCE (IJLTEMAS)

ISSN 2278-2540 | DOI: 10.51583/IJLTEMAS | Volume XV, Issue VI, June 2026

14. Elliot Mbunge, John Batani,Application of deep learning and machine learning models to improve

healthcare in sub-Saharan Africa: Emerging opportunities, trends and implications,Telematics and

Informatics Reports,Volume 11,2023,100097,ISSN 2772-

5030,https://doi.org/10.1016/j.teler.2023.100097.

15. Jaiyeoba, O., Ogbuju, E., Ataguba, G. et al. State-of-the-art skin disease classification: a review of deep

learning models. Netw Model Anal Health Inform Bioinforma 14, 9 (2025).

https://doi.org/10.1007/s13721-024-00495-w

16. Sultana, N. (2022), Predicting sun protection measures against skin diseases using machine learning

approaches. J Cosmet Dermatol, 21: 758-769. https://doi.org/10.1111/jocd.14120

17. A. Mohanty, A. Sutherland, M. Bezbradica and H. Javidnia, "Skin Disease Analysis With Limited Data in

Particular Rosacea: A Review and Recommended Framework," in IEEE Access, vol. 10, pp. 39045-39068,

2022, doi: 10.1109/ACCESS.2022.3165574.

18. Gulhan Bizel , Albert Einstein, Amey G Jaunjare, sharath kumar Jagannathan, Machine Learning Study:

Identification of Skin Diseases for Various Skin Types Using Image Classification. Vol. 2 No. 1 (2024):

JBDAI Second Volume. DOI:

https://doi.org/10.54116/jbdai.v2i1.32

19. LEE, J., KWON, K.. Skin health response to climate change weather tailored cosmetics using artificial

intelligence. Journal of Medical Artificial Intelligence, North America, 7, jun. 2024. Available at:

<https://jmai.amegroups.org/article/view/9056>. Date accessed: 28 Jun. 2026.

20. Shaik Abdul Khalandar Basha, P. M. Durai Raj Vincent, K. Srividya, Pusarla Samyuktha, Jessu

Madhumathi, "A Novel Approach to Analysis Consequence of Climate changes on Erythemato-squamous

Diseases using Machine Learning Algorithms," International Journal of Engineering Trends and

Technology (IJETT), vol. 70, no. 11, pp. 10-18, 2022. Crossref,

https://doi.org/10.14445/22315381/IJETT-V70I11P202

21. Jérémie Boudreault, Félix Lamothe, Céline Campagna, Fateh Chebana,Machine learning for modelling

the health impacts of extreme heat: A comprehensive literature review,Environment International,Volume

206,2025,109965,ISSN 0160-4120,https://doi.org/10.1016/j.envint.2025.109965.

22. Ssebyala SN, Kintu TM, Muganzi DJ, Dresser C, Demetres MR, Lai Y, et al. (2024) Use of machine

learning tools to predict health risks from climate-sensitive extreme weather events: A scoping review.

PLOS Clim 3(1): e0000338. https://doi.org/10.1371/journal.pclm.0000338

23. R. G. Tiwari, T. E. Nyamasvisva, N. Ibrahim, A. K. Agarwal, N. Rakesh and M. Gulhane, "Climate-Aware

Healthcare: Predictive Modeling of Disease Outbreaks using Multimodal Data," 2025 4th International

Conference on Innovative Mechanisms for Industry Applications (ICIMIA), Tirupur, India, 2025, pp.

1811-1816, doi: 10.1109/ICIMIA67127.2025.11200760.

24. Connor Forbes, Alberto Coccarelli, Zhiwei Xu, Robert D. Meade, Glen P. Kenny, Sebastian Binnewies,

Aaron J.E. Bach,Biophysical versus machine learning models for predicting rectal and skin temperatures

in older adults,Journal of Thermal Biology,Volume 128,2025,104078,ISSN 0306-

4565,https://doi.org/10.1016/j.jtherbio.2025.104078.

25. Islam, S., Sinha, P., Srivastava, R.K., Khare, M. (2025). Heat Waves and Heat Stress in the Changing

Climate: A Data-Driven Evaluation. In: Srivastava, R.K., Chakraborty, A. (eds) Mitigation and Adaptation

Strategies Against Climate Change in Natural Systems. Environmental Earth Sciences. Springer, Cham.

https://doi.org/10.1007/978-3-031-75968-0_14

26. Javari, P., Javari, M. Heat stress and cardiovascular hospitalizations in a semi-arid megacity: a multi-

method epidemiological and machine-learning analysis in Isfahan, Iran. BMC Public Health 26, 1719

(2026). https://doi.org/10.1186/s12889-026-26909-0

27. Aldosary, A.S., Al-Ramadan, B., Kafy, A.A. et al. Forecasting climate risk and heat stress hazards in arid

ecosystems: Machine learning and ensemble models for specific humidity prediction in Dammam, Saudi

Arabia. Nat Hazards 121, 9281–9309 (2025). https://doi.org/10.1007/s11069-025-07140-3

28. Hirano, Y., Kondo, Y., Hifumi, T. et al. Machine learning-based mortality prediction model for heat-

related illness. Sci Rep 11, 9501 (2021). https://doi.org/10.1038/s41598-021-88581-1

29. Sousan S, Mizelle E, Wu Q, Wu R, Iverson G, Popoviciu C, Hemedinger D, Loyola E, Hood T, Ramirez

M, Balanay JA. Assessing the Feasibility of Wearable Devices for Physiological Monitoring and Heat

Risk Prediction in Outdoor Agricultural Workers. Am J Ind Med. 2026 Jun 9. doi: 10.1002/ajim.70103.

Epub ahead of print. PMID: 42265825.

Page 1278

www.rsisinternational.org

INTERNATIONAL JOURNAL OF LATEST TECHNOLOGY IN ENGINEERING,

MANAGEMENT & APPLIED SCIENCE (IJLTEMAS)

ISSN 2278-2540 | DOI: 10.51583/IJLTEMAS | Volume XV, Issue VI, June 2026

30. Yuemei Wang, Haoyu Chang, Zhiwei Lian,Evaluation of the feasibility of using skin temperature to

predict overall thermal sensation in non-uniform thermal environments,Journal of Thermal

Biology,Volume 106,2022,103254,ISSN 0306-4565,https://doi.org/10.1016/j.jtherbio.2022.103254.

31. K. Tikarya, Y. V. Jain and D. Bhise, "A review: Cattle Breed and Skin Disease Identification Using Deep

Learning," 2023 International Conference on Computing, Communication, and Intelligent Systems

(ICCCIS), Greater Noida, India, 2023, pp. 835-842, doi: 10.1109/ICCCIS60361.2023.10425776.

32. Anderson, A., Bruce, F., Soyer, H.P., Williams, C. and Saunderson, R.B. (2023), The impact of climate

change on skin health. Med J Aust, 218: 388-390. https://doi.org/10.5694/mja2.51931

33. Alzaeemi, S., Tay, K.G., Ali, G.A. et al. A website-based Skin Disease Identification using a Convolutional

Neural Network for Childcare Applications. Iran J Sci Technol Trans Electr Eng (2026).

https://doi.org/10.1007/s40998-026-01018-1

34. Yincai Wu, Xintu Lin, Lily Chen, Diansong Gan, Rujian Li, Yuejun Liu, Lijun Song, Xihai Hao, Tungalag

Dong, Linze Liu, Fenglong Lin, Shenglong Wang,Preparation a skin disease UV protection polylactic acid

film and crystallinity, mechanical properties characterization,Materials Today Communications,Volume

30,2022,103085,ISSN 2352-4928,https://doi.org/10.1016/j.mtcomm.2021.103085.

35. Lee, J.; Kwon, K.H. Sustainable Countermeasures for Skin Health Improvement for Green Consumers:

The Utilization of Hsian-Tsao during Global Warming. Sustainability 2023, 15, 14619.

https://doi.org/10.3390/su151914619

36. A. A. Nafea, S. A. Alameri, R. R. Majeed, M. A. Khalaf, and M. M. AL-Ani , Trans., “A Short Review

on Supervised Machine Learning and Deep Learning Techniques in Computer Vision ”, Babylonian

Journal of Machine Learning, vol. 2024, pp. 48–55, Feb. 2024, doi: 10.58496/BJML/2024/004.

37. M. Bkassiny, Y. Li and S. K. Jayaweera, "A Survey on Machine-Learning Techniques in Cognitive

Radios," in IEEE Communications Surveys & Tutorials, vol. 15, no. 3, pp. 1136-1159, Third Quarter

2013, doi: 10.1109/SURV.2012.100412.00017.

38. Ramu, P., Thananjayan, P., Acar, E. et al. A survey of machine learning techniques in structural and

multidisciplinary optimization. Struct Multidisc Optim 65, 266 (2022). https://doi.org/10.1007/s00158-

022-03369-9

39. Emmanuel G. Pintelas, Theodore Kotsilieris, Ioannis E. Livieris, and Panagiotis Pintelas. 2018. A review

of machine learning prediction methods for anxiety disorders. In Proceedings of the 8th International

Conference on Software Development and Technologies for Enhancing Accessibility and Fighting Info-

exclusion (DSAI '18). Association for Computing Machinery, New York, NY, USA, 8–15.

https://doi.org/10.1145/3218585.3218587

40. Mohanty, A., Gao, G. A survey of machine learning techniques for improving Global Navigation

Satellite Systems. EURASIP J. Adv. Signal Process. 2024, 73 (2024). https://doi.org/10.1186/s13634-

024-01167-7

41. R. Reddy and G. K. Shyam, "Analysis Through Machine Learning Techniques: A Survey," 2018 Second

International Conference on Green Computing and Internet of Things (ICGCIoT), Bangalore, India,

2018, pp. 542-546, doi: 10.1109/ICGCIoT.2018.8753050.