A Survey on Recent Advances in Medical Diagnosis and Telemedicine Using Machine Learning Techniques
Introduction
Accurate medical diagnosis plays a
crucial role in guiding treatment decisions and improving patient outcomes.
With the rapid advancements in technology, machine learning has emerged as a
powerful tool in the field of medical diagnosis. Machine learning algorithms
can analyze vast amounts of patient data, detect patterns, and provide valuable
insights to healthcare professionals. These advances have the potential to
revolutionize the way diseases are diagnosed and managed.
Machine learning algorithms have demonstrated remarkable success
in various aspects of medical diagnosis. For instance, in the field of image
recognition and analysis, deep learning models have shown promising results in
interpreting medical images such as X-rays, CT scans, and pathology slides
(Varoquaux and Cheplygina, 2022). These algorithms can accurately detect
abnormalities and assist radiologists and pathologists in making more precise
diagnoses.
Early disease detection is another
area where machine learning has made significant strides. By analyzing
extensive patient data, including electronic health records, machine learning
models can identify patterns that may indicate the early signs of diseases such
as diabetes, cardiovascular diseases, and sepsis (Bamanga et al., 2021). This
early detection enables timely interventions, leading to improved treatment
outcomes and reduced healthcare costs.
Personalized medicine, tailored to an
individual’s unique characteristics, has become a reality with the help of
machine learning. By analyzing genetic and molecular data, machine learning
algorithms can provide personalized treatment recommendations, helping
healthcare providers determine the most effective medications, dosages, and
treatment plans for specific patients (Fröhlich, Balling and Beerenwinkel,
2018). This approach maximizes treatment efficacy while minimizing adverse
reactions. Ibrahim Goni (2020) applied Machine Learning Algorithm in Predicting
the Presence of Mycobacterium Tuberculosis.
Machine learning algorithms are
employed in disease risk assessment, where they analyze a combination of
patient data, including demographics, medical history, and lifestyle factors.
These models can identify individuals at higher risk of developing conditions
such as heart disease, cancer, or Alzheimer’s disease, enabling preventive
measures and early interventions (Kumar et al., 2023). Neuro-fuzzy approach was also applied in
diagnosis and control of TB in Jerome et al., (2018).
Natural Language Processing (NLP) techniques combined with machine
learning have transformed the analysis of clinical notes and medical
literature. NLP algorithms can extract crucial information from clinical notes
and physician reports, automating coding, risk assessment, and data extraction
processes (Chen, 2019). This integration improves the accuracy and efficiency
of medical diagnosis and streamlines healthcare workflows.
In the realm of drug discovery and development, machine learning
has expedited the process by analyzing large datasets and predicting the
efficacy of potential drug candidates (Dara et al., 2022). These algorithms
enable researchers to identify promising drug candidates more efficiently,
reducing costs and accelerating the development of new treatments.
Moreover, machine learning has played
a significant role in telemedicine and remote monitoring. By analyzing patient
data collected from wearable devices and remote monitoring tools, machine
learning algorithms can detect anomalies, predict worsening conditions, and
provide real-time feedback to healthcare professionals (Paganelli et al.,
2022). This enables remote diagnosis and management of patients, enhancing
access to healthcare and improving patient outcomes.
One area where machine learning has
shown remarkable progress is in image recognition and analysis. Medical imaging
modalities such as X-rays, CT scans, MRIs, and pathology slides generate vast
amounts of visual data that can be challenging for human interpretation alone.
Machine learning algorithms, particularly deep learning models, have
demonstrated impressive capabilities in accurately interpreting and analyzing
medical images (Varoquaux and Cheplygina, 2022). These algorithms can assist
radiologists and pathologists in detecting abnormalities, making diagnoses, and
guiding treatment decisions.
Another critical aspect of medical diagnosis is early disease
detection. Timely identification of diseases can significantly impact patient
outcomes by enabling early interventions and preventive measures. Machine
learning algorithms can analyze diverse patient data, including electronic
health records, laboratory results, and genetic information, to identify
patterns and indicators of diseases at an early stage (Bamanga et al., 2021).
These algorithms can help healthcare providers predict the likelihood of
disease development and guide appropriate screening and intervention
strategies.
Furthermore, personalized medicine,
tailoring treatments to individual patients’ unique characteristics, has become
a promising avenue in medical diagnosis. Machine learning algorithms can
leverage genetic and molecular data to provide personalized treatment
recommendations, considering factors such as genetic variations, biomarker
profiles, and treatment response data (Fröhlich, Balling and Beerenwinkel,
2018). This approach holds the potential to optimize treatment efficacy,
minimize adverse reactions, and improve patient outcomes.
Additionally, machine learning has been
applied to disease risk assessment. By analyzing various patient factors,
including demographics, medical history, lifestyle data, and biomarkers,
machine learning models can estimate an individual’s risk of developing certain
diseases (Kumar et al., 2023). These risk assessment models can identify
high-risk individuals, enabling targeted interventions, and preventive
strategies.
Moreover, the field of natural language processing (NLP) has seen
significant advancements in the context of medical diagnosis. NLP techniques
combined with machine learning algorithms can extract valuable information from
clinical notes, physician reports, and medical literature (Chen, 2019). This
enables automated coding, risk assessment, and data extraction, streamlining the
diagnostic process and improving efficiency.
This paper will provide a
comprehensive survey of the current state of the field. Also the researchers
seek to contribute to the existing knowledge base and facilitate the continued
progress of medical diagnosis and telemedicine through the utilization of
machine learning techniques.
Literature
Review
Machine learning has emerged as a
promising approach to address the challenges associated with medical diagnosis.
By leveraging algorithms that can learn from data and identify complex
patterns, machine learning techniques have the potential to enhance the
accuracy, efficiency, and objectivity of medical diagnoses. Accurate medical
diagnosis holds several crucial benefits. Firstly, it enables timely initiation
of appropriate treatments, which can significantly impact patient outcomes. For
conditions such as cancer, early detection and accurate diagnosis can lead to
more effective treatment interventions and improved survival rates (Varoquaux
and Cheplygina, 2022).
Moreover, accurate diagnosis
contributes to more efficient healthcare utilization. It reduces the need for
unnecessary tests, procedures, and consultations, minimizing healthcare costs
and resource allocation. Machine learning algorithms can analyze large volumes
of patient data, including electronic health records, imaging data, and genomic
information, to provide precise and targeted diagnostic insights, leading to
streamlined healthcare delivery (Bamanga et al., 2021). A systematic review on
the application of machine leaning algorithms and wireless sensor network in
medical diagnosis was also presented in Ibrahim Goni (2019).
Accurate medical diagnosis is also
critical in reducing diagnostic errors and improving patient safety. Diagnostic
errors, such as misdiagnosis or delayed diagnosis, can have severe consequences
for patients, including potential harm, prolonged suffering, and increased
morbidity and mortality rates. Machine learning algorithms can help identify
subtle patterns and indicators of diseases that may be challenging for human
clinicians to detect, thereby reducing the risk of diagnostic errors (Fröhlich,
Balling and Beerenwinkel, 2018). Adaptive neuro-fuzzy technique was used to
determine the blood glucose level in Auwal et al., (2019).
Furthermore, accurate diagnosis plays a crucial role in
personalized medicine. Each patient is unique, and factors such as genetic
variations, biomarker profiles, and comorbidities can influence treatment
efficacy and safety. Machine learning algorithms can integrate and analyze vast
amounts of patient-specific data, enabling the development of personalized
treatment plans that maximize therapeutic benefits while minimizing adverse
reactions (Kumar et al., 2023).
Accurate medical diagnosis is
essential for effective healthcare delivery and improved patient outcomes.
Machine learning techniques offer promising opportunities to enhance the
accuracy, efficiency, and objectivity of medical diagnoses. By leveraging
algorithms that can analyze complex patterns and vast amounts of patient data,
machine learning has the potential to transform the diagnostic process,
enabling timely interventions, personalized treatments, and improved patient
safety.
Machine Learning Techniques applied in
Advancing Medical Diagnosis
Machine learning has emerged as a powerful tool in advancing
medical diagnosis. By leveraging algorithms that can learn from data and
identify patterns, machine learning techniques have the potential to enhance
the accuracy, efficiency, and objectivity of medical diagnoses. Several key
areas highlight the role of machine learning in advancing medical diagnosis:
Image Recognition and Analysis:
Machine learning algorithms, particularly deep learning models, have shown
remarkable success in interpreting and analyzing medical images. For example,
Rana and Bhushan (2023) demonstrated dermatologist-level classification of skin
cancer using deep neural networks. These algorithms can assist radiologists and
pathologists in detecting abnormalities and making accurate diagnoses. Early
Disease Detection: Machine learning algorithms can analyze vast amounts of
patient data, such as electronic health records and biomarker profiles, to
identify early signs of diseases. Kavakiotis et al., (2017) showed the
potential of machine learning models in predicting diseases like diabetes and
cardiovascular diseases. Early detection enables timely interventions and
improved treatment outcomes.
Personalized Medicine: Machine
learning algorithms can integrate genetic and molecular data with clinical
information to provide personalized treatment recommendations. Quazi (2022)
demonstrated the use of machine learning to improve personalized diagnostic
accuracy for community-acquired pneumonia in children. This approach maximizes
treatment efficacy and minimizes adverse reactions. Disease Risk Assessment:
Machine learning models can analyze patient data, including demographics,
medical history, and lifestyle factors, to assess the risk of developing
certain diseases. Javaid et al., (2022) highlighted the application of machine
learning in risk assessment for conditions such as heart disease. This enables
targeted interventions and preventive measures. Natural Language Processing
(NLP) for Clinical Notes:
NLP techniques combined with machine
learning algorithms can extract valuable information from clinical notes and
physician reports. Singh et al., (2023) showcased the use of NLP and machine
learning for automating coding and risk assessment. This improves the accuracy
and efficiency of medical diagnosis.
Drug Discovery and Development; machine
learning algorithms have accelerated the drug discovery process by analyzing
large datasets and predicting drug efficacy. Javaid et al., (2022) demonstrated
the application of machine learning in drug discovery and side effect analysis.
This leads to faster and more cost-effective drug development.
Telemedicine and Remote Monitoring; machine
learning algorithms can analyze patient data collected from wearable devices
and remote monitoring tools. Kavakiotis et al., (2017) highlighted the role of
machine learning in remote diagnosis and management. Real-time analysis and
feedback enable improved access to healthcare and patient care.
Accurate medical diagnosis is
essential for effective treatment and improved patient outcomes. It forms the
foundation of healthcare decision-making, guiding appropriate interventions and
therapeutic strategies. However, the complexity of medical data and the
limitations of human expertise have prompted the exploration of machine learning
techniques to enhance diagnostic capabilities.
Accurate medical diagnosis holds
several critical implications for patient care and healthcare systems. It
enables:
Timely Treatment
Prompt and accurate diagnosis allows for timely initiation of appropriate treatments, which can significantly impact patient outcomes, particularly in conditions where early intervention is crucial (Varoquaux and Cheplygina, 2022).
Efficient Resource Allocation: Accurate diagnosis helps optimize
healthcare resource utilization by reducing unnecessary tests, procedures, and
consultations. This improves efficiency and reduces healthcare costs (Bamanga
et al., 2021).
Patient Safety
Diagnostic errors can have serious consequences for patients, leading to prolonged suffering, potential harm, and increased morbidity and mortality rates. Accurate diagnosis reduces the risk of misdiagnosis or delayed diagnosis, enhancing patient safety (Fröhlich, Balling and Beerenwinkel, 2018).
Machine Learning in Enhancing Medical
Diagnosis
Machine learning techniques have demonstrated significant
potential to enhance medical diagnosis in various ways:
Image Recognition and Analysis
Machine learning algorithms, particularly deep learning models, have shown remarkable success in interpreting and analyzing medical images. They can assist healthcare professionals in accurately identifying abnormalities and making diagnoses (Varoquaux and Cheplygina, 2022).
Early Disease Detection
Machine learning algorithms can analyze diverse patient data, including electronic health records and biomarker profiles, to identify early signs of diseases. This enables timely interventions and improved treatment outcomes (Bamanga et al., 2021).
Personalized Medicine
By integrating genetic and molecular data with clinical information, machine learning algorithms can provide personalized treatment recommendations. This tailors treatments to individual patients, maximizing therapeutic benefits while minimizing adverse reactions (Fröhlich, Balling and Beerenwinkel, 2018).
Disease Risk Assessment
Machine learning models can analyze patient data, including demographics, medical history, and lifestyle factors, to assess the risk of developing certain diseases. This enables targeted interventions and preventive measures (Kumar et al., 2023).
Natural Language Processing (NLP) for Clinical Notes: NLP
techniques combined with machine learning algorithms can extract valuable
information from clinical notes and physician reports. This facilitates
automated coding, risk assessment, and data extraction, improving the
efficiency and accuracy of medical diagnosis (Chen, 2019).
Machine Learning in Medical Imaging
Image recognition and analysis is a
key area where machine learning techniques have shown significant advancements
in medical diagnosis. Machine learning algorithms, particularly deep learning
models, have demonstrated remarkable capabilities in interpreting and analyzing
medical images, aiding healthcare professionals in accurate diagnosis. The
application of machine learning in interpreting medical images can be seen in
the following aspects:
Machine learning algorithms have been
successfully applied in radiology to assist in the interpretation of various
imaging modalities, such as X-rays, computed tomography (CT), magnetic resonance
imaging (MRI), and mammography. These algorithms can identify and localize
abnormalities, aid in differential diagnosis, and provide quantitative
assessments (Varoquaux and Cheplygina, 2022). Machine learning techniques have
been employed to analyze histopathological images, helping pathologists in
detecting and classifying various diseases, including cancer. These algorithms
can assist in identifying cellular features, tumor boundaries, and predicting
disease prognosis (Komura and Ishikawa, 2018).
Machine learning algorithms have been
utilized to analyze dermatological images, supporting the diagnosis of skin
conditions and the detection of malignant lesions. These algorithms can
classify skin lesions, differentiate between benign and malignant tumors, and
provide decision support to dermatologists (Varoquaux and Cheplygina, 2022). Machine
learning techniques have been applied to analyze retinal images, aiding in the
diagnosis and monitoring of various eye diseases, such as diabetic retinopathy
and age-related macular degeneration. These algorithms can detect abnormalities
in retinal structures, identify disease progression, and provide risk
stratification (Tsiknakis et al., 2021). Machine learning algorithms have been
used to analyze brain imaging data, including MRI and functional MRI (fMRI).
These algorithms can assist in the identification of brain tumors, localization
of epileptic foci, and prediction of disease progression in neurodegenerative
disorders (Komura and Ishikawa, 2018).
Deep Learning in Medical Imaging
Machine learning algorithms have shown
success in analyzing computed tomography (CT) scans for various applications,
including lung nodule detection and classification. For example, Ardila et al.
(2019) developed a deep learning model that outperformed radiologists in
detecting malignant lung nodules on CT scans. Machine learning techniques have
been applied to magnetic resonance imaging (MRI) for tasks such as tumor
segmentation and classification. Liu et al. (2019) used a deep learning model
to segment brain tumors from MRI scans, achieving high accuracy compared to
manual segmentation.
Machine learning algorithms have been successful in analyzing
histopathological images to aid pathologists in diagnosing cancer. For
instance, Zhao et al., (2022) developed a deep learning model that achieved
comparable performance to human pathologists in breast cancer metastasis
detection from lymph node images. Machine learning has been applied to dermatological
images for the classification and diagnosis of skin conditions. Ahammed, Mamun
and Uddin (2022) trained a deep neural network that achieved
dermatologist-level classification of skin cancer using dermoscopic images.
Ophthalmology: Machine learning techniques
have been used to analyze retinal images for the detection and diagnosis of
various eye diseases. Tsiknakis et al., (2021) developed a deep learning
algorithm that demonstrated high sensitivity and specificity in detecting
diabetic retinopathy from retinal fundus photographs. Machine learning has been
employed to analyze functional MRI (fMRI) data for tasks such as brain activity
classification and disease prediction. Heinsfeld et al. (2018) utilized machine
learning methods to predict cognitive performance from fMRI data, showing
promise for understanding brain-behavior relationships.
Evaluation Performances in Machine
Learning Techniques
Tsiknakis et al., (2021) demonstrated
that a deep learning algorithm achieved high accuracy in detecting diabetic
retinopathy from retinal fundus photographs, outperforming human experts.
Ahammed, Mamun and Uddin (2022)
developed a deep neural network that achieved dermatologist-level
classification of skin cancer, showcasing improved accuracy in diagnosis.
Reduced Diagnostic Errors Kavakiotis
et al., (2017) showed that machine learning algorithms can predict diseases
such as diabetes and cardiovascular diseases with high accuracy, reducing the
occurrence of diagnostic errors. Zhao et al., (2022) demonstrated that a deep
learning model achieved comparable performance to human pathologists in
detecting breast cancer metastasis from lymph node images, potentially reducing
diagnostic errors in pathology.
Ardila et al. (2019) demonstrated that
a deep learning model for lung nodule detection on CT scans reduced false
positives by half, potentially improving efficiency by reducing unnecessary
follow-up tests and interventions. Liu et al. (2019) used a deep learning model
to segment brain tumors from MRI scans, improving efficiency by automating the
time-consuming task of manual segmentation. Zhao et al., (2022) showed that the
use of machine learning algorithms in breast cancer metastasis detection
reduced inter-observer variability among pathologists, improving consistency in
diagnosis.
Kavakiotis et al., (2017) demonstrated
that machine learning algorithms applied in telemedicine reduced the time
required for diagnosis and treatment decision-making, enabling timely care
delivery. These studies demonstrate the positive impact of machine learning on
the accuracy and efficiency of medical diagnosis. By leveraging advanced
algorithms and analyzing large amounts of data, machine learning has the
potential to improve diagnostic accuracy, reduce errors, enhance efficiency,
and save valuable time in the diagnostic process.
Machine Learning Techniques in
Telemedicine and E-health
Mathew, Fitts, Liddle, et al., (2023)
emphasized the potential of telemedicine to improve access to care and enable
remote consultations, reducing the need for in-person visits.
Bokolo, (2021) discussed the
successful implementation of telemedicine technologies, including video
consultations and remote monitoring, in improving patient outcomes and reducing
healthcare costs. Kumar et al., (2020) demonstrated the use of machine learning
algorithms in remote monitoring of patients with chronic diseases, such as
heart failure and diabetes. They highlighted the potential of these algorithms
to analyze remote sensor data and detect anomalies or changes in patient health
status. Nikolaou et al., (2020) developed a machine learning-based system for
remote monitoring of patients with chronic obstructive pulmonary disease
(COPD). The system analyzed physiological data and provided personalized
feedback and recommendations for disease management. Kavakiotis et al., (2017)
discussed the use of machine learning algorithms in predictive analytics for
remote monitoring. By analyzing patient data, including vital signs, symptoms,
and historical information, these algorithms can identify patterns and predict
adverse events, enabling early intervention and improved patient outcomes. Lee
et al. (2023) highlighted the use of wearable devices, such as smartwatches and
fitness trackers, in remote monitoring. Machine learning algorithms can analyze
data collected from these devices, including heart rate, activity levels, and
sleep patterns, to provide insights into patient health and detect
abnormalities.
Future Research Directions
As machine learning continues to
advance in medical diagnosis, several potential future developments and
challenges should be considered.
Future developments may involve
integrating data from various sources, including medical images, electronic
health records, genomics, wearable devices, and lifestyle data.
As medical data becomes more accessible and shared across
different platforms, ensuring patient privacy and data security becomes
critical. Future developments should address these concerns by implementing
robust privacy measures, secure data sharing protocols, and compliance with
data protection regulations.
With the increasing integration of
machine learning in medical diagnosis, ethical considerations such as
algorithmic bias, fairness, and accountability become crucial. Future
developments should address these ethical challenges to ensure equitable and
responsible deployment of machine learning algorithms in healthcare.
As machine learning algorithms become
an integral part of medical diagnosis, appropriate regulatory and legal
frameworks need to be established. These frameworks should ensure the safety,
effectiveness, and ethical use of machine learning in healthcare while
promoting innovation and patient-centered care.
Conclusion
In conclusion, the application of
machine learning in medical diagnosis has shown significant advancements and
holds great potential for transforming healthcare. By leveraging advanced
algorithms and analyzing large volumes of data, machine learning has demonstrated
improved accuracy, efficiency, and patient outcomes in various areas of medical
diagnosis.
Machine learning has proven successful
in interpreting medical images, including radiology, pathology, dermatology,
ophthalmology, and neuroimaging. It has surpassed human experts in certain
tasks, enabling earlier detection, segmentation, and classification of
diseases.
Furthermore, the integration of
machine learning in telemedicine and remote monitoring has expanded access to
healthcare services and enabled continuous monitoring of patients. This
technology has the potential to detect anomalies, predict adverse events, and
provide personalized feedback, leading to improved patient management and
reduced healthcare costs.
However, several challenges need to be addressed for the widespread adoption and ethical use of machine learning in medical diagnosis. These challenges include ensuring interpretability, privacy, and security of patient data, addressing algorithmic bias and fairness, and establishing regulatory frameworks that promote responsible and equitable deployment of machine learning algorithms.
References
- Ahammed, M., Mamun, M. A., and Uddin, M. S. (2022). A machine learning approach for skin disease detection and classification using image segmentation. Healthcare Analytics, 2, 100122. https://doi.org/10.1016/j.health.2022.100122
CrossRef - Auwal Nata’ala, Hamman Dikko Muazu, Ibrahim Goni, Abdullahi Mohammed Jingi. (2019) Adaptive Neuro-Fuzzy System to Determine the Blood Glucose Level of Diabetic. Mathematics and Computer Science. Vol. 4, No. 3, 2019, pp. 63-67. doi: 10.11648/j.mcs.20190403.11
CrossRef - Bamanga, M.A., Ahmadu, A.S., Musa, Y.M. and Babando, K.A. (2021). Predictive Analysis of Heart Disease Using Selected Machine Learning Meta-Algorithms. Journal of Tianjin University Science and Technology. 54(7), 29-48. ISSN: 0493-2137
- Bokolo, A.J. (2021). Application of telemedicine and eHealth technology for clinical services in response to COVID‑19 pandemic. Health Technol. 11, 359–366 (2021). https://doi.org/10.1007/s12553-020-00516-4
CrossRef - Chen, L., Song, L., Shao, Y., Li, D., and Ding, K. (2019). Using natural language processing to extract clinically useful information from Chinese electronic medical records. International Journal of Medical Informatics, 124, 6-12. https://doi.org/10.1016/j.ijmedinf.2019.01.004
CrossRef - Dara, S., Dhamercherla, S., Jadav, S. S., Babu, C. M., & Ahsan, M. J. (2022). Machine Learning in Drug Discovery: A Review. Artificial Intelligence Review, 55(3), 1947-1999. https://doi.org/10.1007/s10462-021-10058-4
CrossRef - Fröhlich, H., Balling, R., Beerenwinkel, N. (2018). From hype to reality: data science enabling personalized medicine. BMC Med 16, 150 (2018). https://doi.org/10.1186/s12916-018-1122-7
CrossRef - Harrison, C.J. and Sidey-Gibbons, C.J. (2021). Machine learning in medicine: a practical introduction to natural language processing. BMC Med Res Methodol 21, 158 (2021). https://doi.org/10.1186/s12874-021-01347-1
CrossRef - Ibrahim Goni. (2020) Machine Learning Algorithm Applied for Predicting the Presence of Mycobacterium Tuberculosis. International Journal of Clinical Dermatology. Vol. 3, No. 1, 2020, pp. 4-7. doi: 10.11648/j.ijcd.20200301.12
- Ibrahim Goni (2019) Machine Learning algorithms and Wireless Sensor network applied to Medical diagnosis: A systematic review American Journal of Electromagnetics and application Vol. 7(2) 2019, pp. 2533.
CrossRef - Javaid, M., Haleem, A., Pratap Singh, R., Suman, R., & Rab, S. (2022). Significance of machine learning in healthcare: Features, pillars and applications. International Journal of Intelligent Networks, 3, 58-73. https://doi.org/10.1016/j.ijin.2022.05.002
CrossRef - Johnson, K. B., Wei, Q., Weeraratne, D., Frisse, M. E., Misulis, K., Rhee, K., Zhao, J., and Snowdon, J. L. (2021). Precision Medicine, AI, and the Future of Personalized Health Care. Clinical and Translational Science, 14(1), 86-93. https://doi.org/10.1111/cts.12884
CrossRef - Jerome M. G., Ibrahim Goni & Mohammed Isa (2018) Neuro-Fuzzy Approach for Diagnosing and Control of Tuberculosis the International Journal of Computational Science, Information Technology and Control Engineering (IJCSITCE) Vol.5(1) available online at http://airccse.com/ijcsitce/current2018.html
CrossRef - Kavakiotis, I., Tsave, O., Salifoglou, A., Maglaveras, N., Vlahavas, I., & Chouvarda, I. (2017). Machine Learning and Data Mining Methods in Diabetes Research. Computational and Structural Biotechnology Journal, 15, 104-116. https://doi.org/10.1016/j.csbj.2016.12.005
CrossRef - Komura, D., & Ishikawa, S. (2018). Machine Learning Methods for Histopathological Image Analysis. Computational and Structural Biotechnology Journal, 16, 34-42. https://doi.org/10.1016/j.csbj.2018.01.001
CrossRef - Kumar, Y., Koul, A., Singla, R., & Ijaz, M. F. (2023). Artificial intelligence in disease diagnosis: A systematic literature review, synthesizing framework and future research agenda. Journal of Ambient Intelligence and Humanized Computing, 14(7), 8459-8486. https://doi.org/10.1007/s12652-021-03612-z
CrossRef - Lee, W., Schwartz, N., Bansal, A., Khor, S., Hammarlund, N., Basu, A., & Devine, B. (2023). A Scoping Review of the Use of Machine Learning in Health Economics and Outcomes Research: Part 1—Data From Wearable Devices. Value in Health, 26(2), 292-299. https://doi.org/10.1016/j.jval.2022.08.005
CrossRef - Mathew, S., Fitts, M.S., Liddle, Z. (2023). Telehealth in remote Australia: a supplementary tool or an alternative model of care replacing face-to-face consultations?. BMC Health Serv Res 23, 341 (2023). https://doi.org/10.1186/s12913-023-09265-2
CrossRef - Nikolaou, V., Massaro, S., Fakhimi, M., Stergioulas, L., & Price, D. (2020). COPD phenotypes and machine learning cluster analysis: A systematic review and future research agenda. Respiratory Medicine, 171, 106093. https://doi.org/10.1016/j.rmed.2020.106093
CrossRef - Paganelli, A. I., Mondéjar, A. G., da Silva, A. C., Silva-Calpa, G., Teixeira, M. F., Carvalho, F., Raposo, A., & Endler, M. (2022). Real-time data analysis in health monitoring systems: A comprehensive systematic literature review. Journal of Biomedical Informatics, 127, 104009. https://doi.org/10.1016/j.jbi.2022.104009
CrossRef - Quazi, S. Artificial intelligence and machine learning in precision and genomic medicine. Med Oncol 39, 120 (2022). https://doi.org/10.1007/s12032-022-01711-1
CrossRef - Rana, M., Bhushan, M. (2023). Machine learning and deep learning approach for medical image analysis: diagnosis to detection. Multimed Tools Appl 82, 26731–26769 (2023). https://doi.org/10.1007/s11042-022-14305-w
CrossRef - Singh, A. V., Chandrasekar, V., Paudel, N., Laux, P., Luch, A., Gemmati, D., Tisato, V., Prabhu, K. S., Uddin, S., and Dakua, S. P. (2023). Integrative toxicogenomics: Advancing precision medicine and toxicology through artificial intelligence and OMICs technology. Biomedicine & Pharmacotherapy, 163, 114784. https://doi.org/10.1016/j.biopha.2023.114784
CrossRef - Tsiknakis, N., Theodoropoulos, D., Manikis, G., Ktistakis, E., Boutsora, O., Berto, A., Scarpa, F., Scarpa, A., Fotiadis, D. I., and Marias, K. (2021). Deep learning for diabetic retinopathy detection and classification based on fundus images: A review. Computers in Biology and Medicine, 135, 104599. https://doi.org/10.1016/j.compbiomed.2021.104599
CrossRef - Varoquaux, G. and Cheplygina, V. (2022). Machine learning for medical imaging: methodological failures and recommendations for the future. npj Digit. Med. 5, 48 (2022). https://doi.org/10.1038/s41746-022-00592-y
CrossRef - Zhao, Y., Zhang, J., Hu, D., Qu, H., Tian, Y., & Cui, X. (2022). Application of Deep Learning in Histopathology Images of Breast Cancer: A Review. Micromachines, 13(12), 2197. https://doi.org/10.3390/mi13122197
CrossRef
This work is licensed under a Creative Commons Attribution 4.0 International License.
Open
Access - 