Diabetes Monitoring System in Smart Health Cities Based on Big Data Intelligence

Round 1

Reviewer 1 Report

Below I am passing my comments to the authors.

1/ First, congratulations for the thematic. It is very appropriate nowadays. In this way, in the Abstract I would like to ask you to enhance the problem, where do current initiatives fail?

2/ Also in the Abstract, improve your contribution, addition to the literature.

3/  Is your solution focused only on diabetes. Why? What is the behavior of such problem that we have only in diabetes?

4/  Improve the quality of the paragraphs. Some are tiny, some are large. Some has long sentences, which is bad. See this in the introduction. Rewrite the text.

5/  You motivation in the Introduction is not enough.

AI is cool, ML is cool and I will use them.
This is not right.
You should present briefly the open gap in the literature.

6/  In Section 2, how did you select the related work?

7/  In Figure 3, please, present what is yours, what is legacy?  Also, the things in this figure are flying.

8/ Why using Bluetooth? What is the role of cloud computing? Who inserts the labels?

9/ How is the functioning of the notifications? Are your working with fixed thresholds? Why? In other words, in which circumstances are you calling the ambulance?

10/  Figure 4 is so generic.  Also, perceive that we have a collection of algorithms that are used for CLASSIFCAITION, not for prediction.  Also in Figure 4, why not using ARIMA or linear regression?

11/  It is important to elucidate details regarding implementation.  Give us details about the prototype.  Moreover, how about input application? Are you working with real datasets?

12/  Also in the results, I need to see a statical analysis. How many runs did you do? Why? How about variance, standard deviation, mean, samples, etc...

13/  What are the main limitations of this work?

14/ In the Conclusion section, present the contributions for the society and details regarding technology transfer (how to transform your ideas in products).

14/ At this moment, the work is poor. There are a lot of things to solve.

Author Response

Reviewer 1

Below I am passing my comments to the authors.

1/ First, congratulations for the thematic. It is very appropriate nowadays. In this way, in the Abstract I would like to ask you to enhance the problem, where do current initiatives fail?

2/ Also in the Abstract, improve your contribution, addition to the literature.

The abstract has been modified in the revised version to the following:

Diabetes is a metabolic disorder in which the body is unable to properly regulate blood sugar levels. It can occur when the body doesn't produce enough insulin or when cells become resistant to insulin's effects. There are two main types of diabetes, Type 1 and Type 2, which have different causes and risk factors. Early detection of diabetes allows for early intervention and management of the condition. This can help prevent or delay the development of serious complications associated with diabetes. Early diagnosis also allows for individuals to make lifestyle changes to prevent the progression of the disease. Healthcare systems play a vital role in the management and treatment of diabetes. They provide access to diabetes education, regular check-ups, and necessary medications for individuals with diabetes. They also provide monitoring and management of diabetes-related complications, such as heart disease, kidney failure, and neuropathy. Through early detection, prevention and management programs, healthcare systems can help improve the quality of life and outcomes for people with diabetes. Current initiatives in healthcare systems for diabetes may fail due to lack of access to education and resources for individuals with diabetes. There may also be inadequate follow-up and monitoring for those who have been diagnosed, leading to poor management of the disease and lack of prevention of complications. Additionally, current initiatives may not be tailored to specific cultural or demographic groups, resulting in a lack of effectiveness for certain populations. In this study, we developed a diabetes prediction system using a healthcare framework. The system employs various machine learning methods such as K-Nearest Neighbors, Decision Tree, Deep Learning, SVM, Random Forest, AdaBoost and Logistic Regression. The performance of the system was evaluated using the PIMA Indians Diabetes dataset and achieved a training accuracy of 82\% and validation accuracy of 80\%.

3/  Is your solution focused only on diabetes. Why? What is the behavior of such problem that we have only in diabetes?

4/  Improve the quality of the paragraphs. Some are tiny, some are large. Some has long sentences, which is bad. See this in the introduction. Rewrite the text.

5/  You motivation in the Introduction is not enough.

The following describes the motivation and why to focus on diabetes in healthcare and has been added to the introduction section. And quality of the paragraphs has been recovered

The motivation for automatic prediction of diabetes in healthcare systems is to improve early detection and intervention of the disease. By utilizing machine learning and other predictive methods, healthcare systems can identify individuals at risk for diabetes before symptoms appear, allowing for early intervention and prevention of serious complications. Additionally, automatic prediction can help improve the efficiency and cost-effectiveness of diabetes management, by reducing the need for manual screening and allowing healthcare providers to focus on those individuals most at risk. Furthermore, this approach can also help to reduce health disparities by identifying and targeting high-risk populations that may not have access to traditional screening methods. Overall, the goal is to improve the overall health outcomes for individuals with diabetes and reduce the burden of the disease on the healthcare system.

Healthcare systems for diabetes play a crucial role as a starting point for other health monitoring. Diabetes is a chronic condition that often leads to other serious health complications such as heart disease, kidney failure and blindness. By implementing effective and efficient systems for the management of diabetes, healthcare providers can not only improve the health outcomes for individuals with diabetes but also identify and intervene in the early stages of other chronic conditions. Additionally, by using diabetes as a starting point, healthcare systems can learn from the methods and strategies that have been successful in managing diabetes and apply them to other chronic conditions. This can help improve the overall health of the population and reduce the burden of chronic disease.

Healthcare systems for diabetes can be generalized for other health monitoring by utilizing similar frameworks and methods for early detection and intervention. For example, implementing regular check-ups and screenings for other chronic conditions, such as heart disease or hypertension, can help identify and manage these conditions in their early stages. Additionally, utilizing the same data collection and analysis techniques, such as machine learning and predictive modeling, can aid in identifying individuals at risk for these conditions. Furthermore, providing education and resources for individuals to manage their overall health can also help in preventing and managing other chronic conditions. By adopting a holistic approach to healthcare that focuses on early detection and intervention, healthcare systems can effectively manage and prevent a variety of chronic conditions.

AI is cool, ML is cool and I will use them.

This is not right.

You should present briefly the open gap in the literature.

6/  In Section 2, how did you select the related work?

The literature review section has been modified accordingly to cover these comments:

According the reviewed literature on diabetes prediction, there are several open gaps, including Lack of generalizability: Many studies on diabetes prediction have used small, homogeneous samples, making it difficult to generalize the findings to other populations. Also, limited use of electronic health records (EHRs): Despite the increasing availability of EHRs, many studies on diabetes prediction have not utilized this data source, which could provide a wealth of information for predicting diabetes. Insufficient attention to social determinants of health: Social determinants of health, such as poverty and race, have been shown to play a significant role in the development of diabetes, yet many studies on diabetes prediction have not taken these factors into account.

In previous literature, it can be noticed that limited consideration of the impact of comorbidities: Diabetes is often accompanied by other chronic diseases, yet most studies on diabetes prediction have not considered the impact of comorbidities on diabetes risk. Futhermore, previous studies lack of long-term follow-up, and limited use of multifactorial and advanced machine learning methods which could improve the performance of prediction models. Overall, there is a need for more comprehensive, generalizable, and long-term studies that take into account social determinants of health, comorbidities, and advanced machine learning methods, and use electronic health records as data source.

7/  In Figure 3, please, present what is yours, what is legacy?  Also, the things in this figure are flying.

8/ Why using Bluetooth? What is the role of cloud computing? Who inserts the labels?

The following has been added to the methodology section to answer reviewer comments

The integration of cloud computing and Bluetooth connected devices can enhance healthcare monitoring by providing remote and real-time data collection, storage, and analysis. With cloud computing, data collected from Bluetooth devices such as glucose monitors, blood pressure cuffs, and activity trackers can be transmitted and stored securely on remote servers for easy access by healthcare providers. This allows for more efficient and frequent monitoring of patients, and can assist in early detection and intervention of any health issues. Additionally, cloud computing can enable the use of advanced analytics and machine learning algorithms to identify patterns and make predictions, improving the overall management of chronic conditions such as diabetes.

9/ How is the functioning of the notifications? Are your working with fixed thresholds? Why? In other words, in which circumstances are you calling the ambulance?

Notifications in healthcare monitoring systems are set to trigger when certain thresholds are met. They are typically based on established clinical guidelines and are specific to the condition being monitored. For example, notifications may be sent when blood sugar levels exceed a certain level indicating a need for immediate intervention. These thresholds are fixed as they are based on expert's knowledge and evidence-based research and are intended to provide objective measures for emergency response. The notifications are used to alert healthcare providers, who will then determine if an ambulance should be called.

10/  Figure 4 is so generic.  Also, perceive that we have a collection of algorithms that are used for CLASSIFCAITION, not for prediction.  Also in Figure 4, why not using ARIMA or linear regression?

We are not using ARIMA for prediction or forecasting as many previous researcher in healthcare monitoring systems because Data complexity. These methods are based on simple linear relationships and may not be able to handle more complex data patterns. ARIMA can be difficult to interpret and understand, which can be a disadvantage for researchers who need to understand the underlying mechanisms of the data. ARIMA may not be able to adapt to changing patterns in the data over time. And the implemented techniques including deep learning algorithms looks better for us in such applications.

11/  It is important to elucidate details regarding implementation.  Give us details about the prototype.  Moreover, how about input application? Are you working with real datasets?

This has been answered in section 3.2 (highlighted in red)

12/  Also in the results, I need to see a statical analysis. How many runs did you do? Why? How about variance, standard deviation, mean, samples, etc...

The following has been added to the performance evaluation section, and answer why not to use all metrics:

Performance evaluation is an important step in machine learning applications, as it allows researchers to measure the effectiveness of the model. It can be done using a variety of metrics such as accuracy, precision, recall, F1 score, and ROC AUC. However, not all metrics are suitable for all applications, and researchers may choose to use specific metrics based on the research goals and characteristics of the data. For example, accuracy may be appropriate for balanced datasets, while F1 score may be more suitable for imbalanced datasets. Additionally, it is not practical to use all metrics as it can be time-consuming and may not provide clear results. Researchers must carefully select the appropriate evaluation metrics for their specific application to ensure the effectiveness of the model.

13/  What are the main limitations of this work?

The following has been added to the discussion section:

There are several limitations of using machine learning (ML) in diabetes prediction in health monitoring work:

1. Data bias: ML models are only as good as the data they are trained on, and if the data is biased, the model will also be biased. This can lead to inaccurate predictions and poor performance, particularly for underrepresented groups.
2. Lack of interpretability: Many ML models, particularly deep learning models, are considered "black boxes" and can be difficult to interpret. This can make it challenging for researchers and healthcare providers to understand how the model is making its predictions and identify potential errors.
3. Limited generalizability: ML models are trained on specific datasets, and may not perform well on new or unseen data. This can be a significant limitation in healthcare, where data is often collected from diverse populations with unique characteristics.
4. Lack of domain knowledge: many Machine learning algorithms and models are complex and require a deep understanding of the domain and data to be used effectively.
5. Limited data availability: In some cases, there may not be enough data available to train effective ML models, which can be a significant limitation in healthcare, where data is often collected from diverse populations with unique characteristics.
6. Lack of explainability and transparency: ML models are often considered "black boxes" which can be difficult for healthcare practitioners and patients to understand the decision-making process and the factors that influence the predictions.

Overall, while ML can be a powerful tool for diabetes prediction, it is important to consider these limitations and use appropriate techniques to address them.

14/ In the Conclusion section, present the contributions for the society and details regarding technology transfer (how to transform your ideas in products).

The following has been added to the discussion section:

Using machine learning (ML) in diabetes prediction in health monitoring can make significant contributions to society by improving early detection and intervention of the disease, reducing healthcare costs, and improving the overall health outcomes for individuals with diabetes. ML-based models can assist healthcare providers in identifying individuals at risk for diabetes and in monitoring the progression of the disease, allowing for more efficient and cost-effective management. Additionally, ML can also help to reduce health disparities by identifying high-risk populations that may not have access to traditional screening methods.

For technology transfer, researchers and industry partners need to work together to develop and test the models in real-world settings, identify the challenges and limitations of the models, and adapt the models to meet the specific needs of the target population. Furthermore, regulatory bodies, such as FDA, should be involved to ensure the safety and efficacy of the developed products.

Overall, ML-based systems for diabetes prediction have the potential to improve the lives of millions of people, but technology transfer is an essential step to ensure that these systems are implemented in a way that maximizes their potential benefits.

Reviewer 2 Report

1. State of the art must be substantially modified in order to refer to subject of the paper and avoid the paper that are not related with it, e.g., ref 11.

There are papers that deal with Heath care platforms that deals with big data in cloud and also in diabetes on cloud that clearly must be mentioned, e.g.:

a) Xiangyong Kong, et. al., Disease-specific data processing: An intelligent digital platform for diabetes based on model prediction and data analysis utilizing big data technology, Front. Public Health, 2022

b) Amir Bahman, et. al., A scalable, secure, and interoperable platform for deep data-driven health management, NATURE COMMUNICATIONS, 2021

c) Hugo Peixoto, et. al., Predicting Diabetes Disease for healthy smart cities, EAI Endorsed Transactions on Smart Cities, 2022

d) Anum Naseem, et. al. Novel Internet of Things based approach toward diabetes prediction using deep learning models, 2022

2. The location of dataset (and details) must be known to the reader. 

3. Table 5. must have values.

4. The implementation of KNN, Decision Tree, Random Forest, SVM, MLP, An AdaBoost, Logistic regression in cloud computing must be proved. 

5. The connection of simulation with "Intelligent Health Cities" is not demonstrated. The Figure 3 is very generic, it is at declarative level of concept.

5. Multilayer Perception is a very early neural network, meanwhile Deep Learning is much more than that (reference to KERAS and TensorFlow). 

6. The  novelty in this paper are completely unclear.

Author Response

Reviewer 2

1. State of the art must be substantially modified in order to refer to subject of the paper and avoid the paper that are not related with it, e.g., ref 11.

State of the art references may not be relevant in machine learning (ML) applications for several reasons. One reason is that the field of ML is rapidly evolving, and new techniques and technologies are constantly being developed. This means that the state of the art at the time a study is conducted may have already been surpassed by newer and more advanced methods by the time the study is published. Additionally, the application of ML in healthcare is a relatively new field, and there may not be enough research or studies to provide a comprehensive understanding of the state of the art. Furthermore, ML applications in healthcare require a deep understanding of the domain and the data, and the state of the art in one domain may not be relevant in another. Therefore, researchers may need to use other sources of information, such as expert opinion, to guide their work.

There are papers that deal with Heath care platforms that deals with big data in cloud and also in diabetes on cloud that clearly must be mentioned, e.g.:

1. a) Xiangyong Kong, et. al., Disease-specific data processing: An intelligent digital platform for diabetes based on model prediction and data analysis utilizing big data technology, Front. Public Health, 2022
2. b) Amir Bahman, et. al., A scalable, secure, and interoperable platform for deep data-driven health management, NATURE COMMUNICATIONS, 2021
3. c) Hugo Peixoto, et. al., Predicting Diabetes Disease for healthy smart cities, EAI Endorsed Transactions on Smart Cities, 2022
4. d) Anum Naseem, et. al. Novel Internet of Things based approach toward diabetes prediction using deep learning models, 2022

The requested researches have been cited

Many previous researches have been conducted in the field of Heath care platforms that deals with big data in cloud and also in diabetes on cloud such as [30-33].

2. The location of dataset (and details) must be known to the reader.

This has been answered in section 3.2 (highlighted in red)

3. Table 5. must have values.

All values can be found in the cited reference, and could not be added here for not confusing the readers

4. The implementation of KNN, Decision Tree, Random Forest, SVM, MLP, An AdaBoost, Logistic regression in cloud computing must be proved.
5. The connection of simulation with "Intelligent Health Cities" is not demonstrated. The Figure 3 is very generic, it is at declarative level of concept.

This work has been conducted offline, and the proposed system could be applied in the cloud once every part in the targeted healthcare system is completed, the real implementation over the cloud can be proven in future research. And the connection of simulation with Intelligent Health Cities will be demonstrated.

5. Multilayer Perception is a very early neural network, meanwhile Deep Learning is much more than that (reference to KERAS and TensorFlow).

Pretrained transfer learning could be applied in future work and generalized to the proposed fully connected healthcare system

6. The novelty in this paper are completely unclear.

"I hope the emphasized text in the revised manuscript clarifies the originality of this work."

Reviewer 3 Report

This manuscript is focusing on diabetes prediction and monitoring using machine learning, which is interesting. My comments are as follows:

1) Both motivations and contributions are unclear in Abstract and Introduction, please refine them.

2) The full names of all the abbreviations should be given when they appear for the first time, such as AI in the first paragraph of Introduction.

3) High-quality figures are strongly suggested to better demonstrate the proposed method and experimental results.

4) In related work section, more comments on state-of-the-arts should be considered.

5) More evaluation metrics should be included in experiments, such as G-mean.

6) More state-of-the-art machine learning algorithms should be considered as the baseline methods to make the experiments more sufficient or at least discussed, such as extreme learning. Some related papers are suggested: non-iterative and fast deep learning: multilayer extreme learning machines, JFI, and residual compensation extreme learning machine for regression, neurocomputng.

Author Response

Reviewer 3

This manuscript is focusing on diabetes prediction and monitoring using machine learning, which is interesting. My comments are as follows:

1) Both motivations and contributions are unclear in Abstract and Introduction, please refine them.

The abstract has been modified in the revised version to the following:

Diabetes is a metabolic disorder in which the body is unable to properly regulate blood sugar levels. It can occur when the body doesn't produce enough insulin or when cells become resistant to insulin's effects. There are two main types of diabetes, Type 1 and Type 2, which have different causes and risk factors. Early detection of diabetes allows for early intervention and management of the condition. This can help prevent or delay the development of serious complications associated with diabetes. Early diagnosis also allows for individuals to make lifestyle changes to prevent the progression of the disease. Healthcare systems play a vital role in the management and treatment of diabetes. They provide access to diabetes education, regular check-ups, and necessary medications for individuals with diabetes. They also provide monitoring and management of diabetes-related complications, such as heart disease, kidney failure, and neuropathy. Through early detection, prevention and management programs, healthcare systems can help improve the quality of life and outcomes for people with diabetes. Current initiatives in healthcare systems for diabetes may fail due to lack of access to education and resources for individuals with diabetes. There may also be inadequate follow-up and monitoring for those who have been diagnosed, leading to poor management of the disease and lack of prevention of complications. Additionally, current initiatives may not be tailored to specific cultural or demographic groups, resulting in a lack of effectiveness for certain populations. In this study, we developed a diabetes prediction system using a healthcare framework. The system employs various machine learning methods such as K-Nearest Neighbors, Decision Tree, Deep Learning, SVM, Random Forest, AdaBoost and Logistic Regression. The performance of the system was evaluated using the PIMA Indians Diabetes dataset and achieved a training accuracy of 82\% and validation accuracy of 80\%.

2) The full names of all the abbreviations should be given when they appear for the first time, such as AI in the first paragraph of Introduction.

This has been recovered in the revised version and highlighted in red

3) High-quality figures are strongly suggested to better demonstrate the proposed method and experimental results.

All poor quality figures have been replaced with 300 dpi figures in the revised version

4) In related work section, more comments on state-of-the-arts should be considered.

State of the art references may not be relevant in machine learning (ML) applications for several reasons. One reason is that the field of ML is rapidly evolving, and new techniques and technologies are constantly being developed. This means that the state of the art at the time a study is conducted may have already been surpassed by newer and more advanced methods by the time the study is published. Additionally, the application of ML in healthcare is a relatively new field, and there may not be enough research or studies to provide a comprehensive understanding of the state of the art. Furthermore, ML applications in healthcare require a deep understanding of the domain and the data, and the state of the art in one domain may not be relevant in another. Therefore, researchers may need to use other sources of information, such as expert opinion, to guide their work.

However, recently conducted researches that deal with Heath care platforms that deals with big data in cloud and also in diabetes on cloud have been cited

5) More evaluation metrics should be included in experiments, such as G-mean.

The following has been added to the performance evaluation section, and answer why not to use all metrics:

Performance evaluation is an important step in machine learning applications, as it allows researchers to measure the effectiveness of the model. It can be done using a variety of metrics such as accuracy, precision, recall, F1 score, and ROC AUC. However, not all metrics are suitable for all applications, and researchers may choose to use specific metrics based on the research goals and characteristics of the data. For example, accuracy may be appropriate for balanced datasets, while F1 score may be more suitable for imbalanced datasets. Additionally, it is not practical to use all metrics as it can be time-consuming and may not provide clear results. Researchers must carefully select the appropriate evaluation metrics for their specific application to ensure the effectiveness of the model.

6) More state-of-the-art machine learning algorithms should be considered as the baseline methods to make the experiments more sufficient or at least discussed, such as extreme learning. Some related papers are suggested: non-iterative and fast deep learning: multilayer extreme learning machines, JFI, and residual compensation extreme learning machine for regression, neurocomputng.

This work has been conducted offline, and the proposed system could be applied in the cloud once every part in the targeted healthcare system is completed, the real implementation over the cloud can be proven in future research. And the connection of simulation with Intelligent Health Cities will be demonstrated.

Pretrained transfer learning could be applied in future work and generalized to the proposed fully connected healthcare system

Round 2

Reviewer 1 Report

The article was improved. Now, we have a better version. However, there are aspects that should be improved in the next version of the article.

Below I am presenting my list:

1/  In the Introduction, you work is not clear. Your contribution is not clear. Maybe, put it in an item.

2/  You have a lot of short-paragraphs in Section 2. Also, if possible, provide a comparison table in Section 2, to emphasize the gap in the literature.

3/  Critical: Figure 3 is terrible. I cannot recognize your work. A lot of things flying.

4/ Is your proposal scalable?

5/  In Figure 4, you have a lot of ML methods. Some of them, like KNN and SVM are NOT for prediction, but for CLASSIFICATION. Explain this.

6/ Also in Figure 4, explain the period of data preprocessing. What is done there?

7/ Your title is bad. Choose: monitoring OR prediction. Without slash.

8/  Figure 6 is cool, but how can I read it? Hoiw can I transform it in knowledge?

9/  The same for Table 1. What is the impact of this table?How did you configure the notification engine?

10/ Detail the messages in the system. Are you working with direct messaging or PubSub? Are thay sunc or async?

11/  Again, what are the y-axis in Figures 9 and 10 and 11?

12/ For me, it is hard to understand: is you article a survey or proposal?

13/  Explain more details about technology transfer. How to use your proposal in real cases?

Author Response

The article was improved. Now, we have a better version. However, there are aspects that should be improved in the next version of the article.

Below I am presenting my list:

1/  In the Introduction, you work is not clear. Your contribution is not clear. Maybe, put it in an item.

Aims and contribution to the knowledge have been added to the paper as bullet points

2/  You have a lot of short-paragraphs in Section 2. Also, if possible, provide a comparison table in Section 2, to emphasize the gap in the literature.

Short paragraphs have been merged with others

The comparison table has been removed before according to other reviewer comments

3/  Critical: Figure 3 is terrible. I cannot recognize your work. A lot of things flying.

In the revised version, a clarification of this figure has been added and highlighted in red

4/ Is your proposal scalable?

The scalability is mentioned in the paper and highlighted in red

5/  In Figure 4, you have a lot of ML methods. Some of them, like KNN and SVM are NOT for prediction, but for CLASSIFICATION. Explain this.

It has been shown in the revised version that this research focuses on classifying patterns in the data set for predicting the diabetes

6/ Also in Figure 4, explain the period of data preprocessing. What is done there?

A paragraph explaining the preprocessing step has been added to the revised manuscript and highlighted in red

7/ Your title is bad. Choose: monitoring OR prediction. Without slash.

The title has been modified in the revised manuscript

8/  Figure 6 is cool, but how can I read it? How can I transform it in knowledge?

Actually, human could not transfer this to knowledge based on their optical view, but as you mentioned the achieved results here was cool and we think it will be an added value to our paper in illustrating the strength of the conducted experiments

9/  The same for Table 1. What is the impact of this table? How did you configure the notification engine?

From table 1, future researchers can know what are the exact features that could be considered in such applications

10/ Detail the messages in the system. Are you working with direct messaging or PubSub? Are thay sunc or async?

The detail massages are based on a smart mobile applications, which is attached wirelessly to the sensing devices, all data transferred to a cloud based records and the machine learning conducted on a cloud server (Colab), which in terms extract all data from theses HER.

11/  Again, what are the y-axis in Figures 9 and 10 and 11?

The Y axis in all these figure are the machine learning or pretrained models that experimented in this research, and these figures illustrates the differences between these models on the same data set

12/ For me, it is hard to understand: is you article a survey or proposal?

It is not a survey, but it could be a comparison study based on several pre defined AI models and on a healthcare data set, then it can be considered as a proposal

13/  Explain more details about technology transfer. How to use your proposal in real cases?

A paragraph has been added and highlighted in red that explain the future of this research and how it could be encapsulated in a general healthcare system to be beneficial for human

Reviewer 2 Report

The paper has been improved and it can be published.

Author Response

Thank you for your comments and for accepting this paper

Reviewer 3 Report

The authors did not address the comments, the quality of this paper is still poor.

Author Response

Dear Reviewer,

We appreciate your efforts in reviewing this paper and giving valuable comments to improve its quality.

We returned to the comments one by one and revised the paper again to ensure we improved the mentioned weak points.

We hope this version is good enough for you.

Round 3

Reviewer 1 Report

Thank you for the new version of the article. Beow, I am presenting minor issues that should be addressed in the next version:

1/ In the Introduction, rearrange your contributions. Focus on algorithms, architectures, new ideas. Summarize to 2 or 3 great contributions, additions to the literature.

2/  How did you select the related work in Section 2?

3/ Again, in Figure 4, be more precise. How the methods are used, are they supervisioned or non-supervisioned, how about parameters and training.

4/ For prediction, for how long in the future? How many elements are you analyzing in the past?

5/ What are the main limitations of the work?

6/ What is you contribution for the society?

Author Response

Thank you for the new version of the article. Beow, I am presenting minor issues that should be addressed in the next version:

1/ In the Introduction, rearrange your contributions. Focus on algorithms, architectures, new ideas. Summarize to 2 or 3 great contributions, additions to the literature.

The contributions have been rearranged and reduced as three points , which has been highlighted in red in page number 4 in the revised manuscript

2/  How did you select the related work in Section 2?

The following paragraph specifies the way of reviewing the literature has been added to the revised manuscript:

“Many previous related work have been conducted in the field of automaying healthcare process. In this section, the research topic and the scope of the study has been Clearly defined, and a literature review using scholars databases were conducted to evaluate the relevance of each source. The rest of this section includes most recent and related literature that Grouped the sources based on the themes and concepts they address, and consider the impact of the sources, considering the credibility and reputation of the authors.”

3/ Again, in Figure 4, be more precise. How the methods are used, are they supervisioned or non-supervisioned, how about parameters and training.

Supervisioned or non-supervisioned ML is described in section 3.4 in the revised manuscript and highlighted in red. While more information about employed parameters and training information is provided in Table 2 in section 4.2

4/ For prediction, for how long in the future? How many elements are you analysing in the past?

The following has been added to section 4.3 in the revised manuscript and highlighted in red, which explain the prediction life cycle:

“As Specialists in the field guarantees, the prediction life cycle is based on the amount of data used, and as mentioned earlier, this research could be a part of a huge project that helps in managing healthcare sector based on AI. And could be efficient for a long life time when more data will be collected using the proposed system”

5/ What are the main limitations of the work?

The following paragraph has been added to section 4.3 in the revised manuscript and highlighted in red, which explain the main limitations of the work:

“There are several limitations of using AI in the automation of the healthcare sector, including:

• Data quality and availability: The quality and availability of data is a major challenge for AI in healthcare. Health data is often siloed and not in a format that can be easily analyzed by AI algorithms.
• Privacy and security: The handling of sensitive health data is a concern for privacy and security. There is a risk of data breaches and unauthorized access to patient information.
• Ethical and legal issues: The use of AI in healthcare raises ethical and legal questions, such as issues related to bias, accountability, and informed consent.
• Lack of regulatory framework: There is currently a lack of a clear regulatory framework for AI in healthcare, which makes it difficult to ensure the safety and efficacy of AI-powered medical devices and systems.
• Technical limitations: AI algorithms have limited ability to handle complex medical conditions and perform well when there is limited data available. The development of AI algorithms for healthcare also requires domain-specific expertise.
• Resistance to change: The healthcare sector is often slow to adopt new technologies and there may be resistance to the use of AI from healthcare professionals and patients.

Despite these limitations, AI has the potential to significantly improve the efficiency, accuracy, and cost-effectiveness of healthcare delivery. However, careful consideration of these limitations is necessary to ensure the responsible and ethical use of AI in healthcare.”

6/ What is you contribution for the society?

The following paragraph has been added to section 4.3 in the revised manuscript and highlighted in red, which explain the main contribution for the society:

“automatic prediction of diabetes in healthcare systems using machine learning and predictive methods can improve early detection and intervention of the disease, leading to better management and cost-effectiveness. By identifying individuals at risk before symptoms appear, healthcare providers can focus their efforts on high-risk patients, reducing health disparities. Implementing an efficient and effective system for diabetes management can improve overall population health and reduce the burden of chronic disease.”