Pneumonia Classification

AI COMMONS HEALTH & WELLBEING HACKATHON SOLUTIONS

OVERVIEW

The AI Commons Project is a proof of concept of a new methodology of developing Artificial Intelligence solutions that allows anyone, anywhere to benefit from the possibilities that AI can provide. The project aims to increase/improve the accessibility, reproducibility, contextualization and enhancement of Artificial Intelligence solutions globally and especially in emerging markets.

The project aims to demonstrate how a global community of AI experts can learn and co-create mutually beneficial solutions with the opportunity for cross-county incremental enhancement.

STATEMENT OF PURPOSE

INTRODUCTION

Introduce yourself (Documentation team)
Name(s) and institution/organization affiliated with

Data Science Nigeria

Introduce yourself (Solution owners)
Name(s) and institution/organization affiliated with

Rising Odegua (Data Science Nigeria)

Other contributors to this work

Nelson Ogbeide; Ojeabulu O. Gift; Comfort Igboko; Caleb Emelike; Precious Cadeton

PROBLEM DEFINITION

Define the problem
What problem does the solution seek to solve? For how long has the problem existed? How prevalent is problem? Provide any background information relevant to the problem.

Pneumonia is an infection that affects one or both lungs and it is known to cause premature death around the world. World Health Organization(WHO) estimated that about 4 million death occur annually from air pollution diseases including pneumonia

Who are those affected by the problem (Problem owners)
Class of people. Country/region where they live. Impact of problem on their lifestyle

Research has shown that children and people older than 65 are the most vulnerable to the disease and continents with a high number of adult and children ratio like Africa and Asia are mostly affected.

How is the problem currently solved?
Describe the current/existing workaround for the problem

A doctor examines the chest x ray of a paitent to determine if the patient has pneumonia

Yes
Malaria detection using machine learning
Cancer detection using machine learning

SOLUTION

What is this solution about?
Describe the solution. Describe the solution space and opportunity. When was the solution first released? When was the last release? Link to the solution Deck/publications

The solution is a pneumonia detection model. It helps health practitioners in hospitals, clinics and laboratories to quickly detect whether a patient has pneumonia, given the patient’s chest X-ray. The first and only release ofthe solution was in 2019.
See paper Here

Describe the outputs of the solution
Please ensure that your solution output sufficiently address the problem defined in the section above

The outcome of the solution is a prediction of whether the patient has pneumonia or not if a chest X-ray is provided as input

Who are the key stakeholders?

Health practitioners
Patients

What is the expertise types required to develop this solution?
Please provide all technical expertise required to build solution and their roles in the solution development

A data scientist/ machine learning engineer is needed to build the prediction model and a domain expert (such as a thoracic surgeon) is needed to provide technical details on how the diseases work and are being identified

What are the challenges faced while developing the solution
Decribe the challenges/obstacles faced

Small amount of training data

What are your recommendations to improve the solution?
Provide a list of recommendations, if any, to improve the solution

More data should be used for training and evaluation

Have you updated this solution documentation before?
When and how often? What sections have changed? Is the documentation updated every time the solution is retrained or updated?

No. We hope to keep it updated whenever the solution is retrained.

USAGE

What is the intended use of the solution output?
Briefly describe a simple use-case

A simple use case: When a patient shows symptoms of pneumonia, her chest xray is fed into the model to predict in seconds the likelihood of the patient having pneumonia. With this, doctors can help recommend drugs that could help treat the disease at early stage.

Who are the target users?

Health practitioners

What are the key procedures followed while using the solution?
How is the input provided? By whom? How is the output returned?

The chest x ray image which is the input is uploaded into the model by a medical practitioner and the prediction of whether the patient has pneumonia or not is displayed on the screen.

DOMAIN AND APPLICATIONS

What are the domains and applications the solution was tested on or used for?
Were domain experts involved in the development, testing, and deployment? Please elaborate

No.

List applications that the solution has been used for in the past
Please provide information about these applications or relevant pointers. Please provide key performance results for those applications.

The solution has not been used in the past.

DATASET

Describe the dataset
Please provide a brief description of the dataset

N/A

For what purpose was the dataset created?
Was there a specific task in mind? Was there a specific gap that needed to be filled? Please provide a description

N/A

Who created this dataset (e.g., which team, research group) and on behalf of which entity (e.g., company, institution, organization)?

N/A

Who funded the creation of the dataset?
If there is an associated grant, please provide the name of the grantor and the grant name and number

N/A.

COMPOSITION

What do the instances that comprise the dataset represent (e.g., documents, photos, people, countries)?
Are there multiple types of instances (e.g., movies, users, and ratings; people and interactions between them; nodes and edges)? Please provide a description.

N/A.

How many instances are there in total (of each type, if appropriate)?

N/A.

Does the dataset contain all possible instances or is it a sample (not necessarily random) of instances from a larger set?
If the dataset is a sample, then what is the larger set? Is the sample representative of the larger set (e.g., geographic coverage)? If so, please describe how this representativeness was validated/verified. If it is not representative of the larger set, please describe why not (e.g., to cover a more diverse range of instances, because instances were withheld or unavailable).

N/A.

What data does each instance consist of? “Raw” data (e.g., unprocessed text or images)or features?
In either case, please provide a description

N/A.

Is there a label or target associated with each instance?
If so, please provide a description.

N/A.

Is any information missing from individual instances?
If so, please provide a description, explaining why this information is missing (e.g., because it was unavailable). This does not include intentionally removed information, but might include, e.g., redacted text.

N/A.

Are relationships between individual instances made explicit (e.g., users’ movie ratings, social network links)?
If so, please describe how these relationships are made explicit.

N/A.

Are there recommended data splits (e.g., training, development/validation, testing)?
If so, please provide a description of these splits, explaining the rationale behind them

N/A.

Are there any errors, sources of noise, or redundancies in the dataset?
If so, please provide a description.

N/A.

Is the dataset self-contained, or does it link to or otherwise rely on external resources (e.g., websites, tweets, other datasets)?
If it links to or relies on external resources, a) are there guarantees that they will exist, and remain constant, over time; b) are there official archival versions of the complete dataset (i.e., including the external resources as they existed at the time the dataset was created); c) are there any restrictions (e.g., licenses, fees) associated with any of the external resources that might apply to a future user? Please provide descriptions of all external resources and any restrictions associated with them, as well as links or other access points, as appropriate

N/A.

Does the dataset contain data that might be considered confidential (e.g., data that is protected by legal privilege or by doctorpatient confidentiality, data that includes the content of individuals non-public communications)? If so, please provide a description

N/A.

Does the dataset contain data that, if viewed directly, might be offensive, insulting, threatening, or might otherwise cause anxiety?
If so, please describe why.

N/A.

Does the dataset relate to people?
If not, you may skip the remaining questions in this section.

N/A.

Does the dataset identify any subpopulations (e.g., by age, gender)?
If so, please describe how these subpopulations are identified and provide a description of their respective distributions within the dataset

N/A.

Is it possible to identify individuals (i.e., one or more natural persons), either directly or indirectly (i.e., in combination with other data) from the dataset?
If so, please describe how.

N/A.

Does the dataset contain data that might be considered sensitive in any way (e.g., data that reveals racial or ethnic origins, sexual orientations, religious beliefs, political opinions or union memberships, or locations; financial or health data; biometric or genetic data; forms of government identification, such as social security numbers; criminal history)?
If so, please provide a description

N/A.

COLLECTION PROCESS

How was the data associated with each instance acquired?
Was the data directly observable (e.g., raw text, movie ratings), reported by subjects (e.g., survey responses), or indirectly inferred/derived from other data (e.g., part-of-speech tags, model-based guesses for age or language)? If data was reported by subjects or indirectly inferred/derived from other data, was the data validated/verified? If so, please describe how

N/A.

What mechanisms or procedures were used to collect the data (e.g., hardware apparatus or sensor, manual human curation, software program, software API)?
How were these mechanisms or procedures validated?

N/A.

If the dataset is a sample from a larger set, what was the sampling strategy (e.g., deterministic, probabilistic with specific sampling probabilities)?

N/A.

Who was involved in the data collection process
(e.g., students, crowdworkers, contractors) and how were they compensated (e.g., how much were crowdworkers paid)?

N/A.

Over what timeframe was the data collected?
Does this timeframe match the creation timeframe of the data associated with the instances (e.g., recent crawl of old news articles)? If not, please describe the timeframe in which the data associated with the instances was created.

N/A.

Were any ethical review processes conducted
(e.g., by an institutional review board)? If so, please provide a description of these reviewprocesses, including the outcomes, as well as a link or other access pointto any supporting documentation.

N/A.

Does the dataset relate to people? If not, you may skip the remainder of the questions in this section.

N/A.

Did you collect the data from the individuals in question directly, or obtain it via third parties or other sources (e.g., websites)?

N/A.

Were the individuals in question notified about the data collection? If so, please describe (or show with screenshots or other information) how notice was provided, and provide a link or other access point to, or otherwise reproduce, the exact language of the notification itself.

N/A.

Did the individuals in question consent to the collection and use of their data? If so, please describe (or show with screenshots or other information) how consent was requested and provided, and provide a link or other access point to, or otherwise reproduce, the exact language to which the individuals consented.

N/A.

If consent was obtained, were the consenting individuals provided with a mechanism to revoke their consent in the future or for certain uses?
If so, please provide a description, as well as a link or other access point to the mechanism (if appropriate).

N/A.

Has an analysis of the potential impact of the dataset and its use on data subjects
(e.g., a data protection impact analysis)been conducted? If so, please provide a description of this analysis, including the outcomes, as well as a link or other access point to any supporting documentation.

N/A.

PREPROCESSING/CLEANING/
LABELLING

Was any preprocessing/cleaning/labeling of the data done (e.g., discretization or bucketing, tokenization, part-of-speech tagging, SIFT feature extraction, removal of instances, processing of missing values)?
If so, please provide a description. If not, you may skip the remainder of the questions in this section.

N/A.

Was the “raw” data saved in addition to the preprocessed/cleaned/labeled data (e.g., to support unanticipated future uses)?
If so, please provide a link or other access point to the “raw” data.

N/A.

Is the software used to preprocess/clean/label the instances available?
If so, please provide a link or other access point.

N/A.

USES

Has the dataset been used for any tasks already?
If so, please provide a description.

N/A.

Is there a repository that links to any or all papers or systems that use the dataset?
If so, please provide a link or other access point

N/A

What (other) tasks could the dataset be used for?

N/A

Is there anything about the composition of the dataset or the way it was collected and preprocessed/cleaned/labeled that might impact future uses?
For example, is there anything that a future user might need to know to avoid uses that could result in unfair treatment of individuals or groups (e.g., stereotyping, quality of service issues) or other undesirable harms (e.g., financial harms, legal risks) If so, please provide a description. Is there anything a future user could do to mitigate these undesirable harms?

N/A.

Are there tasks for which the dataset should not be used?
If so, please provide a description.

N/A

MAINTENANCE

Who is supporting/hosting/maintaining the dataset?

N/A.

How can the owner/curator/manager of the dataset be contacted (e.g., email address)?

N/A.

Is there an erratum?
If so, please provide a link or other access point.

N/A.

Will the dataset be updated (e.g., to correct labeling errors, add new instances, delete instances)?
If so, please describe how often, by whom, and how updates will be communicated to users (e.g., mailing list, GitHub)?

N/A.

If the dataset relates to people, are there applicable limits on the retention of the data associated with the instances (e.g., were individuals in question told that their data would be retained for a fixed period of time and then deleted)?
If so, please describe these limits and explain how they will be enforced.

N/A.

Will older versions of the dataset continue to be supported/hosted/maintained?
If so, please describe how. If not, please describe how its obsolescence will be communicated to users.

N/A.

If others want to extend/augment/build on/contribute to the dataset, is there a mechanism for them to do so?
If so, please provide a description. Will these contributions be validated/verified? If so, please describe how. If not, why not? Is there a process for communicating/distributing these contributions to other users? If so, please provide a description.

N/A.

DATASET PUBLICLY AVAILABLE

List all the datasets?
For each of the dataset used, please provide a brief description, provide a link to the source of the dataset, attach/provide the link to the datasheet or data statement. If a random sample of the dataset is used, please give description

Chest X-Ray Images (Pneumonia)
The dataset contains 5,863 images in 2 categories namely Normal(Chest x ray) and infected (Chest x ray). The dataset is hosted on kaggle and maintained by the owner Paul Mooney and it does not have a datasheet.
Link to dataset: Click Here

Did the solution require any transformation of the data in addition to those provided in the datasheet? If yes, specify which dataset(s) the transformation was done on and describe the transformation

No.

Did you use synthetic data? If yes, how was it created? Brieﬂy describe its properties and the creation procedure.

No.

MODEL

MODEL DETAILS

A clear description of the model.
Please provide the model date, model version, model type and Information about training algorithms, parameters, fairness constraints or other applied approaches, and features

Model date: 2019. The model was built using keras, a neural network framework in python for deep learning applications. The type of neural network is a 7-level convolutional neural network.

A clear description of the data preparation for the model.
Please provide details of preprocessing, feature engineering and feature selection.

Basic image resize was performed on the data

Is a pre-trained model used?
If yes, please give a brief description of the pre-trained model(s)

No.

A clear explanation of any assumptions.

No.

An analysis of the complexity (time, space, sample size) of algorithm used

No.

When were the models last updated?
How much did the performance change with each update? How often are the models retrained or updated?

The model has not been updated.

EVALUATION

TESTING THE SOLUTION

Describe the testing methodology
Please provide details on train, test and holdout data. What performance metrics were used? (e.g. accuracy, error rates, AUC, precision/recall). Please briefly justify the choice of metrics.

The dataset was split in the ratio 80:10:10 (train, validation, and test dataset). The performance metric used is mean average precision (mAP), it is a very important metric to use when building an object detection model.

Describe the test results
Were latency, throughput, and availability measured? If yes, briefly include those metrics as well.

No.

TESTING BY THIRD PARTIES

Is there a way to verify the performance metrics (e.g., via a service API )?
Briefly describe how a third party could independently verify the performance of the service. Are there benchmarks publicly available and adequate for testing the service

No.

In addition to the solution provider, was this service tested by any third party?
Please list all third parties that performed the testing. Also, please include information about the tests and test results.

This wasn’t tested by a third party.

RESULT

RESULT DETAILS

A clear description of the model result.
Please include the range of hyper-parameters considered, method to select the best hyper-parameter configuration, and specification of all hyper-parameters used to generate results.

The model was able to predict 95% of the test data correctly and 5% wrongly. The model accuracy, precision, recall, f1_score are 94%, 93%, 100% and 96% respectively.

The exact number of training and evaluation runs

40 epochs in 217 steps

A clear definition of the specific measure or statistics used to report results.

The measure of statistics utlized is the classification report available in scikit-learn (python library) which showed the precision, recall , accuracy and f1_score of the model

A description of results with central tendency (e.g. mean) & variation (e.g. error bars)

On training the model, there was an error drop from 100% to 7%.

The average runtime for each result, or estimated energy cost

The average runtime is about 1-2s to predicting each sample result.