Content uploaded by Chee Pui Khei
Author content
All content in this area was uploaded by Chee Pui Khei on Sep 20, 2023
Content may be subject to copyright.
Urinalysis for Stress Level Identification
Ammar Khaled Salem Saber
Department of Biomedical Engineering
& Health Sciences
Faculty of Electrical Engineering, UTM
Johor, Malaysia
k.salem@graduate.utm.my
Mosa Muntadher Mohammed Mosa
Department of Biomedical Engineering
& Health Sciences
Faculty of Electrical Engineering, UTM
Johor, Malaysia
muntadher@graduate.utm.my
Chee Pui Khei
Department of Biomedical Engineering
& Health Sciences
Faculty of Electrical Engineering, UTM
Johor, Malaysia
pkchee@graduate.utm.my
Muhammad Farhanka Thariq
Department of Biomedical Engineering
& Health Sciences
Faculty of Electrical Engineering, UTM
Johor, Malaysia
farhanka.thariq2001@graduate.utm.my
Shahlini A/P Nedumaran
Department of Biomedical Engineering
& Health Sciences
Faculty of Electrical Engineering, UTM
Johor, Malaysia
shahlini@graduate.utm.my
Chua Jin Xiu
Department of Biomedical Engineering
& Health Sciences
Faculty of Electrical Engineering, UTM
Johor, Malaysia
jin.xiu@graduate.utm.my
Yu Jia Qi
Department of Biomedical Engineering
& Health Sciences
Faculty of Electrical Engineering, UTM
Johor, Malaysia
yujiaqi@graduate.utm.my
Abstract—Stress can be defined as any type of change
that causes physical, emotional or psychological strain
according to the World Health Organization. Stress is
our body's response to anything that requires attention
or action. In clinical research, one of the instruments
that are used to measure stress level is by using stress
questionnaires. The outcome of the questionnaire will
then be matched with other means of clinical
investigations using urinalysis before the diagnosis is
confirmed. Since stress leads to more serious mental
health issues in the long run, effective diagnosis of stress
is very important. This study is aimed at investigating
the relationship between stress level and urinalysis
results of a person. This finding implies that the
relationship between stress level and urinalysis results of
a person. The samples collected may help us to get the
data and undergo analysis. The relation between the
stress questionnaire, data collection, and the analysis will
be shown as well together with the ANOVA and
MATLAB of the measured data.
Keywords—Urinalysis, stress level
I. INTRODUCTION
The relationship between urine and stress is
complex and can involve changes in the function of the
kidneys, urinary tract, and other body systems. Stress can
cause changes in the body's hormone levels, which can lead
to changes in the amount and appearance of urine. Stress
can also cause changes in the body's blood flow, which can
affect the function of the kidneys and urinary tract. For
example, stress can cause an increase in the levels of the
hormone adrenaline, which can cause the kidneys to release
more water into the urine and make the urine appear more
dilute. Stress can also cause an increase in the levels of the
hormone cortisol, which can cause the kidneys to retain
more water and make the urine appear more concentrated.
Stress can also cause changes in the pH level of the urine,
making it more acidic or alkaline. Additionally, stress can
also cause discomfort and muscle tension in the bladder and
urinary tract, leading to symptoms such as frequency,
urgency and sometimes pain in the lower abdominal area
Urinalysis is a laboratory test used to analyse a
patient's urine sample. It is a non-invasive method that can
provide valuable information about a person's health status.
A urinalysis typically includes the physical examination of
the urine, chemical analysis, and microscopic examination.
The physical examination may include the colour, clarity,
and specific gravity of the urine. The chemical analysis may
include tests for glucose, protein, blood, pH, and other
substances. The microscopic examination may include the
examination of any cells or crystals present in the urine.
Urinalysis can help diagnose and monitor a wide range of
conditions, including kidney disease, urinary tract
infections, diabetes, and liver disease. It can also detect the
presence of certain medications or illicit drugs in the body.
A urinalysis is a simple and quick test that can be performed
in a doctor's office or at a laboratory.
Stress is a physical, mental and emotional response
to a perceived threat or challenge. It is a normal and natural
response to a wide range of situations, from everyday
pressures at work or school, to major life changes such as
the death of a loved one or the loss of a job. Stress can be
either positive or negative, and it can affect people in
different ways. Positive stress, also known as eustress, can
help motivate and energise people to achieve their goals,
while negative stress, also known as distress, can lead to
feelings of anxiety, depression, and other health problems.
Stress can have both short-term and long-term effects on the
body, including changes in the immune system,
cardiovascular system, and nervous system. Stress
management techniques such as relaxation techniques,
exercise, and therapy can help individuals to cope with
stress and reduce its negative effects.
The Professional Stress Scale (PSS) survey is a
self-report measure used to assess the level of perceived
stress in an individual. It is a widely used tool to measure
stress in various populations including healthcare
professionals, students, and employees. The PSS survey
consists of ten items that measure the individual's perception
of their stress level over the past month. The survey items
are rated on a five-point Likert scale, with responses ranging
from "never" to "very often." The PSS survey has been
shown to be a reliable and valid measure of stress and has
been used in various settings including research studies,
educational settings, and workplaces. The PSS is a quick
and easy tool to use, and it can provide valuable information
about an individual's stress level and how it may be
impacting their well-being.
Our objective is to find the relationship between
the urinalysis and stress level and using Matlab and
ANOVA doing statistical analysis
The problem statement when it comes to the
relationship between stress and urine is to understand how
stress affects the renal and urinary systems and how it can
lead to changes in urine properties and increase the risk of
urinary tract infections. More research is needed to
understand the complex relationship between stress and
urine and identify any potential risk factors. The goal is to
provide healthcare providers with a better understanding of
a patient's overall health and aid in diagnosis and treatment.
II. LITERATURE REVIEW
A. Urinalysis
Urinalysis or known as urine test is a test that
examines the visual, microscopic and chemical aspects of
urine. It is usually used for monitoring certain health
conditions such as kidney disease, liver disease and diabetes
mellitus. This is because urine is a liquid excretion that
contains key information about human health, dietary intake
and exposure to environmental pollutants [1]. There are 11
parameters of urinalysis, including protein, nitrate,
leukocytes, ascorbic acid, glucose, bilirubin, ketone, specific
gravity, urobilinogen, pH and blood. Other than diagnosing
disease, the parameters are also used by researchers to study
the relationship between urine and stress levels.
B. The relationship between urine and stress levels
Proteinuria means that there are proteins in the
urine and this will occur if under stress or after strenuous
exercise. Under normal conditions, approximately 60% of
the proteins are derived from plasma protein. Then, albumin
contributes about 40% of the urinary protein and globulins
constitute 15%. The other proteins include peptides,
enzymes, hormones and immunoproteins. All of these
proteins are reabsorbed by the proximal tubule. Then, Dalui
et al. (2014) investigated the relationship between urinary
albumin: creatinine ratio and stress factors. The depression
level, State and Trait anxiety level and caregivers’ burden
are compared between controls and caregivers. As a result,
it was found that the depression level, State and Trait
anxiety level and urinary albumin: creatinine ratio (UAI:Cr)
of caregivers were significantly higher than the controls [2].
Figure 2.1 Comparison of parameters between
primary caregivers (Cases) and healthy individuals
(Controls) [2]
During the process of screening, there are no other
factors of the raised value of UAI:Cr ratio was noted, the
only difference was the mental stress between caregivers
and controls. Hence, this result can be explained by the fact
that when there is an increase in depression, anxiety and
burdens, it can lead to increased stress and affects the renal
system causing increased albuminuria. Besides, it also
proved that stress could cause the glomerular to become
more permeable to proteins [3]. Thus, this study has shown
that there is a positive correlation between urinary albumin:
creatinine ratio and stress.
Glucosuria, where the urine contains more glucose
than usual also can be affected by emotional stress. This is
because when humans are in stress, either mental stress or
physical stress, a hormone called cortisol is produced. This
hormone could lead to an increase in glucose levels. Next,
an experiment regarding the existence of emotional
glucosuria was also conducted by testing for sugar in
students' urine before and after the examination. The study
was made on two groups of students, second-year medical
students and second-year women students. Both studies
gave the results that had no sugar in the urine before
examination and had small but unmistakable traces of sugar
in the urine passed immediately after the examination. From
the results obtained, it is apparent that mental and emotional
strain can produce temporary glucosuria in humans [4].
Leukocytes or white blood cells play an important
role in the immune system of the human body. It usually
reacts to inflammation and infection. Leukocytosis may also
be caused by stress. This is because depression and anxiety,
the response of the body to stress, are common mood
disorders that are linked to systemic inflammation of the
body (Shafiee et al., 2017). According to Shafiee (2017), he
stated that the mean white blood cell count is increased with
the increasing severity of symptoms of depression and
anxiety among men. He also makes a conclusion that higher
depression and anxiety scores are associated with an
enhanced inflammatory state, as assessed by a higher
haematological inflammatory marker which is white blood
cells [5].
Next, the pH parameter is also useful to determine
the stress level. This is because, under stress, the body will
secrete high amounts of cortisol and catecholamines from
the adrenal gland which leads to the depletion of muscle
glycogen and causes a high pH value [6]. This statement is
also supported by the research conducted by Dobbs et al.
(1981) as a result acquired showed that the urinary pH value
increased after subjects had stressful conditions [7].
However, meal consumption can also affect the pH of urine.
For instance, eating more fruits and vegetables and less
consumption of meat can produce alkaline urine. In contrast,
urine pH may become acidic if intake of certain medicines
that contain chemicals which are responsible for acidic urine
[8] Besides, ketonuria will happen when under stress
conditions. This is due to the reason that ketone is the
alternative energy substrate to glucose and when under
stress, the brain will demand extra glucose from the body to
fulfil its increased needs. Hence, ketone level is increased in
urine and is proved by Kubera et al. (2014) [9].
Lastly, the concentration of bilirubin in urine is
increased when under stress. Yamaguchi et al. (2002)
investigated if the concentration of bilirubin is increased in
urine from subjects exposed to physiological stress. The
subjects are divided into three groups and each group is
having a different stress situation where the first group
needs to deliver a speech with evaluation, the second group
attends the conference only and the third group does not
need to attend the conference. They also need to do a
self-stress score. As a result, the concentration of bilirubin
in the first group is higher than in the other two groups and
there is also a significant correlation between their stress
score and the concentration of bilirubin in urine [10].
III. METHODOLOGY
The relationship between urinalysis and stress level
can be studied by the following methodology that contains
three main parts which are pre-experiment, during
experiment, and post-experiment:
A. Pre-Experiment
1. Choosing a proper questionnaire for measuring the
stress level of the subject ( Perceived Stress Scale -
PSS was chosen for this study).
2. Preparing protocols for the subjects selection and
the researcher which may includes several things
such as subject inclusion and exclusion criteria,
date and time slots, pre-experiment, during
experiment, and post experiment instructions
3. Preparing the guidelines for the subjects (includes
what the subjects need to do before, during, and
after the experiment) and the codes for the ethical
conduct (which includes the privacy and how you
are going to make the data secure).
4. Preparing the Consent form for the subjects to be
signed if they agree to be involved in this study.
5. Searching for subjects (Male) who are interested to
participate in this study and they should fully fill
the selection criteria.
6. Send the necessary forms to the subjects to be read
and signed by them and selecting their preferable
time slots.
B. During Experiment
7. Reach the lab before experiment slots and prepare
the needed tools for urinalysis, the questionnaire,
and sanitising material.
8. The researcher has to wear gloves and a mask for
protection and generate a specific code for the
coming subject.
9. The subject enters the lab and starts filling the
questionnaire that has two parts (PSS and general
questions about his daily life routine).
10. Starting doing the urinalysis experiment by asking
the subject to fill the container with urine (the
subject needs to wash and dry his hand before and
after filling the container).
11. Dividing the urine into five samples to get five
results for more accuracy (Figure 3.1).
Figure 3.1 During Experiment
12. Printing the urinalysis result with the specific code.
13. Ask the subject to dispose of the urine and to wash
and sanitise the container well.
14. Finishing the experiment with the same procedure
for all subjects.
C. Post-Experiment
15. Rechecking and rearranging the collected data and
results of the experiments.
16. Wash and sanitise all of the used material and the
place that was used (Figure 3.1).
Figure 3.2 Post-Experiment
17. Start finding the stress level from the questionnaire
results and analysis.
18. Start doing data analysis using two methods which
are ANOVA and Matlab with specific parameters.
IV. RESULT
The table below showed the results taken from the urinalysis
test reports of 10 male subjects. The results have been
differentiated into different levels of abnormal condition in
which the abnormal values are indicated by the device. The
results provided contain the parameters BIL, BLD, CLA,
COL, GLU, KET, LEU, NIT, Ph, PRO, SG and UBG. Each
parameters represent:
BIL- bilirubin
CLA- clarity
COL- colour
GLU- glucose
KET- ketone
LEU- leukocytes
NIT- nitrite
Ph- Ph value
PRO- protein
SG- specific gravity
UBG- urobilinogen
A. Normal Results
In this characterization, all of the parameters shown in the
report of the subject is in the normal value range or normal
condition.
Figure 4.1 Result of QUEZV
Figure 4.2 Result of 38ICM
Figure 4.3 Result of J6ILD
B. Fewer Abnormal Results
Both of the subjects are different with fewer abnormal
results because each of them have less abnormal condition
in 5 samples taken.
Figure 4.4 Result of ZERXZ
Figure 4.5 Result of SHHNY
C. Moderate Abnormal Results
For the moderate abnormal results, the subjects chosen have
more abnormal condition or abnormal range. However, the
moderate abnormal results here are similar with normal
abnormal results which have high consistency in 5 samples
and are more suitable to be used for analysis.
Figure 4.6 Result of MFQ0Q
Figure 4.7 Result of K8YAN
Figure 4.8 Result of ZGZCE
D. High Abnormal Results
There are two subjects with more abnormal range and
condition in their urinalysis test report. Both of them have
abnormal results in the parameters of colour, ketone,
specific gravity while each of them consist of problems in
protein and clarity too.
Figure 4.9 Result of K4B0M
Figure 4.10 Result of YKSIS
V. DISCUSSION
Anova Analysis
Figure 5.1 ANOVA Result of K4BOM
Figure 5.2 ANOVA Result of YKSIS
From the average of 5 samples for each two individuals of
high abnormal stress, high specific gravity(SG) can be an
indication of stress, as the body is producing more
substances in response to the stress. High levels of
urobilinogen(UBG) in the urine can be an indication of
increased stress, as the body produces more red blood cells
to respond to stress.
Figure 5.3 ANOVA Result of ZGZCE
From the average of 5 sample for the individual of moderate
abnormal stress A higher pH indicates that the urine is more
alkaline, which can indicate that the person is under stress.
Figure 5.4 Result of K4BOM
Darker colours(COL: Orange) of urine can indicate
dehydration caused by increased stress.
Figure 5.5 Result of YKSIS
If the urine is not clear (CLA: Cloudy), this can be an
indication of stress, as the body may be producing
substances such as proteins or hormones to help it cope with
the stress.
A. Specific Gravity(SG) Analysis
Figure5.6 ANOVA Analysis of Specific
Gravity(SG)
The p-value is less than the significance level(p=0.0023),
can reject the null hypothesis and can conclude that there is
a significant difference in specific gravity among the
groups of stress and no stress. This means that the
urinalysis results are different between the group of
individuals experiencing stress and the group of individuals
not experiencing stress.
B. Urobilinogen(UBG) Analysis
Figure 5.7 ANOVA Analysis of Urobilinogen(UBG)
The p-value is very close to zero (0.0001), it can be
considered a strong indication that the null hypothesis is
false, and that there is a significant difference in
Urobilinogen (UBG) among the groups of stress and no
stress.This means that the urinalysis results are different
between the group of individuals experiencing stress and the
group of individuals not experiencing stress.
C. pH Analysis
Figure 5.8 ANOVA Analysis of pH
The p-value is less than the significance level(p=0.0006),
can reject the null hypothesis and can conclude that there is
a significant difference in pH among the groups of stress
and no stress. This means that the urinalysis results are
different between the group of individuals experiencing
stress and the group of individuals not experiencing stress.
Matlab Analysis
A. Problems and Solution
1) MATLAB Model Optimisation.
The initial plan of using Matlab Neural Networks,
which has artificial intelligent tools to train the model, had
to be changed due to the lack of data. We only had 50 sets of
data, which is far below the minimum requirement of 500
sets. As such, we decided to use Matlab Machine Learning
and Deep Learning Tool, the Classification Learner, as an
alternative. The Classification Learner allowed us to
evaluate and compare different types of models and choose
the one that best fits our purpose. We were able to optimise
the model by adjusting the training parameters and other
settings. Ultimately, this enabled us to create a reliable
model for our urinalysis as a stress indicator.
Figure 5.9 Import raw data of urinalysis and
questionnaire with stressors in Matlab
2) Subject selection
The criteria for inclusion and exclusion of the test
subjects were set prior to the experiment. The criteria of
inclusion included male genders, adults between the ages of
18-50, a normal routine of studying as a biomedical
engineering student, physically healthy kidneys, diagnosis
established following the World Federation of Neurology
criteria, more than 6 and less than 36 months of evolution of
the neurologic disease, more than 18 and less than 70 years
old, forced vital capacity, total time of oxygen saturation,
and signed informed consent. The criteria of exclusion
included neurological or psychiatric concomitant disease,
need of parenteral or enteral nutrition through percutaneous
endoscopic gastrostomy or nasogastric tube, concomitant
systemic disease, treatment with corticosteroids,
immunoglobulins or immunosuppressors during the last 12
months, inclusion in other clinical trials, inability to
understand the informed consent, and persons having kidney
or urinary disease or either, or cannot be tested properly. It
was established that the subjects of the experiment would be
biomedical engineering students, thus meeting the criteria of
inclusion. Furthermore, it was also established that no
member of specific demographic subgroups would be
excluded unless the data required were already available
elsewhere and could be obtained from the corresponding
data source.
B. MATLAB Data Analysis of Stressor vs Stress Score
The scatter plot of stressor vs stress score revealed
interesting insights about the subject’s ability to cope with
their environment. It was observed that, with increasing
stress scores, the subject’s ability to cope with all the things
they had to do increased.
Figure 5.10 Graph of ability to cope with all the things
they had to do vs the stress scores
Furthermore, it was noted that smoking habits had
a significant impact on the level of stress scores, with higher
scores being seen in those who smoked. This suggests that
smoking could be a potential predictor of stress levels.
Figure 5.11Graph of smoking habit vs the stress
scores
On the other hand, it was seen that exercising was a
habit that all of the subjects had in common. It could be
opted as one of the factors that let the subjects have
moderate stress scores although coping with great
challenges and having other unhealthy habits in life.
However, more research would have to be done to prove the
correlation.
Figure 5.12 Graph of exercising habit vs the
stress scores
However, when it came to the habit of drinking
coffee or tea, the data was scattered and varied, indicating
that these habits had a less significant impact on the
subject's stress levels. Nevertheless, this data could be
further explored to determine if there are any correlations
between drinking coffee or tea and stress levels. The
content, known as caffeine, affected the accuracy of the
reading in the following data analysis. However, it showed
us caffeine and other meals taken could cause lasting effects
in urine for the human body, but did not show a strong
correlation with stress for the male biomedical engineering
students as the subjects in this research.
Figure 5.13 Graph of coffee or tea consumption vs
stress scores.
C. MATLAB Data Analysis of Urinalysis
as a Stress Indicator
1) Same status indicates normal for all subjects
The parameters that were assessed in the urinalysis
as a stress indicator were Bilirubin (BIL), Blood (BLD),
Glucose (GLU), Leukocytes (LEU) and Nitrite (NIT). All of
the data showed the same status, indicating that all of the
parameters were normal. The criteria we set for the
assessment was that all parameters do not show the same
status, but this was the case in all of the urinalysis results.
As such, the urinalysis would not be using this group of
parameters if it would be a reliable stress indicator for the
students who participated in the study, as they all turned out
to be biomedical engineering students.
Figure 5.14 Scatter Plot of Stress Scores vs Bilirubin
Figure 5.15 Scatter Plot of Stress Scores vs Blood
Figure 5.16 Scatter Plot of Stress Scores vs Glucose
Figure 5.17 Scatter Plot of Stress Scores vs
Leukocytes
Figure 5.18 Scatter Plot of Stress Scores vs Nitrite
2) Scattered status indicates not suitable as the
indicator of stress for all subjects
The research on urinalysis as a stress indicator was
conducted on a group of biomedical engineering students.
Prior to the study, a set of criteria was established to ensure
accuracy and appropriateness of the results. However,
certain indicators of the results of the study turned out to be
quite scattered, which indicated that this method is not
suitable as an indicator of stress for all subjects.
Figure 5.19 Scatter Plot of Stress Scores vs Clear
Figure 5.20 Scatter Plot of Stress Scores vs Colour
Figure 5.21 Scatter Plot of Stress Scores vs Ketones
Figure 5.22 Scatter Plot of Stress Scores vs Protein
In order to further explore this concept, further
research is needed to identify the main factors that affect the
results and to find alternate methods of measuring stress. In
the research, the team was using the following parameters
that are not showing all same or scattered data excluding the
above mentioned in C(1) and C(2) of data analysis using
MATLAB engineering software in the (V) discussion part of
this report.
3) Comparison of Stress Indicators analysed using
ANOVA vs MATLAB classification tool
The results of the urinalysis proved to be
particularly revealing. When the data identified as unsure
accuracy were taken into account in the MATLAB
classification tool, a direct correlation between the stress
scores of the subject and their respective specific gravity
values was observed. The nearer the specific gravity value
was to 1.00, the higher the stress score. This was further
corroborated by the ANOVA, which revealed that the
groups with the highest stress scores had a greater specific
gravity value than the rest. This outcome effectively
corroborated our initial hypothesis that a high specific
gravity reading could be used as an indicator of stress, as it
can be assumed that the body is producing more substances
in response to the stress. All in all, the results of the
urinalysis proved to be particularly revealing in this regard.
Figure 5.23 Scatter Plot of Stress Scores vs Specific
Gravity
Before the comparison, the urobilinogen is a waste
product of the breakdown of red blood cells. High levels of
urobilinogen in the urine can be an indication of increased
stress, as the body produces more red blood cells to respond
to stress.
However, comparing MATLAB classification to
our hypothesis, the hypothesis could not be true in this
experiment due to several reasons, as the stress level among
the male biomedical engineering students as subjects do not
have a consistent rate of breaking down of the red blood
cells as some would exercise and some not according to the
questionnaires that may have affected the accuracy.
According to the study "Effect of different doses of aerobic
exercise training on total bilirubin levels" by Swift et al.
(2012), exercise training was found to significantly increase
serum bilirubin levels.
Nevertheless, urobilinogen is a great parameter
using ANOVA when all data are opted in as higher levels of
it indicate a higher stress level. Using MATLAB,
Urobilinogen is not a great parameter as affected by
exercising habits.
Figure 5.24 Scatter Plot of Stress Scores vs
Urobilinogen
Our initial hypothesis, supported by ANOVA
analysis, suggested that a higher pH in urine would be
indicative of stress. Notwithstanding, when the data
gathered through MATLAB analysis was scrutinised, the pH
was found to be scattered and not suitable to use as a
parameter in this experiment.
This prompted us to investigate further, and we
discovered that the acidity of urine could be affected by the
consumption of tea and coffee, due to the caffeine content.
In support of this, John and Cole (1833) conducted a study
to demonstrate that the caffeine in tea and coffee increases
urinary acidity by increasing the amount of certain acids that
are excreted through urination.
Consequently, the hypothesis of a higher pH
indicating a urine sample is more alkaline and under stress
is not accurate when the MATLAB analysis is used, but
could be accurate when all data is analysed using ANOVA.
Figure 5.25 Scatter Plot of Stress Scores vs pH of
urine
The results of our experiment indicated that the
urinalysis as a stress indicator was indeed successful. In
order to ensure the accuracy of our results, we had set the
criteria for the experiment which included the students
having to be biomedical engineering students.
Upon completing the experiment, it became
evident that the use of ANOVA and MATLAB to calculate
the results of the urinalysis were not the same. While
MATLAB may have been more accurate, ANOVA allowed
us to determine if there were any significant differences
between the results.
We concluded that although both ANOVA and
MATLAB were used for urinalysis as a stress indicator, the
results were not always the same, leading us to believe that
further research and more comparisons should be conducted
in order to determine which method is more reliable.
VI. CONCLUSION
During this module, ANOVA and MATLAB were used
to conduct the experiment. To find and analyse the relation
between urinalysis and stress level, different samples were
chosen as shown in the methodology. The experiment
indicated that the stress level and high SG whenever the
body is producing more substance in response to stress. The
same result when high pH results and/or high UBG, it can
be concluded that more alkaline production which indicates
the person is stressed. By utilising MATLAB, the ability of
the subject to deal with the surroundings increases as the
stress scores increase. The relationship between urinalysis
and stress level has been the focus of research for a long
time ago and was shown in the discussion. However, we still
lack a consensus regarding an appropriate methodology that
can be widely used to measure the relationship of stress
levels with urinalysis. The use of MATLAB in this module
also experiences limitations in the number of subjects
required.
REFERENCES
[1] Zhang Z, Liu J, Cheng Y, Chen J, Zhao H and Ren X (2022) Urine
Analysis has a Very Broad Prospect in the Future. Front. Anal. Sci.
1:812301. doi: 10.3389/frans.2021.812301
[2] Dalui, A., Guha, P., De, A., Chakraborty, S., & Chakraborty, I. (2014).
Assessment of stress & related albuminuria in caregivers of severe mentally
ill persons. The Indian journal of medical research,139(1), 174–177.
[3] S. Ratnakar C. Banupriya P. Doureradjou S. Vivekanandam M.K.
Srivastava B.C. Koner Evaluation of anxiety, depression and urinary
protein excretion among the family caregivers of advanced cancer
patientsBiol Psychol2008792234238
[4] Folin, O., Denis, W., & Smillie, W. G. (1914). Some observations on
“emotional glycosuria” in man. Journal of Biological Chemistry,17(4),
519-520.
[5] Shafiee, M., Tayefi, M., Hassanian, S. M., Ghaneifar, Z., Parizadeh, M.
R., Avan, A., Rahmani, F., Khorasanchi, Z., Azarpajouh, M. R., Safarian,
H., Moohebati, M., Heidari-Bakavoli, A., Esmaeili, H., Nematy, M.,
Safarian, M., Ebrahimi, M., Ferns, G. A., Mokhber, N., &
Ghayour-Mobarhan, M. (2017). Depression and anxiety symptoms are
associated with white blood cell count and red cell distribution width: A
sex-stratified analysis in a population-based study.
Psychoneuroendocrinology,84, 101–108.
https://doi.org/10.1016/j.psyneuen.2017.06.021
[6] Swift DL, Johannsen NM, Earnest CP, Blair SN, Church TS. Effect of
different doses of aerobic exercise training on total bilirubin levels. Med
Sci Sports Exerc. 2012 Apr;44(4):569-74. doi:
10.1249/MSS.0b013e3182357dd4. PMID: 21900842; PMCID:
PMC3267007.
[7] Tabite, R., Barka, K., Farh, M., El Abbadi, N., Riad, F., Tahri, E. H., ...
& El Khasmi, M. (2018). Association of serum levels of cortisol and pH
and stress oxidant in camel meat during ten days of storage. ISOCARD.
[8] Dobbs, S. D., Strickler, D. P., & Maxwell, W. A. (1981). The effects of
stress and relaxation in the presence of stress on urinary pH and smoking
behaviors. Addictive Behaviors,6(4), 345-353.
[9] Muhammad Imran Qadir and Amna Ashraf. (2019). Is There any
Correlation between Urine PH and Fear of Darkness. Journal of Pharmacy
and Drug Development 1(2).
[10] John, J., Cole. (1833). On the deleterious effects produced by drinking
tea and coffee in excessive quantities.. The Lancet, 20(508):274-278. doi:
10.1016/S0140-6736(02)94577-0
[11] Kubera, B., Hubold, C., Wischnath, H., Zug, S., & Peters, A. (2014).
Rise of ketone bodies with psychosocial stress in normal weight men.
Psychoneuroendocrinology,45, 43–48.
https://doi.org/10.1016/j.psyneuen.2014.03.008
[12] Yamaguchi, T., Shioji, I., Sugimoto, A., & Yamaoka, M. (2002).
Psychological stress increases bilirubin metabolites in human urine.
Biochemical and biophysical research communications,293(1), 517–520.
https://doi.org/10.1016/S0006-291X(02)00233-4
APPENDIX
APPENDIX 1:
MATLAB Classification Code
function [trainedClassifier, validationAccuracy] =
trainClassifier(trainingData)
% [trainedClassifier, validationAccuracy] =
trainClassifier(trainingData)
% Returns a trained classifier and its accuracy. This code
recreates the
% classification model trained in Classification Learner app.
Use the
% generated code to automate training the same model with
new data, or to
% learn how to programmatically train models.
% Input:
% trainingData: A table containing the same predictor
and response
% columns as those imported into the app.
% Output:
% trainedClassifier: A struct containing the trained
classifier. The
% struct contains various fields with information
about the trained
% classifier.
% trainedClassifier.predictFcn: A function to make
predictions on new
% data.
% validationAccuracy: A double containing the
accuracy in percent. In
% the app, the History list displays this overall
accuracy score for
% each model.
%
% Use the code to train the model with new data. To retrain
your
% classifier, call the function from the command line with
your original
% data or new data as the input argument trainingData.
%
% For example, to retrain a classifier trained with the
original data set
% T, enter:
% [trainedClassifier, validationAccuracy] =
trainClassifier(T)
%
% To make predictions with the returned 'trainedClassifier'
on new data T2,
% use
% yfit = trainedClassifier.predictFcn(T2)
%
% T2 must be a table containing at least the same predictor
columns as used
% during training. For details, enter:
% trainedClassifier.HowToPredict
% Auto-generated by MATLAB on 14-Jan-2023 15:59:08
% Extract predictors and response
% This code processes the data into the right shape for
training the
% model.
inputTable = trainingData;
predictorNames = {'SampleID', 'RackNumber',
'TubeNumber', 'BIL', 'BLD', 'CLA', 'COL', 'GLU', 'KET',
'LEU', 'NIT', 'Ph', 'PRO', 'SG', 'UBGumolL', 'Age',
'DoYouSmoke', 'WhatWasYourLastMeal',
'HowOftenDoYouDrinkCoffeeAndTea',
'HowLongDoYouExerciseEachWeek',
'InTheLastMonthHowOftenHaveYouBeenUpsetBecauseOfS
omethingThatHap',
'InTheLastMonthHowOftenHaveYouFeltThatYouWereUnab
leToControlTheI',
'InTheLastMonthHowOftenHaveYouFeltNervousAndStress
ed',
'InTheLastMonthHowOftenHaveYouFeltConfidentAboutYo
urAbilityToHan',
'InTheLastMonthHowOftenHaveYouFeltThatThingsWereG
oingYourWay',
'InTheLastMonthHowOftenHaveYouFoundThatYouCouldN
otCopeWithAllThe',
'InTheLastMonthHowOftenHaveYouBeenAbleToControlIrri
tationsInYour',
'InTheLastMonthHowOftenHaveYouFeltThatYouWereOnTo
pOfThings',
'InTheLastMonthHowOftenHaveYouBeenAngeredBecause
OfThingsThatHapp',
'InTheLastMonthHowOftenHaveYouFeltDifficultiesWerePil
ingUpSoHigh', 'STRESS_SCORES', 'STRESS_LEVEL'};
predictors = inputTable(:, predictorNames);
response =
inputTable.DidYouDrinkEnoughTheWaterBeforeTheTest;
isCategoricalPredictor = [true, false, false, true, true, true,
true, true, true, true, true, false, true, false, false, false, true,
true, true, true, false, false, false, false, false, false, false,
false, false, false, false, true];
% Train a classifier
% This code specifies all the classifier options and trains the
classifier.
classificationTree = fitctree(...
predictors, ...
response, ...
'SplitCriterion','gdi',...
'MaxNumSplits', 100, ...
'Surrogate','off',...
'ClassNames', categorical({'500 ml approximately';
'501 ml approximately';'502 ml approximately';'503 ml
approximately';'504 ml approximately';'70% of the
requested';'Around 1 Liter';'No';'Yeah,';'Yes'}));
% Create the result struct with predict function
predictorExtractionFcn = @(t) t(:, predictorNames);
treePredictFcn = @(x) predict(classificationTree, x);
trainedClassifier.predictFcn = @(x)
treePredictFcn(predictorExtractionFcn(x));
% Add additional fields to the result struct
trainedClassifier.RequiredVariables = {'Age','BIL','BLD',
'CLA','COL','DoYouSmoke','GLU',
'HowLongDoYouExerciseEachWeek',
'HowOftenDoYouDrinkCoffeeAndTea',
'InTheLastMonthHowOftenHaveYouBeenAbleToControlIrri
tationsInYour',
'InTheLastMonthHowOftenHaveYouBeenAngeredBecause
OfThingsThatHapp',
'InTheLastMonthHowOftenHaveYouBeenUpsetBecauseOfS
omethingThatHap',
'InTheLastMonthHowOftenHaveYouFeltConfidentAboutYo
urAbilityToHan',
'InTheLastMonthHowOftenHaveYouFeltDifficultiesWerePil
ingUpSoHigh',
'InTheLastMonthHowOftenHaveYouFeltNervousAndStress
ed',
'InTheLastMonthHowOftenHaveYouFeltThatThingsWereG
oingYourWay',
'InTheLastMonthHowOftenHaveYouFeltThatYouWereOnTo
pOfThings',
'InTheLastMonthHowOftenHaveYouFeltThatYouWereUnab
leToControlTheI',
'InTheLastMonthHowOftenHaveYouFoundThatYouCouldN
otCopeWithAllThe','KET','LEU','NIT','PRO','Ph',
'RackNumber','SG','STRESS_LEVEL',
'STRESS_SCORES','SampleID','TubeNumber',
'UBGumolL','WhatWasYourLastMeal'};
trainedClassifier.ClassificationTree = classificationTree;
trainedClassifier.About = 'This struct is a trained model
exported from Classification Learner R2021a.';
trainedClassifier.HowToPredict = sprintf('To make
predictions on a new table, T, use: \n yfit = c.predictFcn(T)
\nreplacing ''c'' with the name of the variable that is this
struct, e.g. ''trainedModel''. \n \nThe table, T, must contain
the variables returned by: \n c.RequiredVariables \nVariable
formats (e.g. matrix/vector, datatype) must match the
original training data. \nAdditional variables are ignored. \n
\nFor more information, see <a
href="matlab:helpview(fullfile(docroot, ''stats'', ''stats.map''),
''appclassification_exportmodeltoworkspace'')">How to
predict using an exported model</a>.');
% Extract predictors and response
% This code processes the data into the right shape for
training the
% model.
inputTable = trainingData;
predictorNames = {'SampleID','RackNumber',
'TubeNumber','BIL','BLD','CLA','COL','GLU','KET',
'LEU','NIT','Ph','PRO','SG','UBGumolL','Age',
'DoYouSmoke','WhatWasYourLastMeal',
'HowOftenDoYouDrinkCoffeeAndTea',
'HowLongDoYouExerciseEachWeek',
'InTheLastMonthHowOftenHaveYouBeenUpsetBecauseOfS
omethingThatHap',
'InTheLastMonthHowOftenHaveYouFeltThatYouWereUnab
leToControlTheI',
'InTheLastMonthHowOftenHaveYouFeltNervousAndStress
ed',
'InTheLastMonthHowOftenHaveYouFeltConfidentAboutYo
urAbilityToHan',
'InTheLastMonthHowOftenHaveYouFeltThatThingsWereG
oingYourWay',
'InTheLastMonthHowOftenHaveYouFoundThatYouCouldN
otCopeWithAllThe',
'InTheLastMonthHowOftenHaveYouBeenAbleToControlIrri
tationsInYour',
'InTheLastMonthHowOftenHaveYouFeltThatYouWereOnTo
pOfThings',
'InTheLastMonthHowOftenHaveYouBeenAngeredBecause
OfThingsThatHapp',
'InTheLastMonthHowOftenHaveYouFeltDifficultiesWerePil
ingUpSoHigh','STRESS_SCORES','STRESS_LEVEL'};
predictors = inputTable(:, predictorNames);
response =
inputTable.DidYouDrinkEnoughTheWaterBeforeTheTest;
isCategoricalPredictor = [true, false, false, true, true, true,
true, true, true, true, true, false, true, false, false, false, true,
true, true, true, false, false, false, false, false, false, false,
false, false, false, false, true];
% Perform cross-validation
partitionedModel =
crossval(trainedClassifier.ClassificationTree, 'KFold', 9);
% Compute validation predictions
[validationPredictions, validationScores] =
kfoldPredict(partitionedModel);
% Compute validation accuracy
validationAccuracy = 1 - kfoldLoss(partitionedModel,
'LossFun','ClassifError');
APPENDIX 2:
Urinalysis Invitation and Using Soulbound NFT to Remind Contributors