代写Biostatistics POPH90013 – 2024 Assignment 3代写留学生Matlab语言程序
- 首页 >> Matlab编程Biostatistics POPH90013 - 2024
Assignment 3 - Questions
Due: Wednesday 8th May, 11:00 pm (Melbourne time)
The maximum mark for this assignment is 60. It forms 30% of the final grade for this subject. Your assignment should be submitted via Gradescope as a PDF document.
Please put your student ID number in the header of the document.
Unless you are asked to do so, please do not include any Stata output in your assignment document. Instead, format any results you want to show in away that would be suitable for inclusion in a report or journal article.
This Assignment has 6 questions. You should attempt all questions.
For this assessment, you will need to download and open the files “Assignment3_wound.dta” and “Assignment3_heart.dta” from Canvas. Perform all Stata tasks via a do-file (you can use the do-files from the Stata practicals located on Canvas, as a guide).
Section A - Wound Dataset
The Wound Healing Society defines a chronic wound as one that has failed to proceed through an orderly and timely reparative process to produce anatomic and functional integrity within an expected period. Chronic wounds represent a significant annual burden on the Australian health care system, with direct health care costs reaching $2.85 billion. Several factors can cause improper or impaired wound healing. Such factors include age, stress, diabetes, obesity, medications, alcoholism, smoking, and nutrition. A better understanding of the influence of these factors on repair may lead to therapeutics that improve wound healing and resolve impaired wounds.
For this section of the assignment, you will be using the dataset “Assignment3_wound.dta”, a prospective cohort study of 650 wound patients, investigating the risk factors for wound infection, where the patients were followed up for wound infection over 12 weeks while receiving standard care. A description of the variables included in the Assignment3_wound.dta dataset is provided in Table 1 below.
Table 1: Description of the variables in the Assignment3_wound.dta dataset
Variable name |
Description |
id |
Study participant identification number |
age |
Age (years) |
sex_male |
Sex (0 – Female, 1 – Male) |
bmi |
Body mass index (kg/m2) |
smoke |
Smoking status (0 – Non-smoker, 1 – Smoker) |
alc |
Alcohol consumption per week (ml/week) |
diab |
Type II diabetes (0 – No, 1 – Yes) |
infect |
Was the wound infected at twelve weeks? (0 – No, 1 – Yes) |
stress |
Psychological stress at twelve weeks (units, Range: 0 - No stress, 10 - Maximum stress) |
*All variables except wound infection (infect) and psychological stress (stress) were measured at baseline (i.e., hospital admission).
Imagine you area graduate research student at the University of Melbourne, investigating factors that increase a patient’s risk for delayed wound healing and the psychological effects of chronic non- healing wounds. You will be using data from the prospective cohort study of 650 wound patients mentioned above for your research.
Question 1 [15 marks]
Your current research project focuses on evaluating whether patients with type II diabetes are more susceptible to wound infections. You have been invited to present your research at the University’s Graduate Research Seminar Series, and as part of your presentation, you have been asked to submit an abstract summarising your research.
Write an abstract based on your current research project to send to the organiser of the Graduate Research Seminar Series. Your abstract should include the following sections (max 250 words):
a) Background [2 marks]
b) Methods [3 marks]
c) Results [8 marks]
i. Summarise and describe the distribution of all baseline patient characteristics of the study population.
ii. Quantify the proportion of patients with a wound infection at twelve weeks, and include a comment about any missing data for wound infection.
iii. Quantify and interpret the association between type II diabetes and wound infection. d) Conclusion [2 marks]
Question 2 [10 marks]
For your next research project, you have planned to investigate whether impaired wound healing may lead to increased levels of psychological stress. You have been asked to conduct an initial assessment of the association between wound infection and psychological stress, and summarise your findings in a single presentation slide for the upcoming research team meeting.
Complete the tasks outlined below required to produce the presentation slide:
a) Visualise and quantify the association between wound infection and psychological stress. [6 marks]
b) Summarise your findings in no more than 4 key points for the presentation slide (max 100 words). [4 marks]
Question 3 [7 marks]
You are part of a journal club which meets monthly to review articles on treatments for chronic wounds. For the next meeting of the journal club, you have been assigned to lead a discussion on the study titled, “LeucoPatch system for the management of hard-to-heal diabetic foot ulcers in the UK, Denmark, and Sweden: an observer-masked, randomised controlled trial (Game et al., Lancet Diabetes Endocrinol, 2018)a.”
In preparation for the meeting, you must review the study abstract provided below, discuss the study findings in the context of the primary research question, and write a short paragraph on whether or not you agree with the conclusions made by the study investigators (max 250 words). [7 marks]
Background: The LeucoPatch device uses bedside centrifugation without additional reagents to generate a disc comprising autologous leucocytes, platelets, and fibrin, which is applied to the surface of the wound. We aimed to test the effectiveness of LeucoPatch on the healing of hard-to-heal foot ulcers in people with diabetes.
Methods: This was a multicentre, international, observer-masked, randomised controlled trial of people with diabetes and a hard-to-heal foot ulcer done in 32 specialist diabetic foot clinics in three countries (UK, Denmark, and Sweden). After a 4-week run-in period, those with a reduction in ulcer area of less than 50% were randomly allocated (1:1) by computer-generated, web-based randomisation (block sizes of two, four, and six) to either prespecified good standard care alone or care plus weekly application of LeucoPatch. The primary outcome was the proportion of ulcers that healed within 20 weeks assessed in the intention-to-treat population (all participants with post- randomisation data collected), defined as complete epithelialisation (confirmed by an observer who was masked to randomisation group), and remained healed for 4 weeks. This trial is registered with the ISRCTN registry, number 27665670, and ClinicalTrials.gov, number NCT02224742.
Findings: Between Aug 30, 2013, and May 3, 2017, 269 participants were randomly allocated to receive treatment (137 to receive standard care and 132 to receive LeucoPatch). The mean age was 61·9 years (SD 11·6), 217 (82%) were men, and 222 (83%) had type 2 diabetes. In the LeucoPatch group, 45 (34%) of 132 ulcers healed within 20 weeks versus 29 (22%) of 134 ulcers in the standard care group (odds ratio 1·58, 96% CI 1·04-2·40; p=0·0235) by intention-to-treat analysis. Time to healing was shorter in the LeucoPatch group (p=0·0246) than in the standard care group. No difference in adverse events was seen between the groups. The most common serious adverse event (SAE) was diabetic foot infection (24 events in the LeucoPatch group [24% of all SAEs] and 20 in the standard care group [27% of all SAEs]. There were no device-related adverse events.
Interpretation: The use of LeucoPatch is associated with significant enhancement of healing of hard- to-heal foot ulcers in people with diabetes.
a Game F, JeffcoateW, Tarnow L, Jacobsen JL, Whitham DJ, Harrison EF, Ellender SJ, Fitzsimmons D, Löndahl M; LeucoPatch II trial team. LeucoPatch system for the management of hard-to-heal diabetic foot ulcers in the UK, Denmark, and Sweden: an observer-masked, randomised controlled trial. Lancet Diabetes Endocrinol. 2018;6(11):870-878.
Section B - Heart Disease Dataset
Heart disease is the leading single cause of death in many countries across the globe including Australia. Heart disease could be in various forms including, coronary artery diseases, arrhythmias, and congenital heart defects, among many others.
For this section of the assignment, you will be using the dataset “Assignment3_heart.dta” . This is a modified dataset from the HEART randomised controlled trial with 244 patients, investigating the effects of abstinence from smoking on the risk of heart disease.
Adults who smoked more than 20 cigarettes per day and had no history of heart disease were randomly assigned in a 1:1 ratio to either abstain from smoking or continue their usual smoking. The primary outcome was the presence of heart disease at 6 weeks follow-up. Heart disease was detected if a patient had at least 1 major vessel with >50% narrowing. Systolic blood pressure was measured at follow-up as a secondary outcome.
A description of the variables included in the Assignment3_heart.dta dataset is provided in Table 2 below.
Table 2: Description of the variables in the Assignment3_heart.dta dataset
Variable name |
Description |
id |
Study participant identification number |
age |
Age (years) |
sex_male |
Sex (0 – Female, 1 - Male) |
cholesterol |
Serum cholesterol (mg/dL) |
treatment |
Treatment group (0 – Control, 1 – Intervention)a |
bloodpressure |
Systolic blood pressure at follow-up (mmHg)b |
vessels |
Number of major vessels with >50% narrowing at follow-up |
a Treatment group: Control = Smoking as usual; Intervention = Abstain from smoking. bA minimal difference of 10 mmHg in blood pressure is of clinical importance.
*All variables except the number of major vessels with >50% narrowing (vessels) and systolic blood pressure (bloodpressure) were measured at baseline.
Question 4 [15 marks]
Imagine you area teaching associate at the University of Melbourne, teaching biostatistics to Master of Public Health students at the University. You have been tasked with grading the assignment question below and providing feedback to students.
Question: The aim of this question is to investigate whether abstinence from smoking leads to reduced risk of heart disease. Using data from the HEART randomised controlled trial with 244 patients: i. Generate the primary outcome for this trial, the presence of heart disease at 6 weeks follow- up. Presence of heart disease is defined as a patient having at least 1 major vessel with >50% narrowing. Provide the Stata code used to generate the primary outcome. ii. Quantify the proportion of patients with heart disease at 6 weeks follow-up in each treatment group. iii. Quantify and interpret the association between smoking and heart disease. |
Review the student answer below and provide feedback to the student. Your feedback should include the following:
a) Identify any errors made by the student when formulating the answer. [8 marks] b) Provide amodel answer to address the above question. [7 marks]
Student answer: i. Stata code: gen heart_disease = 1 if vessels > 1 replace heart_disease = 0 if heart_disease == . ii. Proportion with heart disease at follow-up in the control group = 46 (37.7%) Proportion with heart disease at follow-up in the intervention group = 25 (20.5%) iii. Smoking reduced the risk of heart disease by 17.2% units. P-value < 0.05, results are statistically significant, therefore, we reject the null hypothesis. |
Question 5 [8 marks]
While smoking is a known risk factor of heart disease, its connection to blood pressure is still being investigated. Therefore, as a secondary aim, the investigators of the HEART trial were interested in examining whether abstinence from smoking would lead to low blood pressure.
Imagine you are a consultant biostatistician at the University of Melbourne, collaborating with the study investigators of the HEART trial on providing statistical support to the design and analysis of the study.
At the time of designing the study, the investigators came across a similar smoking cessation trial conducted on a similar patient population by Puddey et al. (Journal of Chronic Diseases, 1985)a, investigating the effects of a smoking cessation programme on systolic blood pressure over a 6-week period. Puddeyet al. (1985) concluded the following:
“We conclude that although stopping smoking affects several factors which may potentially influence blood pressure, this does not result in any significant change in blood pressure over a 6-week period. Concern that advice to patients to cease smoking may lead to a prompt increase in blood pressure appears unnecessary.”
a Puddey IB, Vandongen R, Beilin LJ, English DR, Ukich AW. The effect of stopping smoking on blood pressure--a controlled trial. Journal of Chronic Diseases. 1985;38(6):483-93.
Upon having a look at the data briefly, a study investigator has told the research team that the results of the HEART trial reflect the conclusions made by Puddey et al. (1985). Quantify and interpret the association between smoking and blood pressure using data from the HEART trial, and comment on whether or not you agree with the study investigator’sclaim. [8 marks]
Question 6 [5 marks]
Provide a copy of your Stata do-file for performing the statistical analyses for this Assignment, both sections A and B. Do not upload a second file when submitting your assignment, instead copy and paste all the commands from yourStata do-file to your assignment word document prior to converting to PDF.
Important
For this assignment we have only considered the univariable or the unadjusted associations between the exposure and outcome. There may be other factors (e.g., age, sex) associated with both the exposure and the outcome which may explain the associations that we observe (i.e., confounders). You will investigate how to adjust for such confounding variables in Assignment 4.