I now have comprehensive content from Park's and Henry's for all four topics. Let me compile the complete, well-structured answer.
1. Screening for Disease
Definition
Screening has been defined as:
"The search for unrecognized disease or defect by means of rapidly applied tests, examinations or other procedures in apparently healthy individuals."
- Park's Textbook of Preventive and Social Medicine
It is the active search for disease among apparently healthy people and is considered a fundamental aspect of prevention. Screening differs from the periodic health examination in that it is:
- Capable of wide application
- Relatively inexpensive
- Requires little physician time (a technician can administer the test; the physician interprets it)
Screening also differs from diagnosis - a screening test is NOT a diagnostic test. It is only an initial examination. Those with positive results are referred for further diagnostic workup and treatment.
Types of Screening
Three types of screening are described (Park's Textbook of Preventive and Social Medicine):
a. Mass Screening
- Screening of a whole population or large subgroup irrespective of individual risk level
- Example: Chest X-ray for tuberculosis in an entire community
- Limitation: Indiscriminate mass screening has little justification unless backed by suitable treatment that reduces the duration or alters the outcome of illness. Evidence has shown mass screening does not always reduce mortality and can increase cost without observable benefit.
b. High-Risk (Selective) Screening
- Applied selectively to groups defined as high-risk based on epidemiological research
- More productive and economical than mass screening
- Examples:
- Screening for cervical cancer in lower socioeconomic groups (higher incidence)
- Screening family members of diabetic or hypertensive patients
- Screening for elevated serum cholesterol in those with family history of coronary heart disease
- Epidemiologists have extended this concept to screening for risk factors (e.g., elevated blood pressure, raised serum cholesterol) which antedate actual disease
c. Multiphasic Screening
- Application of two or more screening tests in combination to a large number of people at one time
- May include: health questionnaire, clinical examination, blood/urine chemistry, lung function tests, audiometry, visual acuity measurement
- Example: Combined HIV + syphilis + hepatitis B screening at a single visit
- Limitation: Randomized controlled studies in the UK and USA showed multiphasic screening has NOT shown benefit in mortality or morbidity reduction; it has increased costs. Most tests in multiphasic screening programmes have not been validated individually.
Uses of Screening
Four main uses have been described (Park's Textbook of Preventive and Social Medicine):
a. Case Detection (Prescriptive Screening)
- Presumptive identification of unrecognized disease, not arising from the patient's request
- People are screened primarily for their own benefit
- Examples: Neonatal PKU screening, bacteriuria in pregnancy, breast cancer screening, diabetes mellitus detection
- Since disease detection is initiated by medical/public health personnel, they carry special obligation to ensure early treatment is started
b. Control of Disease
- Screening aimed at interrupting transmission of communicable diseases
- Example: Contact tracing and screening in tuberculosis, STI screening, screening blood donors for HIV/hepatitis
c. Research
- Screening used for epidemiological research purposes
- Establishes prevalence of disease/risk factors in a community
- Generates data to guide public health policy
d. Educational Opportunities
- Screening programmes (e.g., for diabetes) provide opportunities for creating public awareness and educating health professionals about disease
Criteria for Selection of Disease (Wilson-Jungner WHO Criteria)
The WHO criteria for screening, originally proposed by Wilson and Jungner (1968), remain the standard (Tietz Textbook of Laboratory Medicine, 7th Edition):
Criteria related to the DISEASE:
- The condition should be an important health problem (significant morbidity/mortality)
- There should be a recognizable latent or early symptomatic stage
- The natural history of the condition should be adequately understood
- The condition should have a detectable preclinical phase (a "lead time")
Criteria related to TREATMENT:
5. There should be an accepted and effective treatment for patients with recognized disease
6. Early intervention should be of more benefit than treatment started at a later stage
7. There should be appropriate facilities for diagnosis and treatment
8. There should be an agreed policy on whom to treat
Criteria related to the TEST:
9. The screening test should be suitable - simple, safe, rapid, and acceptable to the population
10. High sensitivity and specificity of the test are essential
11. The distribution of test values in the target population should be known, and a suitable cutoff defined
Criteria related to COST:
12. The cost of case-finding (including diagnosis and treatment) should be economically balanced in relation to possible expenditure on medical care as a whole
13. Case-finding should be a continuing process, not a "once and for all" project
Criteria for Selection of the Screening Test
A good screening test should be:
| Criterion | Explanation |
|---|
| Sensitivity | High - must detect most true cases (low false negatives) |
| Specificity | Reasonably high - avoid too many false positives |
| Simple | Easy to perform, can be done by technicians |
| Safe | No significant risk to the subject |
| Acceptable | Acceptable to the population being screened |
| Inexpensive | Low cost per test |
| Rapid | Results available quickly |
| Reliable | Consistent results on repeat testing (reproducible) |
| Valid | Measures what it is intended to measure |
2. Levels of Prevention
Prevention is defined in terms of four levels, corresponding to the natural history of disease (Park's Textbook of Preventive and Social Medicine, p. 52-53):
Level 0: Primordial Prevention
Definition: Prevention of the emergence or development of risk factors in countries or population groups in which they have not yet appeared.
- This is primary prevention in its purest sense
- Many adult diseases (obesity, hypertension, coronary artery disease) have early origins in childhood, when lifestyles are formed
- Main intervention: Individual and mass education
- Target: Children and young people, before harmful lifestyles are adopted
- Examples:
- Discouraging children from smoking before the habit forms
- National dietary guidelines to prevent obesity in a population where it is not yet prevalent
- Promoting physical activity in school curricula
Level 1: Primary Prevention
Definition:
"Action taken prior to the onset of disease, which removes the possibility that a disease will ever occur."
- Intervenes in the pre-pathogenesis phase
- Concerned with the concept of "positive health" - enabling individuals to lead socially and economically productive lives
- Two main approaches:
- Population (mass) strategy: Directed at the whole population to reduce average risk (e.g., reducing average blood pressure by reducing salt in food supply)
- High-risk strategy: Targets individuals at special risk identified by clinical methods
Examples:
- Immunization against polio, measles, tetanus
- Oral rehydration therapy promotion
- Fluoridation of water supply (prevents dental caries)
- Use of condoms (prevents HIV/STIs)
- Antismoking campaigns
- Safe food, water, and sanitation
Level 2: Secondary Prevention
Definition:
"Action which halts the progress of a disease at its incipient stage and prevents complications."
- Specific interventions: early diagnosis (screening tests, case-finding) + adequate treatment
- Attempts to arrest the disease process before irreversible pathological changes occur
- Also reduces communicability of infectious diseases
Examples:
- Pap smear for early detection of cervical cancer
- Blood pressure measurement to detect hypertension
- Mammography for early breast cancer
- Blood glucose testing for diabetes
- Chest X-ray/Mantoux test for early tuberculosis
- Treating hypertension before a stroke occurs
Limitation: The patient has already suffered mental anguish, physical pain, and the community has already lost productivity. More expensive and less effective than primary prevention in the long run.
Level 3: Tertiary Prevention
Definition:
"All measures available to reduce or limit impairments and disabilities, minimize suffering caused by existing departures from good health and to promote the patient's adjustment to irremediable conditions."
- Intervenes in the late pathogenesis phase
- Includes both treatment of established disease (to prevent further sequelae) and rehabilitation
- Modern rehabilitation includes psychosocial, vocational, and medical components
Examples:
- Physiotherapy after a stroke to reduce disability
- Prosthetic limbs after amputation in a diabetic patient
- Colostomy care after colorectal cancer surgery
- Psychiatric rehabilitation for chronic schizophrenia
- Vocational retraining after spinal cord injury
Summary Table: Levels of Prevention
| Level | Target | Phase | Intervention Examples |
|---|
| Primordial | Risk factors not yet present | Before risk factors emerge | Health education, lifestyle promotion |
| Primary | Healthy individuals | Pre-pathogenesis | Vaccination, sanitation, health promotion |
| Secondary | Early/subclinical disease | Early pathogenesis | Screening, early diagnosis, prompt treatment |
| Tertiary | Established disease with complications | Late pathogenesis | Treatment, rehabilitation, disability limitation |
3. Sensitivity and Specificity of a Screening Test
(Henry's Clinical Diagnosis and Management by Laboratory Methods)
These are the two most important measures of a test's diagnostic accuracy. They measure a test's ability to distinguish between disease and absence of disease at a chosen cutoff value.
The 2×2 Contingency Table
All calculations are based on this table:
| Disease Present | Disease Absent | Total |
|---|
| Test Positive | True Positive (TP) | False Positive (FP) | TP + FP |
| Test Negative | False Negative (FN) | True Negative (TN) | FN + TN |
| Total | TP + FN | FP + TN | All |
Sensitivity
Definition: The ability of a test to detect disease - the proportion of persons WITH disease in whom the test is positive.
$$\text{Sensitivity} = \frac{TP}{TP + FN} \times 100%$$
- Also called the True Positive Rate
- Its inverse (1 - Sensitivity) = False Negative Rate
- A test with 90% sensitivity: correctly identifies 90 out of 100 diseased patients; misses 10 (false negatives)
- High sensitivity = few false negatives
- A highly sensitive test is used to rule OUT disease (mnemonic: SnNOut - Sensitive test, Negative result, rules Out)
When is high sensitivity needed?
When the consequence of missing a case is serious (e.g., HIV screening, cancer screening). A low threshold is used - many false positives are accepted to capture all true cases.
Specificity
Definition: The ability of a test to detect the absence of disease - the proportion of persons WITHOUT disease in whom the test is negative.
$$\text{Specificity} = \frac{TN}{TN + FP} \times 100%$$
- Also called the True Negative Rate
- Its inverse (1 - Specificity) = False Positive Rate
- A test with 90% specificity: correctly identifies 90 out of 100 disease-free patients as negative; 10 are falsely called positive
- High specificity = few false positives
- A highly specific test is used to rule IN disease (mnemonic: SpPIn - Specific test, Positive result, rules In)
When is high specificity needed?
When initiating toxic, costly, or irreversible treatment based on the test result - you need confidence that the positive result truly indicates disease.
Worked Example (Henry's Clinical Diagnosis, p. 119):
200 AMI patients and 200 healthy controls are tested with a cardiac marker:
| Disease (AMI) | No Disease | Total |
|---|
| Test Positive | 196 (TP) | 20 (FP) | 216 |
| Test Negative | 4 (FN) | 180 (TN) | 184 |
| Total | 200 | 200 | 400 |
- Sensitivity = 196/(196+4) × 100 = 98%
- Specificity = 180/(180+20) × 100 = 90%
- Positive Predictive Value (PPV) = 196/(196+20) × 100 = 91%
- Negative Predictive Value (NPV) = 180/(180+4) × 100 = 98%
Sensitivity-Specificity Trade-off
There is an inverse relationship between sensitivity and specificity when the cutoff is altered:
- Lowering the cutoff → Increases sensitivity (catches more true cases) but decreases specificity (more false positives)
- Raising the cutoff → Increases specificity (fewer false positives) but decreases sensitivity (more false negatives)
This is because the distributions of test values in diseased and non-diseased populations overlap. The ideal test has no overlap; in practice, the cutoff is set to minimize the more harmful type of error.
Predictive Values (Affected by Prevalence)
| Value | Formula | Meaning |
|---|
| PPV | TP/(TP+FP) | Probability that a positive test truly has disease |
| NPV | TN/(TN+FN) | Probability that a negative test truly lacks disease |
PPV increases with higher disease prevalence - the same test performs better (fewer false positives relative to true positives) in a high-prevalence population. This is why a test ideal for a high-risk group may perform poorly when applied to the general population.
4. Difference Between Screening Test and Diagnostic Test
(Park's Textbook of Preventive and Social Medicine - Table 1)
| Feature | Screening Test | Diagnostic Test |
|---|
| Population | Done on apparently healthy individuals | Done on those with symptoms, signs, or indications |
| Scope | Applied to groups | Applied to individual patients; all diseases considered |
| Purpose | Identify suspects who need further evaluation | Confirm or refute the presence of disease |
| Accuracy | Less accurate - a presumptive test | More accurate - uses full clinical evaluation |
| Cost | Less expensive | More expensive |
| Basis for treatment | NOT a basis for treatment - positive result requires follow-up | Used as basis for treatment |
| Finality | Results are relatively fixed based on a single cutoff | Diagnosis is modified in light of new evidence; sum of all clinical evidence |
| Number of criteria | Based on one criterion or cutoff point | Based on evaluation of multiple symptoms, signs, and lab findings |
| Initiative | Comes from the investigator or public health agency | Comes from the patient presenting with a complaint |
Key principle: A positive screening test does NOT mean the person has the disease - it only means they are suspects who require diagnostic testing. A positive diagnostic test IS the basis for treatment.
Note: These criteria are not absolute - some tests (e.g., glucose tolerance test, haemoglobin for anaemia) serve both screening and diagnostic purposes depending on context.
Sources: Park's Textbook of Preventive and Social Medicine; Henry's Clinical Diagnosis and Management by Laboratory Methods; Tietz Textbook of Laboratory Medicine, 7th Edition; Harrison's Principles of Internal Medicine, 22nd Edition