Decoding Multiple Organ Dysfunction: Biomarkers, MOD scores and Tableau-Based Analytics Part-2: Biomarkers, Analytics & Tableau-Driven MOD Insights
Updated: Jan 13
Why Biomarkers Matter in Organ Dysfunction
Biomarkers are crucial in organ dysfunction for early detection. Biomarkers can signal injury much earlier or at subclinical stage allowing timely intervention before the situation is irreversible causing damages to the organs. Biomarkers help identify patient's specific 'endotype' which helps determine the target therapies which are most effective in improving outcomes rather than wrong treatments and wastage of time. Monitoring of biomarkers helps clinicians to check patients response to medications. For example, monitoring procalcitonin (PCT) levels can help determine if the duration of antibiotic treatment can be safely shortened.
Figure: Importance of Biomarkers
Biomarkers provide valuable information for predicting severe outcomes such as progression of Multi organ failure or death. Ultimately, this information helps clinicians in making crucial decisions like level of care to be provided (ICU admission). Many promising biomarkers can be detected through blood tests and urine tests which provides valuable information. Biomarkers act as early warning signals as they are objective, measurable indicators of any changes before occurrence of any symptoms hence acting as a crucial bridge between exposure and clinical illness. Every patient responds to treatments differently. By analyzing a patient's unique biomarker profile, healthcare practitioners can tailor therapies to be most effective for that individual, leading to timely and effective interventions.
Organ-wise Biomarkers Overview and Defining Abnormal Clinical thresholds
Heart (Cardiac)
Heart biomarkers are crucial for accessing normal heart functioning and injuries to the muscles of heart if any.
Troponin- Its a protein complex in heart and skeletal muscles. Highly sensitive marker responsible for contraction. Cardiac specific troponins (I and T) are key biomarkers for heart damage, heart attacks as they get released in our bloodstreams which heart muscle cells die. The reference ranges for the troponin test, according to the American Board of Internal Medicine, are measured in nanograms per milliliter (ng/mL). They are:
Troponin I: 0 - 0.04 ng/mL- (Troponin level above 0.04 ng/mL is considered abnormal)
Troponin T: 0 - 0.01 ng/mL
Creatine- While less specific than troponin, these can also indicate muscle damage, including cardiac muscle injury.
Liver (Hepatic)
Liver biomarkers help evaluate liver functioning.
Alanine Aminotransferase (ALT) and Aspartate Aminotransferase (AST) - These are the enzymes whose elevated level indicates liver cell damage or inflammation (hepatitis).
Alkaline Phosphatase (ALP) and Bilirubin- accesses liver metabolism.
Abnormal ranges for AST (10-40 U/L), Alkaline Phosphatase (ALP, 30-120 U/L), and Bilirubin (0.3-1.2 mg/dL). These ranges can vary by lab to lab, but generally, levels above these indicate liver issues. Elevations pointing to conditions like hepatitis, cholestasis (high ALP/GGT/Bilirubin), or damage to the muscles (high AST).
Kidney (Renal)
Kidney biomarkers assess filtration and injury.
Serum Creatinine- its elevated levels may indicate impaired kidney function.
Male: 0.74 - 1.35 mg/dL Female: 0.59 - 1.04 mg/dL (High levels may indicate reduced kidney function) Muscle mass and age are influential factors for these levels.
Blood Urea Nitrogen (BUN)- Used for accessing Kidney function and hydration status. 6-24 mg/dL.
Lungs (Respiratory)
Lung biomarkers are molecules found in the blood, other bodily fluids, or tissues that can indicate abnormal bodily processes, conditions, or diseases, particularly lung cancer and other pulmonary diseases. An "abnormal range" for these biomarkers means levels are higher or lower than in healthy individuals.
Let us explore on how patient biometric data from the dataset can be analyzed to identify Multiorgan dysfunction and understand how early recognition can change outcomes essential for clinicians, researchers, and healthcare analysts. To briefly understand how abnormal range of biomarkers can lead to organ disfunction we will use the Dataset1.csv that contains Clinical Data. Load the dataset into Tableau (Public/Desktop). Then, we create the calculated fields to determine the organ specific organ dysfunction flag.
Organ-Wise Tableau Calculations
Heart Organ dysfunction flag- HEART organ dysfunction flag based on Troponin and gender adjusted Creatinine.
IF
{ FIXED [Patient ID] :
MAX(
IF [Troponin I] > 0.04 THEN 1 ELSE 0 END
IF [Gender] = 0 THEN
IF [Creatinine] < 0.6 OR [Creatinine] > 1.1 THEN 1 ELSE 0 END
ELSE
IF [Creatinine] < 0.7 OR [Creatinine] > 1.3 THEN 1 ELSE 0 END
END
)
} >= 1
THEN 1 ELSE 0 ENDFor each patient in our dataset tableau checks- Troponin >0.04 (Myocardial Injury) and Creatinine Female (0.6-1.1), Creatinine Male (0.7-1.3) - Cardio- Renal dysfunction. Any one of the biomarkers goes abnormal, HEART organ is considered dysfunctional.
Kidney organ dysfunction Flag-
ELSEIF { FIXED [Patient ID] : MAX(
IF [Potassium]<3.5 OR [Potassium]>5.2 THEN 1 ELSE 0 END +
IF [Chloride]<96 OR [Chloride] > 106 THEN 1 ELSE 0 END +
IF [Calcium] < 8.6 OR [Calcium]>10.3 THEN 1 ELSE 0 END +
IF [Gender] = 0 THEN
IF [BUN] < 6 OR [BUN]>21 THEN 1 ELSE 0 END
ELSE
IF [BUN] < 8 OR [BUN]>24 THEN 1 ELSE 0 END
END +
IF [Gender] = 0 THEN
IF [Creatinine] < 0.6 OR [Creatinine] > 1.1 THEN 1 ELSE 0 END
ELSE
IF [Creatinine] < 0.7 OR [Creatinine] > 1.3 THEN 1 ELSE 0 END
END +
IF [Glucose] > 140 THEN 1 ELSE 0 END
)} >= 1 THEN 'KIDNEY'We have included 4 Renal functions to calculate kidney dysfunction. Creatinine is responsible for filtration, BUN clears nitrogen, Potassium, Chloride and calcium are responsible for maintaining electrolyte balance and glucose regulates metabolism. These Biomarkers detects pre-renal shock, sepsis induced AKI and dialysis level metabolic failure. The calculated field helps early detection of kidney failure when K rises, Ca drops, BUN climbs and glucose levels spikes.
Liver Organ dysfunction flag-
ELSEIF { FIXED [Patient ID] : MAX(
IF [AST] <10 OR AST > 40 THEN 1 ELSE 0 END +
IF [Alkalinephos] <44 OR [Alkalinephos] > 147 THEN 1 ELSE 0 END +
IF [Bilirubin total] >= 1.2 THEN 1 ELSE 0 END +
IF [Bilirubin direct] > 0.3 THEN 1 ELSE 0 END
)} >= 1 THEN 'LIVER' We tried capturing 3 dimensions of hepatic dysfunction. AST responsible for Hepatocyte injury represents dying cells. Alkaline phosphatase regulates biliary flow, total bilirubin responsible for detox and clearance, direct bilirubin takes care of conjugation and excretion.
Lung Organ dysfunction flag-
ELSEIF { FIXED [Patient ID] : MAX(
IF [P H] < 7.35 OR [P H] > 7.45 THEN 1 ELSE 0 END +
IF [Base Excess] < -2 OR [Base Excess] > 2 THEN 1 ELSE 0 END +
IF [FiO2] < .21 THEN 1 ELSE 0 END +
IF [SaO2] <95 OR [SaO2]>99 THEN 1 ELSE 0 END +
IF [PaCO2] < 38 OR [PaCO2] > 42 THEN 1 ELSE 0 END +
IF [Resp] < 12 OR [Resp] > 20 THEN 1 ELSE 0 END
)} >= 1 THEN 'LUNG' ENDIt flags a patient as lung dysfunction if any respiratory biomarker is abnormal. PH and Base Excess is responsible for respiratory and metabolic arrangements. PaCO2 and respiratory rate flagged due to CO2 retention and distress. FiO2 and SaO2 are flagged due to Hypoxia.
Organs | Flag |
Heart | Troponin, BP, Lactate |
Kidney | Creatinine and Urine |
Liver | Bilirubin, AST |
Lung | PH, PaCO2,SaO2, FiO2, RR |
Table: Organ dysfunction flag biomarkers (Table credits- Author)
Tableau Visualizations
Created a calculated field named Organ dysfunction using above mentioned organ wise dysfunction flags. Drag Organ dysfunction under column. Drag patient ID to rows and convert it into distinct Count CNTD (Patient ID). Filter Organ dysfunction and CNTD(Patient ID) to remove null values. Under marks- from the dropdown select shapes and drag organ dysfunction to shapes. You will be able to provide different shapes to each organ by double-clicking the shapes option under marks. Drag Patient ID to label and convert it into distinct count- CNTD(Patient ID). converted to - % of total distinct count of patient ID along table (across) to show percentage of patients with dysfunction in regards to each organ. In tableau desktop you can give organ specific images to the respective organs to make it visually appealing. Visualization shown below:
Image: Multi-organ Dysfunction (Image credit- Author)
Key Insights-
Heart involvement accounts for 51.9% of patients in our dataset . This indicates cardiac dysfunction is the primary contributor to multi-organ dysfunction in this population. Kidney dysfunction is the second leading contributor indicating Renal involvement affects 34.5% of patients. Highlights the strong role of kidney failure in systemic illness and MOD progression. Analysis emphasizes the need for early cardiac and renal monitoring.
Conclusion
Multi-organ dysfunction syndrome (MODS) is not a single disease rather its a dynamic, data-driven process in which organ systems fail due to systemic inflammation, hypoxia and metabolic derangement. From part1 and part2 we demonstrated how combining clinical scoring systems with biomarker-driven analytics transforms MOD from clinical concept into measurable, trackable and predictable condition.
In part1, MOD score provided a global severity framework. With the application of MOD scoring system to our dataset in tableau we showed that the patient population is heavily skewed towards moderate-to-severe organ dysfunction with large portion of patients with high predicted mortality risk, making MODS as a dominant feature in critically ill patients.
In part2, biomarkers reveled how and why these scores arise. Using objective laboratory thresholds (Troponin, Creatinine, Bilirubin, ABGs, electrolytes, etc.), we converted raw clinical data into real-time organ dysfunction flags. This helped us identify which organs were failing first, which were most commonly involved, and how dysfunction spreads across systems. The finding that cardiac and renal systems were the most frequently affected provided crucial insight.
Together, these two layers—MOD scores (severity) and biomarkers (mechanism)—form a powerful, integrated framework. MOD scores tell us how sick a patient is. Biomarkers tell us why. By combining both these studies into tableau calculations and dashboard clinicians and Analysts can-
i) Detect organ failure
ii) Identify high risk patients sooner
iii) Track progression hour-by-hour
iv) Effectively allocate ICU resources
Ultimately, we can conclude MODS is a race against time- Earlier we recognize the dysfunction greater chances of survival. By combining clinical science with data analytics, turns MODS from a silent killer to a visible, quantifiable and actionable condition giving healthcare teams clear insights they need to intervene before occurrence of irreversible organ dysfunction condition.
