Biomedical Research

Artificial Intelligence in Medicine

Artificial intelligence in medical practice is the use of computer techniques to perform clinical diagnoses and suggest treatments in medical areas [1]. It has the capability of detecting meaningful relationships in a data set and could be used for the diagnosis, treatment, and for coming to a particular conclusion. Similar to the way doctors are educated through years of medical schooling and learning from mistakes, artificial intelligence algorithms learn to do the same job as a doctor. They perform tasks requiring human intelligence like pattern and speech recognition, image analysis, and decision making. The Artificial Intelligence algorithm includes feeding data in the computer system, which are structured having a label recognizable to the algorithm, performance is analyzed just like exams give an analysis of a medical student’s performance thus giving results. Based on the results of this analysis the algorithm can be modified, fed more data, or rolled out for the decision-making of the person writing the algorithm [2].

Fig: AI algorithm learning the basic anatomy of a hand and can recreate where a missing digit should be. This could allow physicians to see the proper place to reconstruct a limb/put a prosthetic.

These performances and results are tested with a physician’s performance to determine its clinical ability and value. In medicine language, it includes input data based upon numericals such as Heart Rate or Blood Pressure and based upon images such as Magnetic Resonance Imaging Scans or Images of Biopsy Tissue Samples. The algorithms from this data could be a probability or a classification. The result of the above example could be the probability of having an arterial clot according to the heart rate and blood pressure data or the labeling of an imaged tissue sample by classifying it as cancerous or non-cancerous. There are two recent applications in the Artificial Intelligence of clinical and accurate algorithms benefiting both patient and doctor for the diagnosis. One is the algorithm researchers at Seoul National University Hospital and College of Medicine developed called Deep Learning-based Automatic Detection to analyze chest radiographs and detect abnormal cell growth (cancers). The results were compared to many physician’s detection abilities and were found to perform better than the doctors [2].

Fig: Artificial Intelligence Algorithm. Left panel showing the image fed into an algorithm. The right panel shows a region of potentially dangerous cells, as identified by an algorithm, that a physician should look at more closely.

Fig: Artificial Intelligence algorithm; Deep Learning Method.The left panel shows the original X-ray. The right panel shows the X-ray with orange color indicating signs of pneumothorax which could be unnoticed by radiologists

The second algorithm was developed by researchers at Google AI Healthcare called Lymph Node Assistant which analyzed histology slides stained tissue samples to identify metastatic breast cancer tumors from lymph node biopsies. It could identify suspicious regions of the sample which could not be distinguished with the human eye. It was proven to accurately classify a cancer as cancerous or non-cancerous in 99% of the cases. Hence these algorithms could help doctors with correct diagnosis thus allowing them to invest time in solving cases that computers cannot solve [2].

Fig: AI algorithm; Lymph node biopsy

Artificial intelligence could be considered a boon as it may help for early diagnosis of diseases whose later diagnosis can cause delays in the treatment and may be harmful to the patient. For example, researchers have claimed that it could be used to diagnose Alzheimer’s disease years before symptoms appear. The computers can be trained for brain scans to be able to spot subtle signs of dementia that could be missed by humans allowing early diagnosis. This could probably be done using 18-F-fluorodeoxyglucose positron emission tomography (FDG-PET). In an FDG-PET scan FDG, a radioactive glucose compound is injected into the blood. PET scans can then measure the uptake of FDG in brain cells, an indicator of metabolic activity. Through Deep Learning, the algorithm can teach itself metabolic patterns that correspond to Alzheimer’s disease.If one can detect the symptoms earlier, it would help investigators to find better ways to reduce or halt the disease process. Future research should take into consideration, training the deep learning algorithm to look for patterns associated with the accumulation of beta-amyloid and tau proteins, abnormal protein clumps, and tangles in the brain that are markers specific to Alzheimer’s disease, according to UCSF’s Youngho Seo, Ph.D., which can add another dimension to using Artificial Intelligence in Alzheimer’s disease detection [3].

Fig: Fluorine 18 fluorodeoxyglucose PET images from Alzheimer’s Disease Neuroimaging Initiative set preprocessed with the grid method for Alzheimer disease patient

Artificial Intelligence has many clinical applications to improve patient care and potentially save lives. Maintaining medical records and past history is the first step in health care where robots collect, store, reformat, and trace data to provide faster and more consistent access. They also analyze data including notes and reports from a patient’s file and clinical expertise to help to choose the right treatment pathway [5].There are some latest tools and technology developed in the health care sector based on the Artificial Intelligence algorithm. This includes: MelaFind, which is a tool that does not involve introduction of instruments into the body and gives extra information to dermatologists in early detection and recognition of skin cancer,lesions and helps in it’s examination. It also helps in evaluation of skin lesions up to 2.5 mm beneath the skin. By using Artificial Intelligence based algorithms, dermatologists can analyze irregular moles and diagnose serious skin cancers such as melanoma. The device demonstrated 98.3% sensitivity by correctly identifying 172 out of 175 melanomas and high-grade lesions. Robotic-assisted therapy is used in neurological patients and is specially used for stroke patients’ recovery. The robotic arm and hand use digital algorithms to detect motions that patients cannot execute during therapy thus improving their performance per hour than they would have if worked with a physical therapist alone thus allowing speedy recover[4].Robots can also perform tests, x-rays, CT scans, data entry, and other tasks faster and more accurately. Cardiology and Radiology are two fields where the amount of data to analyze is huge and time-consuming. Future cardiologists and radiologists should look only at the most critical cases in which human monitoring is useful [5]. Caption Guidance, which is an Artificial Intelligence guided ultrasound platform or software capable of instructing clinicians on obtaining a clearer picture of the heart in motion. It will be used for capturing echocardiographic images of the patient’s heart without special training, spotting high-quality 2D heart images, and automatically recording video clips for later analysis, while calculating heart function measures thus improving the diagnosis of heart diseases [4].

Fig: AI tools in health care

Conclusion: Artificial Intelligence will surely improve the healthcare industry, from predictive medical care and more accurate diagnosis to motivating the patients to take care of their health. It will certainly continue enhancing the patient’s experience and healthcare expertise in general. The use of Artificial Intelligence is predicted to decrease medical costs as there will be more accuracy in diagnosis and better predictions in the treatment plan as well as more prevention of disease. It will not replace healthcare workers but instead allow them to spend more time for the bedside care of their patients, resulting in the greater outcomes for all.


[1]Chan, Y., Chen, Y., Pham, T., Chang, W., & Hsieh, M. (2018, July 15). Artificial Intelligence in Medical Applications. Retrieved September 13, 2020, from

[2]Says:, A., Says:, D., Says:, J., Says:, T., Says:, C., Says:, B., . . . *, N. (2019, June 19). Artificial Intelligence in Medicine: Applications, implications, and limitations. Retrieved September 13, 2020, from

[3]Staff, S. (2018, November 06). Artificial intelligence predicts Alzheimer’s years before diagnosis. Retrieved September 13, 2020, from

[4]Swetha. (2019, November 28). 10 Common Applications of Artificial Intelligence in Health Care. Retrieved September 13, 2020, from

[5]Micah Castelo Micah Castelo is a web editor for EdTech: Focus on K-12 and a regular contributor for HealthTech. Her experience includes education and community news coverage for the Syracuse Post-Standard and international news reporting. (2019, May 01). The Future of Artificial Intelligence in Healthcare. Retrieved September 13, 2020, from

Pratiksha Baliga, Youth Medical Journal 2020


The Impact of COVID-19 on Pre-Diabetic Patients


The COVID-19 pandemic is taking a great toll globally. To control the situation effectively, measures to lower the death rate have to be taken. Doctors have already stated that people with comorbidities like diabetes are at a higher risk of getting severe symptoms of COVID-19 infection.

Increase in Risk

The fluid and electrolyte balance of the body is maintained with the help of the renin-angiotensin system. When a person complains of low blood pressure, the renin (present in the kidney) forms angiotensin I by breaking down the enzyme angiotensinogen. Angiotensin-converting enzyme(ACE) converts angiotensin I into angiotensin II to activate it.
This Angiotensin-converting enzyme (usually present on the lungs, kidney, and heart) binds to the Angiotensin-converting enzyme receptors and squeezes the blood vessels, thus raising the blood pressure of the body. Then the Angiotensin-converting enzyme-2 (ACE-2) breaks down the angiotensin II into molecules that neutralize its harmful effects.

SARS-CoV-2 has a high affinity for ACE-2 receptors present on the surface of healthy cells. Thus it attaches itself to the ACE-2 and attacks the lungs, kidney, and heart.
The levels of ACE-2 increase in a diabetic person (a condition with high blood glucose levels, hyperglycemia) allowing the virus to attack the organs of the diabetic person more disastrously. Acute hyperglycemia upregulates ACE-2 expression on cells which might facilitate viral cell entry. Chronic hyperglycemia downregulates ACE-2 expression making the cells vulnerable to the inflammatory and damaging effects of the virus.

Link Between COVID-19 and Diabetes

COVID-19 is an acute respiratory infection caused by a coronavirus named Severe Acute Respiratory Syndrome Coronavirus 2 (SARS-CoV-2) and is spread through air droplets or close contact with an infected person. Often older people(above 65 years of age) & people with pre-existing diabetic conditions are affected.

The risk of a fatal outcome from COVID-19 is up to 50% higher in patients with diabetes. When diabetic patients develop a viral infection it can increase inflammation and the treatment is hard because of fluctuations in blood glucose levels and the presence of diabetic complications. This is because of the compromised immune systems making it difficult to fight with the virus leading to a longer recovery period.

Linked Complications & Risk Factors

Complications like Acute respiratory distress syndrome (ARDS) & multi-organ failure are prevalent in prediabetic Covid-19 patients. It involves the lower respiratory tract which can offset pneumonia, rapidly progressing to ARDS associated with multi-organ failure.
Acute respiratory distress syndrome (ARDS) is a severe lung condition causing fluid accumulation in the alveoli, progressive fibrosis which comprises the gas exchange. The type 1 & 2 pneumocytes lining the alveoli become dysfunctional leading to a decrease in surfactant levels & the ability of lungs to expand causing Sepsis (a serious infection which causes the immune system to attack the body) and Severe pneumonia (Pus collection in air sacs).

COVID-19 prediabetic patients have direct viral invasion which causes functional immune deficiency and directly reduces immune cell function. This leads to diminished bactericidal clearance, increased infectious complications, and protracted sepsis mortality. Thus they may develop pneumonia leading to sepsis.
SARS-CoV-2 infects the upper respiratory tract & circulating immune cells (CD3, CD4, and CD8 T cells) inducing lymphocyte apoptosis with elevated inflammatory biomarkers such as C-reactive protein, serum ferritin, and IL-6. The T cells inhibit the overactivation of innate immunity resulting in lymphocytopenia, which suppresses the innate immune system and enhances the cytokine secretion resulting in a cytokine storm causing a multi-organ failure.

Body mass index (BMI) in obesity of 30 or above increases the risk. Abdominal obesity is associated with a higher risk involving abnormal secretions of adipokines and cytokines like TNF-alpha and interferon which may induce an impaired immune response. Obese people also experience mechanical respiratory problems, with reduced ventilation of the basal lung sections increasing the risk of pneumonia.

If a person with diabetes has a fever from COVID-19, they lose additional fluids. This can lead to dehydration, which may require intravenous fluids.

Diabetes damages arteries with fatty material deposition on their inner walls (atherosclerosis) which can cause Hypertension. Arterial hypertension is also highly prevalent in Covid19 patients due to the use of ACE inhibitors since SARS-CoV-2 binds to ACE2 to enter target cells. ACE inhibitors and angiotensin receptor blockers increase the expression of ACE2 which facilitates target organ infection and promote the progression of the disease.

Management of Diabetes in Patients with COVID-19

In COVID-19 the endothelial dysfunction associated with hypoxia causes intravascular disseminated coagulation. It involves the formation of abnormal clumps of thickened blood clots inside the blood vessels, leading to massive bleeding in other places causing inflammation & infection. Diabetes is associated with a pro-thrombotic state, which plays a key role in blood clotting with an imbalance between clotting factors and fibrinolysis. Pre-Diabetic patients with COVID-19 have a longer prothrombin time and higher concentrations of D-dimer(a small protein fragment in the blood after a blood clot). Other risk factors such as obesity, older age, and being admitted to the hospital could increase the pro-coagulative state and the risk of thrombotic complications.

Diabetes causes disturbance of glucose homeostasis and worsening of hyperglycemia(a characteristic of Diabetic Ketoacidosis). In diabetic patients with Covid-19, there is a direct effect of SARS-CoV-2 binding to ACE receptors expressed in pancreatic tissue and β-cells harming the β-cell function. Therefore there is an acute loss of insulin secretory capacity, stress condition, and a cytokine storm resulting in Diabetic Ketoacidosis (DKA).

Figure 1 : Synopsis of reciprocal effects of diabetes and COVID-19

Poor glycemic control is a risk factor for serious infections but is useful in some conditions like bacterial pneumonia. To maintain optimal glycaemic control it requires frequent blood glucose monitoring and continuous change in anti-diabetic treatment after the measured glucose levels.

Pre-Diabetic patients with COVID-19 infection should have regular blood glucose monitoring and adequate glycemic control which might reduce the risk of this severe infection. Special considerations to avoid certain antihyperglycemic agents should be noted. In Type 2 diabetes, Metformin (initial drug of choice) possesses a risk of dehydration & lactic acidosis hence should be avoided in patients who have greater potential to progress to severe COVID-19. Dipeptidyl peptidase (DPP)-4 inhibitors are well tolerated & can be used as an alternative to Metformin. Sodium-glucose cotransporter-2 inhibitors have risks of dehydration & Diabetic Ketoacidosis which is one of the complications hence avoided. Similarly, Glucagon-like peptide 1 receptor (GLP-1) agonists have a risk of dehydration so patients on these medications should be closely monitored. If any anti-hyperglycemic drugs are discontinued alternate treatment is usually Insulin and it should be continued if it is already ongoing in a patient.

In type1 diabetes frequent blood glucose monitoring every 3-4hrs & adjustments of insulin dose based on blood glucose values is needed. Urine ketones along with blood glucose should be monitored if fever with hyperglycemia occurs. Systematic screening for pre-diabetes in patients with proven COVID-19 infection is advisable.


There is a bidirectional relationship between Covid-19 and diabetes. On one hand, diabetes is associated with an increased risk of severe Covid-19 while on the other hand new-onset diabetes and severe metabolic complications of preexisting diabetes, including diabetic ketoacidosis and hyperosmolar for which exceptionally high doses of insulin are warranted, have been observed in patients with Covid-19.

It is important to recognize the importance of diabetes as a vital comorbidity in patients with COVID-19. Any prediabetic patient who develops COVID-19 symptoms should contact their healthcare provider as soon as possible. Although people with diabetes are at a risk of more serious complications from COVID-19, it is possible to reduce the risk by maintaining ideal blood sugar levels and following infection prevention measures.


Ceriello, A., Stoian, A., & Rizzo, M. (2020, May). COVID-19 and diabetes management: What should be considered? Retrieved September 05, 2020, from

COVID-19 Infection in People with Diabetes. (2020, March 30). Retrieved September 05, 2020, from

Diabetic, pre-diabetic patients and those with high fasting blood sugar at higher risk of fatality due to COVID-19 – Health News , Firstpost. (2020, July 13). Retrieved September 05, 2020, from

Diabetic, pre-diabetic patients and those with high fasting blood sugar at higher risk of fatality due to COVID-19 – Health News , Firstpost. (2020, July 13). Retrieved September 05, 2020, from

Home. (n.d.). Retrieved September 05, 2020, from

N. Zhu, D., J. Hellewell, S., C. Huang, Y., W. Guan, Z., D. Wang, B., J. Yang, Y., . . . M. Shyamsundar, S. (1970, January 01). SARS-CoV-2 disease severity and diabetes: Why the connection and what is to be done? Retrieved September 05, 2020, from
S, K., H, A., & S, A. (2020, May 15).

Multi-Organ Failure in a Patient With Diabetes due to COVID-19 With Clear Lungs. Retrieved September 05, 2020, from

Pratiksha Baliga, Youth Medical Journal 2020

Health and Disease

Alport Syndrome In Women

What is Alport Syndrome?

Alport Syndrome is a genetically inherited kidney disease. It is caused by genetic mutations of the collagen IV family of proteins, which are a major part of basement membranes present in all tissues, including the kidney, inner ear, and eye. Genetic mutations of collagen IV (COL4A5 is situated on the X chromosome, while COL4A3 and COL4A4 are situated on chromosome 2) cause thinning and splitting of the glomerular basement membrane. X-linked Alport Syndrome (XLAS) is caused by mutations in the COL4A5 gene which encodes the collagen IV α5 chain . Autosomal recessive disease is caused by two mutations in trans (on different chromosomes) in the COL4A3 or COL4A4 genes, which are code for the collagen IV α3 and α4 chains, respectively. The collagen IV α3, α4, and α5 chains form a heterotrimer that is the predominant network of the basement membranes of the glomerular filter, the cochlea, cornea, lens capsule, and retina. The collagen IV heterotrimer consists of a long series of Gly-Xaa-Yaa repeats, where Gly is present at each third residue, and X and Y are often hydroxyproline and proline. This process leads to scarring throughout the kidney, and may later lead to kidney failure. It may also cause abnormalities in the ears and eyes, which can lead to vision and hearing loss.


Hematuria – Blood in urine

Abnormal urine color

Proteinuria – Large amounts of protein “spilling” into the urine

Foamy urine

Edema – Swelling in parts of the body, most noticeable around the eyes, hands and feet, and abdomen

Low Blood Albumin Levels

Flank pain

Decreased or loss of vision (more common in males)

Loss of hearing (more common in females)

High Cholesterol in some cases

High Blood Pressure in some cases

Tendency to form Blood Clots if spilling large amounts of protein

Kidney Failure (in only some cases) as the disease progresses


1)CLASSIC Alport Syndrome: X-linked syndrome with haematuria, sensorineural deafness, and conical deformation of the anterior lens surface(lenticonus)

2)X-LINKED FORMED ASSOCIATED with diffuse leiomyomatosis



Autosomal dominant and recessive forms both cause renal disease without deafness or lenticonus.


Many renal physicians think of Alport Syndrome as primarily affecting men. However, twice as many women are also affected by X-linked Alport Syndrome. The women who are affected are commonly undiagnosed. Half of their sons and daughters are also affected. Recessive inheritance is suspected when women develop early-onset renal failure or lenticonus. Their family may be consanguineous. Other generations, including parents and offspring, are not affected, and on average only one in four of their siblings inherit the disease. 

X-LINKED Alport Syndrome(XLAS):

In cases of X-linked inheritance, the genetic defect causing the disease is on the X chromosome. Since men, unlike women, have only one copy of the X chromosome, X-linked Alport Syndrome is more likely to affect men. Women with one faulty copy of the X chromosome can develop the disease, but it is usually less severe in women because their other X chromosome can compensate. Most go undiagnosed or underdiagnosed due to variations in symptom severity and course of disease progression. Between 15 and 30 % of women with XLAS develop kidney failure by the age of 60 and symptoms of hearing loss by their middle ages.


Women have two copies of the X chromosomes, but one of them is randomly turned off or inactivated during development in a process called LYONIZATION. Thus, in each cell, there is only one active X chromosome and one inactive X chromosome. Since lyonization is random in people and varies from cell to cell, the X chromosome that remains active may either be carrying the normal gene or the defective gene. Depending on the proportion of cells in which the normal X chromosome is active, the symptoms can vary from no symptoms at all to those that are quite severe.

Sometimes, X chromosome inactivation can be preferential (also called skewed X-Inactivation) and the normal X chromosome can be unfavored, resulting in most cells expressing the mutated gene. Such women can be as severely affected by XLAS as men.


X-linked Alport Syndrome is underdiagnosed or undiagnosed in women, which is observed in generational skipping. This occurs because female relatives of affected men are not systematically screened in adult nephrology practice.

A male with X-linked disease has inherited the disease from his mother in 85% of cases. On average, half of the male’s affected family include his sisters, brothers, and daughters, but none of his sons.

For females with X-linked disease, the situation is more complex since the disease can be inherited from her father or mother. If a woman inherits the disease from her father, then all of her sisters are also affected, but if she inherits the disease from her mother, then half of her sisters and half her brothers are also affected. In addition, half an affected woman’s sons and half her daughters are affected.

Clinical features of Alport Syndrome in women:

Clinical features in females depend on mutation type and “lyonization.” Lyonization produces a mosaic distribution of the mutant collagen IV α5 chain and disease in the female kidney and skin. This may result in a normal clinical phenotype (a severe or an intermediate), and the staining pattern for diagnostic testing may be confusing.

Hematuria: Nearly all females with X-linked Alport Syndrome have persistent hematuria from infancy. The presence of even short stretches of lamellation suggests Alport Syndrome.

Albuminuria: Albuminuria is not well-studied in women with Alport Syndrome. 

ESRD: 30% of all women with X-linked Alport Syndrome develop ESRD by the age of 60. Affected women should be strongly advised not to donate a kidney to an affected male relative, even when urine protein excretion is normal. This is because of their own risk of ESRD. It is important, though, to confirm genetically if the mother is actually affected because of the small chance (15%) of a de novo mutation in her son.

Autosomal recessive Alport Syndrome: It affects about one in 40,000 individuals, and is suspected in young women with renal failure and hearing loss, or lenticonus. The family may be consanguineous. Typically, the only other affected family member, if any, is a sibling. The affected woman’s parents, grandparents, and children may have hematuria and thin basement membrane nephropathy, but do not develop renal failure.


Women with Alport Syndrome should be identified at an early age once proteinuria appears.

Accurate diagnosis of Alport Syndrome in girls and women can be challenging because many affected females exhibit only microscopic haematuria and glomerular basement membrane attenuation. In such patients, family history and immunohistochemical analysis of type IV collagen expression in basement membranes of the skin or kidney may be helpful. Alport Syndrome should be suspected in women with haematuria and a positive family history of kidney failure. A negative family history for renal failure does not, however, exclude a diagnosis of Alport Syndrome. In some women with longstanding haematuria, a diagnosis of Alport Syndrome is established only after the diagnosis is made in a child. An individualized approach should be taken toward female members of Alport Syndrome whose haematuria is associated with atypical symptoms, such as dysuria or flank pain, or unexpectedly severe abnormalities of renal function, such as heavy proteinuria or azotemia at a young age.

Type IV IHC abnormalities that are distinguishing characteristics in females include-

I) Typical ARAS female-Renal basement membranes are entirely negative for the α3(IV) and α4(IV) chains, and glomerular basement membranes are completely negative for the α5(IV) chain, reflecting the failure to deposit α3α4α5(IV) trimers.

II) Bowman’s capsules, distal tubular basement membranes and EBM are positive for α5(IV) chains, because formation and deposition of α5α5α6(IV) trimers are preserved.


Renal transplantation is usually very successful in women with Alport Syndrome who progress to end-stage renal failure. Even though anti-GBM nephritis of the renal allograft occurs in about 3% of transplanted Alport males, the risk of this complication in females with XLAS should theoretically be close to zero. Women with ARAS, due to certain COL4A3 mutations, can develop anti-GBM nephritis of the allograft.

By Pratiksha Baliga (India), Youth Medical Journal

Reference sites:

“Alport Syndrome.” NephCure Kidney International,

Kashtan, Clifford E. “Alport Syndrome and the X Chromosome: Implications of a Diagnosis of Alport Syndrome in Females.” OUP Academic, Oxford University Press, 29 Mar. 2007,

Naqvi, Erum. “Alport Syndrome in Women.” Alport Syndrome News, Bionews Services, 25 Apr. 2018,

Savige, Judy, et al. “Alport Syndrome in Women and Girls.” Clinical Journal of the American Society of Nephrology : CJASN, American Society of Nephrology, 7 Sept. 2016,