How about programming empathy and compassion for animals?


“As long as you have not loved an animal, a part of its soul remains awake. ” -Anatole France.

Cancer is a kind of pandemic, which we have seen for ages. It is an epidemic that we have already accepted because of its deadly consequences.

Register for our upcoming Masterclass>>

Made: “Almost 20 million, including humans and animals, have died of cancer in the past two years. This is five times the number of people who have died from Covid-19 to date. “

The painful journey of cancer patients and their loved ones is appalling. Early detection is an essential characteristic in the case of the most complex epidemic diseases such as cancer. Therefore, early prognosis and selection of treatment protocols are key. There are some issues at the local level that actually require urgent attention (mentioned below in the mind map). Through the use of the latest technologies such as artificial intelligence, the healthcare industry could gain deeper insights from the data.

Integrating empathy with AI models and the latest technologies can expand one’s areas of knowledge and provide more advanced and advanced solutions to complex problems. Solving problems for all kinds of species, whether humans or animals, can in fact be seen as the contribution of technology to saving lives.

Looking for a job change? Let us help you.

We have seen the consequences of some epidemic diseases such as cancer, but it is now imperative to focus on them. The combination of cognitive skills and human expertise with new AI techniques can lead us to the most promising solutions for complex health problems and are adaptable to all species.

Need for AI in cancer prognosis

To explore the supporting role of AI technology in working on various aspects of cancer with medical experts, a mind map was designed to give a holistic view of the use of technology to save lives.

Mind map: The use of artificial intelligence in the field of oncology

Based on the current scenarios from the aforementioned mind map, cancer screening and diagnosis are the most crucial areas to work on. To develop an effective screening system and early diagnosis of cancer, especially for pets – since they cannot speak about symptoms or feelings verbally – observation or visual inspection plays a key role.

Generally, visual inspections can be classified into symptoms; physical appearance; and behavior change. Some of the acute symptoms which can give an early clue for a medical examination and therefore can be formulated to create an improved system for diagnostic, screening and clinical decision-making systems are: lumps (large or small); swollen lymph nodes (neck, armpits, under the thigh joints); dark colored tongue; recurrent blisters and sores; heavy panting; Extreme fatigue; increase in the number of white blood cells (laboratory variable); sudden high temperature; blood in the stool or unexpected bleeding; diarrhea; and slow healing of wounds. As for the physical appearance section, We can see red or brown rashes on the skin; dry nose; and sad or panicked facial expressions, and in behavior changes, one can keep a note on their pets being cranky, irritating, etc. (Warning: may be seen for other comorbidities)

Example of a problem statement

An AI-based solution to detect malignant or non-malignant tissue and their type in an animal’s body?

Why is an AI-based system necessary?

Manual process: According to oncologists and pathologists, the first step in the process of diagnosing cancer is to analyze the histopathological slides of the tissues, which is the most crucial and critical part of the diagnostic system. So, usually after visualizing some common symptoms, lab tests can be done. According to medical experts, one of the manual methods of diagnosing cancer is to perform FNAC at the first stage and a thorough histopathological analysis of the slides, that is, the study of tissues by microscopic view to detect the disease under the supervision of a medical expert.

During this histopathology process, the doctor uses certain patterns like the horizontal and vertical zigzag to analyze the tissues on the slides. However, by choosing certain designs on sample slides rather than the entire slide, some important information may be missing, contributing to polarity results. Therefore, the results or the results are less precise. And this is where automation comes in to eradicate human prejudice and error. Therefore, it can help in precision medicine and can lead to better selection of treatment protocols. Maybe an augmented or artificial intelligent model can deliver more accurate results in less time.

How to develop an AI-based self-diagnostic system to detect malignant or non-malignant tissue and their type in the body of an animal?

Automation: For an AI-based solution, the information on the histopathology slides must first be digitized. Sample slide images should be converted to a digital version and saved as an EHR (Electronic Health Record). This digital information (an image or a pattern) from histopathology slides will be analyzed using heuristics and biological parameters (collected from medical experts). The digital images of the EHR can be used as input for the self-diagnostic system and subsequently to classify malignant and non-malignant tissue. For critical cases, additional information such as ultrasound images and x-ray images may be taken into account.

A holistic approach for the development of an AI-based self-diagnostic system to detect malignant tissues and their type in the body of an animal has been proposed in the figure below:

Using a deep learning (DL) model, a corpus of benign / malignant tumor images are collected and provided as input to the model to detect genetic and molecular tumor cells and their alterations. Once an image of a patient’s histopathological slides is analyzed, its characteristics are extracted and classified. The morphological analysis of the tumor cells is observed and matched with the learning corpus. Vital biological statistics are combined with the knowledge base of all types of lymphoma (cancer type) to validate the results for additional or supportive information.

This is just a glimpse of one kind of AI-based solution to saving animals’ lives from deadly diseases like cancer (lymphoma). There are many ways and areas of using the latest technology to improve animal life with the right focus.

Research Perspective

Research carried out at the interface between AI and animal health requires strong interactions between the fields of animal biology, namely infectious diseases, immunology, clinical sciences, the study of genomes, epidemiology. and veterinary sciences, and data science fields such as data analysis, statistics, precision medicine. , drug discovery, predictive models and reasoning, in collaboration with highly efficient veterinary medical experts.

Research, training and support needs are crucial issues at national, European and international levels. In addition, a facilitated and reliable connection is required between researchers, medical experts and technology industry partners, who are often the holders or collectors of data of interest to resolve animal health research questions ( AH) via AI approaches.


The time and money invested in research, development and clinical trials of cancer drugs has increased steadily over the past decades. Despite record rates of cancer research and drug approval, cancer remains one of the leading causes of death. The use of the latest technologies in the field of animal health (AS) is marginally low. Many animal lives can be saved by focusing on implementing life-saving technology solutions or by programming empathy for animals in veterinary health departments or hospitals.

With this article, I try to highlight the main areas that need urgent attention from the perception of technology to fight a deadly disease like cancer for all kinds of species.

The development of AI skills within the HA community is limited compared to the needs. The opportunities for collaboration with AI teams are limited because these teams are already in high demand. A training effort must be provided and generalized to ensure that HA researchers are well aware of the opportunities and limitations of AI and the limits and constraints of AI approaches. Finally, the current growth of AI now makes it possible to integrate the knowledge and points of view of the many players in the field of animal health and welfare more upstream.

However, this requires that AI and its actors accept to face the specificity and complexity of HA. The library of knowledge related to HA should not only be used for insight gains for the improvement of the human species and use this information to design and develop AI tools for animal health and improvement. animals.

* FNAC is a first diagnostic investigation which makes it possible to differentiate the malignant and benign nature of cancerous tissues.

Join our Discord server. Be part of an engaging online community. Join here.

Subscribe to our newsletter

Receive the latest updates and relevant offers by sharing your email.

Amarjeet Kaur

Amarjeet Kaur

Amarjeet Kaur is currently working as Sr. Data Science Manager in the Digital Healthcare department, JIO. She holds a PhD in Computer Science and Technology with specialization in Artificial Intelligence from SNDT Women’s University, Mumbai, India, 2021. She also holds a Diploma and Masters in Computer Science and Engineering. Some of her accomplishments include the Young Researcher Award 2021, the Research Excellence Award 2021 from the Institute of Scholars, the Women in AI Leadership Award 2020: by Analytics India Magazine, the best research paper award at the IEEE international conference ‘ 17 in Computational Intelligence, awarded the Gold Medal for Outstanding Performance in Academics., Research Project Grant by Ministry of Science and Technology, Government of India. She has worked in various fields with over 11 years of research experience and excellent academic qualifications. She worked as a clinical research and development scientist at Tata Memorial Hospital, AI, in the health field. She also worked as Innovation Manager, Maker’s Lab, a unique Thin-q-Bator space, an R&D arm of Tech Mahindra Ltd., in Bengaluru, India. She was part of the WINnovate (Women in Innovation) group to motivate women to break the glass ceiling and explore growing possibilities. Expertise in experimentation, applied research and project management. She is currently focusing on artificial intelligence, natural language speech and text processing, machine learning, and predictive modeling.


Comments are closed.