Personalisation in Cancer Care: In Discovery of a Middle Ground

separator

Onco-pathology has arguably been the centre of innovation within diagnostics. From undergoing a digital revolution to integrating genomic analysis, a deeper understanding of various causes and their interactions has emerged, helping clinicians tailor treatment measures and deal with recurrence.

Specialised approaches that involve immunohistochemistry (IHC), molecular studies and cytogenetics, demand expertise and highly specialised equipment, which cannot be found consistently across all diagnostic facilities. It is true that personalised medicine and precision diagnostics is the future of healthcare. However the developing world needs a strategic allocation of medical capacity, as the resources are scarce and the health needs are alarming.

Here, it is important to differentiate cancers on the basis of diagnosis, into two categories: those that can be diagnosed by routine procedures and those that require the above mentioned specialised approaches, which are of investigative and prognostic value. While most cancers are diagnosed by morphological analysis accompanied with IHC and flow cytometry, certain haematological malignancies and solid cancers demand specialised testing.

Pressing Needs

There is a lack of awareness regarding cancer symptomatology in both rural and urban areas. The dearth of specialised medical facilities, shortage of medical professionals and late clinical presentation of symptoms result in ineffective treatment outcomes. For example, patients with lung cancer, for whom early detection and treatment is critical, were diagnosed with tuberculosis, according to a survey on tertiary healthcare centres. This was due to the absence of experienced clinicians and basic lab facilities.

To circumvent these obstacles, digitisation of patients’ samples and the sharing of medical data to doctors across borders, will facilitate faster and accurate diagnosis for the delivery of immediate care. A recent research study illustrates how medical centres in sub-Saharan Africa are combating prostate cancer mortality rates by using digital pathology to deliver an early diagnosis.

Technical innovations that combine artificial intelligence with digital pathology are being viewed as a strong clinical decision support tool. They provide detailed and insightful reports which will bring specificity in diagnosis.

Facilitating Integrated Diagnostics

Malignancies such as acute and chronic leukaemia, lymphomas, neoplasms of the central nervous system and other solid cancers, are exacting to diagnose as they require molecular and genomic analysis, in addition to routine testing. Differential diagnoses and the identification of treatment options require specialised medical experts to carry out tests, which provide details on genetic anomalies and molecular typing. The results will empower pathologists to give specific diagnoses and clinicians to implement effective treatment measures.

Consider Acute Myeloid Leukaemia (AML), a haematological malignancy that requires swift medical attention. Molecular typing along with flow cytometry is required to categorise AML. All subtypes of AML are given induction chemotherapy, with drugs such as anthracycline and cytarabine, with the exception of Acute Promyelocytic Leukaemia (APL). APL is the only subtype of AML that responds to targeted therapy with all-trans-retinoic acid (ATRA). Hence, determining the subtype of AML is essential as it determines treatment procedures.

The role of smart solutions is completely different from that of routine cancer diagnostics. Firstly, it will help clinicians to decide if specialised testing is required. If so, smart solutions can collate molecular and genomic data to give a comprehensive diagnostic profile, enabling clinicians to decide the course of treatment.

Secondly, it will facilitate cross-comparison between different test results, paving the path for the personalisation of treatment and better treatment outcomes. Recent studies have shown that smart solutions provide insights into tumour growth patterns and response to treatment. These innovations will help tailor treatments ushering in patient-centricity in cancer care.

Finally, it will enable faster and efficient healthcare delivery. Routine screening procedures can be administered to patients who require them and specialised and personalised care can be invested in difficult and complex cases.

In this manner, artificial intelligence can help us discover the middle ground between generalised approaches and highly specific measures, emboldening clinicians to mitigate issues in cancer diagnosis and treatment.

References

Sachdeva, Ruchi, and Sandeep Sachdeva. “Delay in diagnosis amongst carcinoma lung patients presenting at a tertiary respiratory centre.” Clinical Cancer Investigation Journal 3.4 (2014): 288.

Farré, Xavier, and Joshua Kibera. “The untapped potential of digital pathology in prostate cancer diagnosis and medical education in sub-Saharan Africa.” African Journal of Urology 24.1 (2018): 54-55.

Castaneda, Christian, et al. “Clinical decision support systems for improving diagnostic accuracy and achieving precision medicine.” Journal of clinical bioinformatics 5.1 (2015): 4.

Jansen, Ilaria, et al. “Histopathology: ditch the slides, because digital and 3D are on show.” World journal of urology 36.4 (2018): 549-555.