Recent trends in stem cell-based therapies and applications of artificial intelligence in regenerative medicine

Table 1 Summary of the clinical applications of different types of stem cells

Type of stem cell	Discovery time	Source	Advantages	Disadvantages	Clinical applications and prospects
Embryonic stem cells	mESC was first derived in 1980 by Evans and Kaufman[33] in the United Kingdom and Martin[34] in the United States. hESC was derived by Thomson et al[22] isolated from preimplantation blastocysts in 1998	ICM of embryo	Maximum potency and these cells have the potential to differentiate into any cell type of the body	Ethical concerns, risk of developing teratomas and tumors when these undifferentiated cells are implanted in vivo[44-47]	Spinal cord injury[54], macular degeneration[55-58], diabetes mellitus[59], ischemic heart disease[60]
Induced pluripotent stem cells	Induced pluripotent stem cells were first successfully generated by Takahashi and Yamanaka[64] in 2006	Fibroblast cells	These cells have the potential to differentiate into any cell type of the body. Overcomes the ethical concerns associated with embryonic stem cell research and clinical use. Organoid formation, and scope for personalized therapies	Genomic instability, carcinogenicity, immunological rejection	Macular degeneration[81] and Parkinson's disease[89]
Fetal stem cells	First isolated and cultured by John Gearhart and his team at the Johns Hopkins University School of Medicine in 1998[185]	Umbilical cord blood cells	High availability and reduced ethical concerns. Higher expansion rate. Possess osteogenic differentiation capabilities. Produce 2.5-fold more insulin than bone marrow derived cells	May not have adipogenic potential	Pancreatic islet cell generation in vitro. GvHD and systemic lupus erythematosus
		Amniotic fluid and placenta	Harvested with minimal invasiveness	No clinical trials have yet been conducted to assess the safety and effectiveness of these stem cells	Potential treatment for nerve injuries or neuronal degenerative diseases. Bladder regeneration, kidney, lung, heart, heart valve, diaphragm, bone, cartilage and blood vessel formation. Treatment for skin and ocular diseases, inflammatory bowel disease, lung injuries, cartilage defects, Duchenne muscular dystrophy, and stroke. Also used in peripheral nerve regeneration
Adult stem cells
Hematopoietic stem cells	First discovered for clinical use in mice in 1950’s and for clinical use in human in 1970[186,187]	Bone marrow	Multipotent cells	Risks of GvHD[110]. Risks of bloodstream infections caused by Gram-negative bacteria associated with allogeneic hematopoietic transplantation[111,112]. Hemorrhagic cystitis is another complication that has been reported in patients post hematopoietic stem cell transplantation[113]	Hematopoietic stem cell transplantation is used as therapy for several malignant and non-malignant disorders and autoimmune diseases. These cells are also used for the recovery of patients undergoing chemotherapy and radiotherapy[108]
Mesenchymal stem cells	First derived in 1970 and first report of clinical use in 2004[188]	Bone marrow	Potential to differentiate osteocytes, chondrocytes, adipocyte. Multipotentiality, immunomodulatory, anti-inflammatory, efficient homing capacity to injured sites, and minimum ethical issues[121-123]	Procurement of cells from this source is often painful and carries the risk of infection. Cell yield and differentiation potential is dependent on donor characteristics	Generation of pancreatic cells in vitro. Orthopedic conditions characterized by large bone defects, including articular cartilage repair and osteoarthritis, rheumatoid arthritis. BM-MSCs may also be used to treat non-unions, osteonecrosis of the femoral head and to promote growth in osteogenesis imperfecta. Potentially promising treatment for myocardial infarction, GvHD, systemic lupus erythematosus and multiple sclerosis
	First derived in 2001[185]	Adipose tissue isolated from liposuction, lipoplasty or lipectomy materials	This source results in the isolation of up to 500 times more stem cells than BM (5 × 103 cells from 1 g of AT). AT is accessible and abundant and secretes several angiogenic and antiapoptotic cytokines. The immunosuppressive effects of AT-MSCs are stronger than those of BM-MSCs	Cells from this source have inferior osteogenic and chondrogenic potential in comparison to BM-MSCs	Immunosuppressive GvHD therapy. Potential for cell-based therapy for radiculopathy, myocardial infarction, and neuropathic pain. Cosmetic/dermatological applications. Successfully used in the treatment of skeletal muscle-injuries, meniscus damage and tendon, rotator cuff and peripheral nerve regeneration

AT: Adipose tissue; AT-MSCs: Adipose-tissue derived mesenchymal stem cells; BM-MSCs: Bone marrow derived mesenchymal stem cells; GvDH: Graft vs host disease; hESC: Human embryonic stem cell; ICM: Inner cell mass; mESC: Mouse embryonic stem cell.

Table 2 Status of mesenchymal cell-based therapies for different diseases

Disease category	Target disease	Clinical trial phase	Cell source	Company	Product name	ID No.	Status
GvHD	GvHD	Phase III	Mesenchymal stem cells (allogenic bone marrow derived)	Osiris Therapeutics	Prochymal	NCT00366145	Approved via Notice of Compliance with conditions (NOC/c)[32]
	Pediatric (GvHD, Grade III and IV)	Phase III	Mesenchymal stem cells (allogenic bone marrow derived)	Mesoblast	Remestemcel-L (Ryoncil™)	NCT02336230	Prescription Drug User Fee Act (PDUFA) set by US FDA action and Remestemcel-L will be commercially available in the United States (if approved)[124,139-141]
Crohn’s disease		Phase III	Autologous AT-MSC	Cellerix	-	NCT00475410	Completed in 2009 but failed
		Phase III	Allogenic, AT-MSC	TiGenix	Alofisel®	NCT01541579	Approved in 2018, by the European Medicines Agency[142, 143]
Cardiovascular diseases	Chronic advanced ischemic heart failure	Phase III	Autologous BM-MSC	-	-	NCT01768702	Beneficial but not approved yet, further studies need to be undertaken[144-146]
Autoimmune diseases	Systemic lupus erythematosus	Phase I/II	Allogenic BM-MSC, UC-MSC	-	-	NCT01741857, NCT00698191	Ongoing[147,148]
	Type I diabetes	Phase I/II	Allogenic, UC-MSC combined with aulogous BM-MSC	-	-	NCT01374854	Ongoing[149]
Neurodegenerative diseases	Parkinson’s disease	Phase I/II	Allogenic BM-MSC	-	-	NCT02611167	Completed but more interventional studies underway[150]
	Alzheimer’s disease	Phase I	Allogenic UC MSC, Longeveron MSC, BM MSC	-	-	NCT04040348, NCT02600130, NCT02600130	Ongoing[151]
SARS-CoV-2	COVID-19	Phase II/III	BM-MSC, AT-MSC, Placenta derived MSC	Mesoblast, Athersys; Tigenix/Takeda; Pluristem	MultiStem; SPECELL		Ongoing[136,152]

AT-MSC: Adipose-tissue derived mesenchymal stem cells; BM-MSC: Bone marrow derived mesenchymal stem cells; COVID19: Coronavirus-induced disease 2019; SARSCoV-2: Severe acute respiratory distress syndrome coronavirus-2; UC-MSC: Umbilical cord derived mesenchymal stem cells.

Table 3 Summary of recent artificial intelligence-based stem cells therapies

Study objectives	Applied AI algorithm	Important conclusions	Study group
iPSC-derived endothelial cells Identification without the application of molecular labelling using CNN	CNN	Prediction accuracy was a function of pixel size of the images and network depth. The k-fold cross validation suggested that morphological features alone could be enough for optimizing CNNs and they can deliver a high value prediction	Kusumoto and Yuasa[167] (2019)
Automated identification of the iPSC colony images quality	SVM, k-NN	k-NN yielded 62% of the accuracy which was found to be better than the previous studies of that time	Joutsijoki et al[168] (2016)
Assess automated texture descriptors of segmented colony regions of iPSCs and to check their potential	SVM, RF, MLP, Adaboost, DT	SVM, RF and Adaboost classifiers were concluded to exhibit superior classification ability than MLP and DT	Kavitha et al[169] (2018)
Develop a V-CNN model to distinguish the colony-characteristics on the basis of extracted descriptors of the iPSC colony	CNN	Recall, precision, and F-measure values by CNN were found to be comparatively much higher than the SVM. Colony quality accuracy was found to be 95.5% (morphological), 91.0% (textural) and 93.2% (textural)	Kavitha et al[170] (2017)
Use CNNs with transmitted light microscopy images to find out pluripotent stem cells from initial differentiating cells	CNN	CNN can be trained to distinguish among differentiated and undifferentiated cells with an accuracy of 99%	Waisman et al[172] (2019)
Use machine learning algorithms to analyze drug effects on iPSC cardiomyocytes	NB, KNN, LS-SVM, DT, multinomial logistic regression	Classification accuracy of the algorithm developed was found to be nearly 79%	Juhola et al[173] (2021)
To build an analytical procedure for automatic evaluation of Ca2+ transient abnormality, by applying SVM together with an analytical algorithm	SVM	The training and test accuracies were found to be 88% and 87% respectively	Hwang et al[175] (2020)
To develop a linear classification-learning model to differentiate among somatic cells, iPSCs, ESCs, and ECCs on the basis of their DNA methylation profiles	Jubatus (ML analytical platform)	The accuracy of the ML model in identifying various cell types was found to be 94.23%. Also, component analysis of the learned models identified the distinct epigenetic signatures of the iPSCs	Nishino et al[176] (2021)

AI: Artificial intelligence; CNN: Convolution neural network; DT: Decision tree; ECCs: Embryonal carcinoma cells; ESCs: Embryonic stem cells; iPSC: Induced pluripotent stem cells; k-NN: K-nearest neighbor; LS-SVM: Least-squares support-vector machines; MLP: Multilayer perceptron; RF: Random forest; SVM: Support vector machine.