These days, numerous medical services versatile applications are widely utilized which should be charged by the end-clients with paying BTC-cryptocurrency. These portable applications make a major organization of hubs towards the idea of Internet of Medical Things (IoMT) with basic security prerequisites that ought to be truly examined. Since its commencement in 2009, BTC-cryptocurrency has been buried in debates for giving a safe house to criminal operations. A few kinds of illegal clients take cover of secrecy. Discovering these elements is key for scientific examinations. Latest strategies use AI for distinguishing these illegal elements. In any case, the current methodologies just spotlight on a restricted class of illegal clients. This paper addresses by executing a troupe of choice trees for managed learning. Extra boundaries permit the outfit system to pick up segregating highlights that can order numerous gatherings of illegal clients from licit clients. To assess the system, data of 1216 genuine elements on BTC-cryptocurrency was separated that were on the distributed ledger technology. Nine features were designed to prepare the system for isolating 16 diverse licit-unlawful classifications of clients. The implemented system gave a solid instrument to legal examination. Experimental assessment of the system opposite testing systems was done to feature its adequacy. Examinations proved particularity and affectability of the implemented system were similar to different systems. Computer chip and random-access memory use were additionally checked to show the value of the implemented work for true arrangement. © 2021, The Author(s), under exclusive licence to Springer-Verlag London Ltd., part of Springer Nature.