ABSTRACT
The development of artificial intelligence and machine learning algorithms may allow for advances in patient care. There are existing and potential applications in cancer diagnosis and monitoring, identification of at-risk groups of individuals, classification of genetic variants, and even prediction of patient ancestry. This article provides an overview of some current and future applications of artificial intelligence in genomic medicine, in addition to discussing challenges and considerations when bringing these tools into clinical practice.
Subject(s)
Algorithms , Artificial Intelligence , Humans , Machine Learning , GenomicsABSTRACT
Semiconductor quantum dots (QDs) are attractive fluorescent contrast agents for in vivo imaging due to their superior photophysical properties, but traditional QDs comprise toxic materials such as cadmium or lead. Copper indium sulfide (CuInS2, CIS) QDs have been posited as a nontoxic and potentially clinically translatable alternative; however, previous in vivo studies utilized particles with a passivating zinc sulfide (ZnS) shell, limiting direct evidence of the biocompatibility of the underlying CIS. For the first time, we assess the biodistribution and toxicity of unshelled CIS and partially zinc-alloyed CISZ QDs in a murine model. We show that bare CIS QDs breakdown quickly, inducing significant toxicity as seen in organ weight, blood chemistry, and histology. CISZ demonstrates significant, but lower, toxicity compared to bare CIS, while our measurements of core/shell CIS/ZnS are consistent with literature reports of general biocompatibility. In vitro cytotoxicity is dose-dependent on the amount of metal released due to particle degradation, linking degradation to toxicity. These results challenge the assumption that removing heavy metals necessarily reduces toxicity: indeed, we find comparable in vitro cytotoxicity between CIS and CdSe QDs, while CIS caused severe toxicity in vivo compared to CdSe. In addition to highlighting the complexity of nanotoxicity and the differences between the in vitro and in vivo outcomes, these unexpected results serve as a reminder of the importance of assessing the biocompatibility of core QDs absent the protective ZnS shell when making specific claims of compositional biocompatibility.
Subject(s)
Copper , Cytotoxins , Indium , Quantum Dots , Sulfides , Animals , Copper/chemistry , Copper/pharmacokinetics , Copper/pharmacology , Cytotoxins/chemistry , Cytotoxins/pharmacokinetics , Cytotoxins/pharmacology , Dose-Response Relationship, Drug , Female , Hep G2 Cells , Humans , Indium/chemistry , Indium/pharmacokinetics , Indium/pharmacology , Mice , Mice, Inbred BALB C , Quantum Dots/chemistry , Quantum Dots/therapeutic use , Sulfides/chemistry , Sulfides/pharmacokinetics , Sulfides/pharmacologyABSTRACT
Emerging applications of machine learning and artificial intelligence offer the opportunity to discover new clinical knowledge through secondary exploration of existing patient medical records. This new knowledge may in turn offer a foundation to build new types of clinical decision support (CDS) that provide patient-specific insights and guidance across a wide range of clinical questions and settings. This article will provide an overview of these emerging approaches to CDS, discussing both existing technologies as well as challenges that health systems and informaticists will need to address to allow these emerging approaches to reach their full potential.
Subject(s)
Clinical Laboratory Information Systems/organization & administration , Decision Support Systems, Clinical , Machine Learning , HumansABSTRACT
OBJECTIVES: Laboratory-based utilization management programs typically rely primarily on data derived from the laboratory information system to analyze testing volumes for trends and utilization concerns. We wished to examine the ability of an electronic health record (EHR) laboratory orders database to improve a laboratory utilization program. METHODS: We obtained a daily file from our EHR containing data related to laboratory test ordering. We then used an automated process to import this file into a database to facilitate self-service queries and analysis. RESULTS: The EHR laboratory orders database has proven to be an important addition to our utilization management program. We provide three representative examples of how the EHR laboratory orders database has been used to address common utilization issues. We demonstrate that analysis of EHR laboratory orders data has been able to provide unique insights that cannot be obtained by review of laboratory information system data alone. Further, we provide recommendations on key EHR data fields of importance to laboratory utilization efforts. CONCLUSION: We demonstrate that an EHR laboratory orders database may be a useful tool in the monitoring and optimization of laboratory testing. We recommend that health care systems develop and maintain a database of EHR laboratory orders data and integrate this data with their laboratory utilization programs.
Subject(s)
Clinical Laboratory Techniques , Databases, Factual , Electronic Health Records , Research Design , HumansABSTRACT
OBJECTIVES: To assess the ability of flow cytometry (FC) to detect putative neoplastic T-cell subsets on skin shave biopsy (SSB) specimens from patients with mycosis fungoides (MF) and to study the immunophenotype of skin-infiltrating tumor cells in MF. METHODS: SSB specimens from patients with suspected MF were bisected and submitted for both FC and routine histopathology. Six-dimensional gating strategies were applied to identify putative neoplastic cells, independently from their expected immunophenotype. RESULTS: Aberrant T cells were detected by FC in 18 of 33 SBB specimens, of which all had clinicomorphologic features of MF. Of the remaining 15 SSB specimens, six had clinicomorphologic features of MF and nine were diagnosed with benign inflammatory dermatoses. Unexpectedly, CD26 was aberrantly overexpressed in 11 (73%) and lost in three (20%) of 15 SSB specimens from patients with MF where this antigen was evaluated. Other detected aberrancies included CD3 dim- (13/18 [72%]), CD7 dim- (15/18 [83%]), and CD4-/CD8- (3/18 [17%]). CONCLUSIONS: FC is capable of identifying putative neoplastic cells on SSB specimens from patients with MF. Bright homogeneous CD26 expression is a common and previously undescribed immunophenotypic aberrancy on MF skin infiltrates.