ArticlePDF Available

Deep learning revolutionizes healthcare and precision medicine: the next wave of artificial intelligence applications in biomedicine

Authors:
computer methods and programs in biomedicine 138 (2016) A1A2
journal homepage: www.intl.elsevierhealth.com/journals/cmpb
Editorial
Deep learning revolutionizes healthcare and
precision medicine: the next wave of articial
intelligence applications in biomedicine
Deep learning techniques and tools have advanced applica-
tions of articial intelligence in many elds including bio-
medicine. The editors’ choice articles in this month all
incorporated these techniques to facilitate healthcare and
precision medicine.
The rst editors’ choice,Automated diagnosis of coronary
artery disease (CAD) patients using optimized SVM [1],” pre-
sents a CAD detection method using heart rate variability
(HRV) signals from electrocardiogram (ECG). First, HRV fea-
tures in time, frequency, and nonlinear domains from both
CAD patients and normal controls were extracted. After that,
principal component analysis (PCA) was applied to reduce
feature dimension and reveal hidden information underlay in
the data. Finally, deep learning techniques combined with
support vector machine (SVM) classier were incorporated to
detect CAD. Davari et al. demonstrated that the proposed
method achieved 99.2%, 98.4%, and 100% in accuracy, sensi-
tivity, and specicity, respectively. Moreover, it performed fast
without sacricing its diagnosis power using only eleven
reduced HRV signals. Combined with mobile systems, this
study can be used to save the lives of CAD patients in the
future.
For healthcare implementation, Kanda et al. proposed a novel
study to depict the inuence of alpha rhythm on eyes-closed-
awake electroencephalogram (EEG) epoch selection in “EEG
epochs with less alpha rhythm improve discrimination of
mild Alzheimer’s [2].” EEG epochs were rst divided as domi-
nant alpha scenario and rare alpha scenario according to the
percentage of alpha waves. Then, the probands are classied
into four groups: dominant alpha scenario controls, mild
Alzheimer’s patients with dominant alpha scenario, rare
alpha scenario healthy elderly, and mild Alzheimer’s patients
with rare alpha scenario. Group differences using one-way
ANOVA tests were calculated followed by post-hoc multiple
comparisons. Surprisingly, signicant differences were found
between mild Alzheimer’s patients and healthy elderly only
for the rare alpha scenario. Experiment results revealed that,
contrarily to what was expected, less synchronized EEG
epochs better discriminated mild Alzheimer’s than those pre-
senting abundant alpha. These novel ndings can provide
epoch selection strategies for Alzheimer’s studies dealing
with resting state EEG.
As for precision medicine, Rubio-Camarillo et al. developed an
integrated next-generation sequencing (NGS) analysis system
in “RUbioSeq+: a multiplatform application that executes
parallelized pipelines to analyse next-generation sequencing
data [3].” The authors selected well-established software
to construct pipelines for DNA-seq, CNA-seq, bisulteseq,
and ChIP-seq experiments. This new extended version of
RUbioSeq not only improved parallelized and multithreaded
execution options, but also included pairwise case-control
comparison analyses and an interactive graphical user inter-
face (GUI) that facilitates biomedical researchers. Moreover,
RUbioSeq+ is freely available for public use, and the generated
results have been experimentally validated and accepted for
publication. This new system can automate NGS analysis,
reduce human errors, and improve the reproducibility of
deep-sequencing studies.
The above editors’ choice articles utilized deep learning tech-
niques in detection of CAD, discrimination of mild Alzheim-
er’s, and automated analysis of NGS data. In the future, this
fast-growing eld will generate more exciting advances in
biomedical and health informatics.
REFERENCES
[1] A. Davari Dolatabadi, S.E.Z. Khadem, Automated Diagnosis
of Coronary Artery Disease (CAD) Patients Using Optimized
SVM. Comput. Methods Programs Biomed. 138 (2017)
117–126.
[2] P.A.M. Kanda, E.F. Oliveira, F.J. Fraga, EEG epochs with less
alpha rhythm improve discrimination of mild Alzheimer's.
Comput. Methods Programs Biomed. 138 (2017) 13–22.
[3] M. Rubio-Camarillo, H. López-Fernández, G. Gómez-López,
Á. Carro, J.M. Fernández, C. Fustero Torre, et al., RUbioSeq+:
A multiplatform application that executes parallelized
pipelines to analyse next-generation sequencing data.
Comput. Methods Programs Biomed. 138 (2017) 73–81.
A2        () AA
Emily Chia-Yu Sua
aGraduate Institute of Biomedical Informatics,
College of Medicine Science and Technology, Taipei Medical
University, Taipei, Taiwan
Usman Iqbalb,c
bMaster Program in Global Health and Development, College of
Public Health, Taipei Medical University, Taipei, Taiwan
cInternational Center for Health Information Technology (ICHIT),
Taipei Medical University, Taipei, Taiwan
Yu-Chuan (Jack) Lia,c,d,*
aGraduate Institute of Biomedical Informatics, College of Medicine
Science and Technology, Taipei Medical University, Taipei, Taiwan
cInternational Center for Health Information Technology (ICHIT),
Taipei Medical University, Taipei, Taiwan
dChair, Dept. of Dermatology, Wan Fang Hospital, Taipei, Taiwan
*Corresponding author at: 250- Wuxing Street, Xinyi District,
Taipei 11031, Taiwan. Fax: +886 2 6638 7537.
E-mail address: jack@tmu.edu.tw; jaak88@gmail.com
(Y.-C. Li).
ResearchGate has not been able to resolve any citations for this publication.
ResearchGate has not been able to resolve any references for this publication.